diff --git a/(docs)/fr/docs/applied_prompting/build_chatbot_from_kb/page.mdx b/(docs)/fr/docs/applied_prompting/build_chatbot_from_kb/page.mdx index ec09f93ed72..db320f9ad0b 100644 --- a/(docs)/fr/docs/applied_prompting/build_chatbot_from_kb/page.mdx +++ b/(docs)/fr/docs/applied_prompting/build_chatbot_from_kb/page.mdx @@ -1,15 +1,15 @@ export const metadata = { sidebar_position: 40, - title: "đą Chatbot + Knowledge Base", + title: "đą Chatbot + Base de Connaissances", }; -# đą Chatbot + Knowledge Base +# đą Chatbot + Base de Connaissances -Recent advancements in large language models (LLMs) such as [GPT-3](https://arxiv.org/abs/2005.14165) and [ChatGPT](https://chat.openai.com/chat) have created a lot of buzz in the tech industry. These models are incredibly powerful for content generation, but they also have some downsides such as bias(@nadeem-etal-2021-stereoset) and hallucinations(@Ji_2022). One area in which these LLMs can be particularly useful is chatbot development. +Les rĂ©centes avancĂ©es dans les grands modĂšles de langage (LLMs) tels que [GPT-3](https://arxiv.org/abs/2005.14165) et [ChatGPT](https://chat.openai.com/chat) ont créé beaucoup d'enthousiasme dans l'industrie technologique. Ces modĂšles sont incroyablement puissants pour la gĂ©nĂ©ration de contenu, mais ils prĂ©sentent Ă©galement certains inconvĂ©nients comme des biais(@nadeem-etal-2021-stereoset) et des hallucinations(@Ji_2022). Un domaine dans lequel ces LLMs peuvent ĂȘtre particuliĂšrement utiles est le dĂ©veloppement de chatbots. -## Intent-Based Chatbots +## Chatbots basĂ©s sur l'intention -Traditional chatbots are typically intent-based, meaning they are designed to respond to specific user intents. Each intent is made up of a set of sample questions and an associated response. For example, the intent âWeatherâ might include sample questions like âWhatâs the weather today?â or âWill it rain today?â and a response like âToday will be sunny.â When a user asks a question, the chatbot matches it to the intent with the most similar sample questions and returns the associated response. +Les chatbots traditionnels sont gĂ©nĂ©ralement basĂ©s sur l'intention, ce qui signifie qu'ils sont conçus pour rĂ©pondre Ă des intentions spĂ©cifiques de l'utilisateur. Chaque intention est composĂ©e d'un ensemble de questions types et d'une rĂ©ponse associĂ©e. Par exemple, l'intention "MĂ©tĂ©o" pourrait inclure des questions comme "Quel temps fait-il aujourd'hui ?" ou "Va-t-il pleuvoir aujourd'hui ?" et une rĂ©ponse comme "Aujourd'hui sera ensoleillĂ©." Lorsqu'un utilisateur pose une question, le chatbot l'associe Ă l'intention dont les questions types sont les plus similaires et renvoie la rĂ©ponse associĂ©e.
- How a traditional intent-based chatbot works. Image by the author. + Comment fonctionne un chatbot traditionnel basé sur l'intention. Image par l'auteur.
- How a chatbot leveraging GPT-3 could work. Image by the author. + Comment pourrait fonctionner un chatbot utilisant GPT-3. Image par l'auteur.
- How a chatbot leveraging GPT-3 could work. GPT-3 could be used to generate - an appropriate answer leveraging the information from knowledge base - documents. Image by the author. + Comment pourrait fonctionner un chatbot utilisant GPT-3. GPT-3 pourrait ĂȘtre utilisĂ© pour gĂ©nĂ©rer + une rĂ©ponse appropriĂ©e en s'appuyant sur les informations des documents de la base de connaissances. + Image par l'auteur.
- Information used to craft our GPT-3 prompt. Image by the author. + Informations utilisées pour élaborer notre prompt GPT-3. Image par l'auteur.
- As an advanced chatbot named Skippy, your primary goal is to assist users to
- the best of your ability.
+ En tant que chatbot avancé nommé Skippy, votre objectif principal est d'aider les utilisateurs du mieux que vous le pouvez.
-Then, suppose the semantic search step extracts the following document from our knowledge base. All the documents describe how the VideoGram product works, which is an imaginary product similar to Instagram, but only for videos.
+Ensuite, supposons que l'étape de recherche sémantique extrait le document suivant de notre base de connaissances. Tous les documents décrivent comment le produit VideoGram fonctionne, qui est un produit imaginaire similaire à Instagram, mais uniquement pour les vidéos.
- A document explaining how login to VideoGram works. Image by the author. + Un document expliquant comment se connecter Ă VideoGram. Image par l'auteur.
- As an advanced chatbot named Skippy, your primary goal is to assist users to the best of your ability. + En tant que chatbot avancé nommé Skippy, votre objectif principal est d'aider les utilisateurs du mieux que vous le pouvez.-Last, we need to add the conversation and the user question to the end of the prompt, like in the following example. +Enfin, nous devons ajouter la conversation et la question de l'utilisateur à la fin du prompt, comme dans l'exemple suivant.
- START CONTEXT - Login to VideoGram from Website - 1. Open your web browser and go to the VideoGram website. - 2. Click on the âLoginâ button located in the top right corner of the page. - 3. On the login page, enter your VideoGram username and password. - 4. Once you have entered your credentials, click on the âLoginâ button. - 5. You should now be logged in to your VideoGram account. -
- Login to VideoGram from Mobile App - 1. Open the VideoGram app on your mobile device. - 2. On the main page, tap the âLoginâ button located in the bottom right corner. - 3. On the login page, enter your VideoGram username and password. - 4. Once you have entered your credentials, tap the âLoginâ button. - 5. You should now be logged in to your VideoGram account. - END CONTEXT + DĂBUT DE CONTEXTE + Connexion Ă VideoGram depuis le site web + 1. Ouvrez votre navigateur web et accĂ©dez au site web de VideoGram. + 2. Cliquez sur le bouton "Connexion" situĂ© dans le coin supĂ©rieur droit de la page. + 3. Sur la page de connexion, entrez votre nom d'utilisateur et votre mot de passe VideoGram. + 4. Une fois que vous avez saisi vos identifiants, cliquez sur le bouton "Connexion". + 5. Vous devriez maintenant ĂȘtre connectĂ© Ă votre compte VideoGram. +
+ Connexion Ă VideoGram depuis l'application mobile + 1. Ouvrez l'application VideoGram sur votre appareil mobile. + 2. Sur la page principale, appuyez sur le bouton "Connexion" situĂ© dans le coin infĂ©rieur droit. + 3. Sur la page de connexion, entrez votre nom d'utilisateur et votre mot de passe VideoGram. + 4. Une fois que vous avez saisi vos identifiants, appuyez sur le bouton "Connexion". + 5. Vous devriez maintenant ĂȘtre connectĂ© Ă votre compte VideoGram. + FIN DE CONTEXTE
- As an advanced chatbot named Skippy, your primary goal is to assist users to the best of your ability. --Passing this prompt to GPT-3, I got the following generated answer. +En passant ce prompt à GPT-3, j'ai obtenu la réponse générée suivante.
- START CONTEXT - Login to VideoGram from Website - 1. Open your web browser and go to the VideoGram website. - 2. Click on the âLoginâ button located in the top right corner of the page. - 3. On the login page, enter your VideoGram username and password. - 4. Once you have entered your credentials, click on the âLoginâ button. - 5. You should now be logged in to your VideoGram account. -
- Login to VideoGram from Mobile App - 1. Open the VideoGram app on your mobile device. - 2. On the main page, tap the âLoginâ button located in the bottom right corner. - 3. On the login page, enter your VideoGram username and password. - 4. Once you have entered your credentials, tap the âLoginâ button. - 5. You should now be logged in to your VideoGram account. - - END CONTEXT -
+ En tant que chatbot avancé nommé Skippy, votre objectif principal est d'aider les utilisateurs du mieux que vous le pouvez. +
+ DĂBUT DE CONTEXTE + Connexion Ă VideoGram depuis le site web + 1. Ouvrez votre navigateur web et accĂ©dez au site web de VideoGram. + 2. Cliquez sur le bouton "Connexion" situĂ© dans le coin supĂ©rieur droit de la page. + 3. Sur la page de connexion, entrez votre nom d'utilisateur et votre mot de passe VideoGram. + 4. Une fois que vous avez saisi vos identifiants, cliquez sur le bouton "Connexion". + 5. Vous devriez maintenant ĂȘtre connectĂ© Ă votre compte VideoGram. +
+ Connexion Ă VideoGram depuis l'application mobile + 1. Ouvrez l'application VideoGram sur votre appareil mobile. + 2. Sur la page principale, appuyez sur le bouton "Connexion" situĂ© dans le coin infĂ©rieur droit. + 3. Sur la page de connexion, entrez votre nom d'utilisateur et votre mot de passe VideoGram. + 4. Une fois que vous avez saisi vos identifiants, appuyez sur le bouton "Connexion". + 5. Vous devriez maintenant ĂȘtre connectĂ© Ă votre compte VideoGram. + FIN DE CONTEXTE +
- SKIPPY: Hello, Iâm Skippy! How can I help you? - USER: I canât find the login button. - SKIPPY: + SKIPPY : Bonjour, je m'appelle Skippy ! Comment puis-je vous aider ? + UTILISATEUR : Je ne trouve pas le bouton de connexion. + SKIPPY :
- No problem! On the website, the login button is located in the top right corner of the page. On the mobile app, the login button is located in the bottom right corner. Let me know if you need any further assistance!
+ Pas de problÚme ! Sur le site web, le bouton de connexion est situé dans le coin supérieur droit de la page. Sur l'application mobile, le bouton de connexion est situé dans le coin inférieur droit. N'hésitez pas à me demander si vous avez besoin d'autres informations !
-Notice how the information in the generated answer comes from the knowledge base document.
+Remarquez comment les informations dans la réponse générée proviennent du document de la base de connaissances.
-## Disambiguating Questions with GPT-3
+## Désambiguïsation des questions avec GPT-3
-Letâs try with a more vague user utterance, like âcanât loginâ. Hereâs the complete prompt.
+Essayons avec une expression d'utilisateur plus vague, comme "impossible de me connecter". Voici le prompt complet.
- As an advanced chatbot named Skippy, your primary goal is to assist users tothe best of your ability. --GPT-3 answers trying to understand better whatâs the problem of the user. +GPT-3 rĂ©pond en essayant de mieux comprendre quel est le problĂšme de l'utilisateur.
- START CONTEXT - Login to VideoGram from Website - 1. Open your web browser and go to the VideoGram website. - 2. Click on the âLoginâ button located in the top right corner of the page. - 3. On the login page, enter your VideoGram username and password. - 4. Once you have entered your credentials, click on the âLoginâ button. - 5. You should now be logged in to your VideoGram account. -
- Login to VideoGram from Mobile App - 1. Open the VideoGram app on your mobile device. - 2. On the main page, tap the âLoginâ button located in the bottom right corner. - 3. On the login page, enter your VideoGram username and password. - 4. Once you have entered your credentials, tap the âLoginâ button. - 5. You should now be logged in to your VideoGram account. - END CONTEXT -
- SKIPPY: Hello, Iâm Skippy! How can I help you? - USER: Canât login - SKIPPY: + En tant que chatbot avancĂ© nommĂ© Skippy, votre objectif principal est d'aider les utilisateurs du mieux que vous le pouvez. +
+ DĂBUT DE CONTEXTE + Connexion Ă VideoGram depuis le site web + 1. Ouvrez votre navigateur web et accĂ©dez au site web de VideoGram. + 2. Cliquez sur le bouton "Connexion" situĂ© dans le coin supĂ©rieur droit de la page. + 3. Sur la page de connexion, entrez votre nom d'utilisateur et votre mot de passe VideoGram. + 4. Une fois que vous avez saisi vos identifiants, cliquez sur le bouton "Connexion". + 5. Vous devriez maintenant ĂȘtre connectĂ© Ă votre compte VideoGram. +
+ Connexion Ă VideoGram depuis l'application mobile + 1. Ouvrez l'application VideoGram sur votre appareil mobile. + 2. Sur la page principale, appuyez sur le bouton "Connexion" situĂ© dans le coin infĂ©rieur droit. + 3. Sur la page de connexion, entrez votre nom d'utilisateur et votre mot de passe VideoGram. + 4. Une fois que vous avez saisi vos identifiants, appuyez sur le bouton "Connexion". + 5. Vous devriez maintenant ĂȘtre connectĂ© Ă votre compte VideoGram. + FIN DE CONTEXTE +
+ SKIPPY : Bonjour, je m'appelle Skippy ! Comment puis-je vous aider ? + UTILISATEUR : Impossible de me connecter + SKIPPY :
- Iâm sorry to hear that. Can you tell me if you are trying to login via the
- VideoGram website or mobile app?
+ Je suis désolé d'entendre cela. Pouvez-vous me dire si vous essayez de vous connecter via le site web de VideoGram ou via l'application mobile ?
-Next, hereâs how the complete conversation goes. The whole prompt is hidden for better visibility.
+Voici comment se déroule ensuite la conversation complÚte. Le prompt complet est masqué pour une meilleure visibilité.
- USER: Canât login + UTILISATEUR : Impossible de me connecter-GPT-3 can manage disambiguation, provided that it has the right contextual information. +GPT-3 peut gĂ©rer la dĂ©sambiguĂŻsation, Ă condition qu'il dispose des informations contextuelles appropriĂ©es. -## Problems With Generating Answers with GPT-3 +## ProblĂšmes avec la gĂ©nĂ©ration de rĂ©ponses avec GPT-3 -The previous examples worked well. However, there are several ways in which this chatbot could fail. +Les exemples prĂ©cĂ©dents ont bien fonctionnĂ©. Cependant, il existe plusieurs façons dont ce chatbot pourrait Ă©chouer. -If we ask âIs the mobile app free?â to GPT-3 passing the login document as context, youâd often get an answer like âYes, the VideoGram mobile app is free to download and useâ, even if such information is not contained in the context information. Generating false information is very bad for customer service chatbots! +Si nous demandons "L'application mobile est-elle gratuite ?" Ă GPT-3 en passant le document de connexion comme contexte, vous obtiendrez souvent une rĂ©ponse comme "Oui, l'application mobile VideoGram est gratuite Ă tĂ©lĂ©charger et Ă utiliser", mĂȘme si cette information n'est pas contenue dans le contexte. GĂ©nĂ©rer de fausses informations est trĂšs mauvais pour les chatbots de service client ! -GPT-3 rarely generates false information when the answer to the user question can be found in the context. As user questions are often short and ambiguous texts, we canât rely on the semantic search step to always retrieve a correct document, and so we are always vulnerable to false information generation. +GPT-3 gĂ©nĂšre rarement de fausses informations lorsque la rĂ©ponse Ă la question de l'utilisateur peut ĂȘtre trouvĂ©e dans le contexte. Comme les questions des utilisateurs sont souvent des textes courts et ambigus, nous ne pouvons pas compter sur l'Ă©tape de recherche sĂ©mantique pour toujours rĂ©cupĂ©rer un document correct, et nous sommes donc toujours vulnĂ©rables Ă la gĂ©nĂ©ration de fausses informations. ## Conclusion -GPT-3 is very useful for creating conversational chatbots and is able to answer a series of specific questions on the basis of contextual information inserted in the prompt. However, itâs hard to make the model produce answers leveraging only the information in the context, as the model tends to hallucinate (i.e. generating new information, potentially false). Generating false information is a problem of different severity depending on the use case. +GPT-3 est trĂšs utile pour crĂ©er des chatbots conversationnels et est capable de rĂ©pondre Ă une sĂ©rie de questions spĂ©cifiques sur la base d'informations contextuelles insĂ©rĂ©es dans le prompt. Cependant, il est difficile de faire en sorte que le modĂšle produise des rĂ©ponses s'appuyant uniquement sur les informations du contexte, car le modĂšle a tendance Ă halluciner (c'est-Ă -dire Ă gĂ©nĂ©rer de nouvelles informations, potentiellement fausses). GĂ©nĂ©rer de fausses informations est un problĂšme de gravitĂ© diffĂ©rente selon le cas d'utilisation. -Written by [Fabio Chiusano](https://www.linkedin.com/in/fabio-chiusano-b6a3b311b/). +Ăcrit par [Fabio Chiusano](https://www.linkedin.com/in/fabio-chiusano-b6a3b311b/). diff --git a/(docs)/fr/docs/applied_prompting/build_chatgpt/page.mdx b/(docs)/fr/docs/applied_prompting/build_chatgpt/page.mdx index a025e6ee142..e3a625a8d30 100644 --- a/(docs)/fr/docs/applied_prompting/build_chatgpt/page.mdx +++ b/(docs)/fr/docs/applied_prompting/build_chatgpt/page.mdx @@ -1,9 +1,9 @@ export const metadata = { sidebar_position: 4, - title: "đą Build ChatGPT from GPT-3", + title: "đą Construire ChatGPT Ă partir de GPT-3", }; -# đą Build ChatGPT from GPT-3 +# đą Construire ChatGPT Ă partir de GPT-3
- SKIPPY: Iâm sorry to hear that. Can you tell me if you are trying to login via - the VideoGram website or mobile app? + SKIPPY : Je suis dĂ©solĂ© d'entendre cela. Pouvez-vous me dire si vous essayez de vous connecter via le site web de VideoGram ou via l'application mobile ?
- USER: Mobile app + UTILISATEUR : Application mobile
- SKIPPY: OK, no problem. To login via the mobile app, open the VideoGram app - on your mobile device. On the main page, tap the âLoginâ button located in - the bottom right corner. On the login page, enter your VideoGram username - and password. Once you have entered your credentials, tap the âLoginâ - button. You should now be logged in to your VideoGram account. Please let me - know if you need any further assistance. + SKIPPY : D'accord, pas de problĂšme. Pour vous connecter via l'application mobile, ouvrez l'application VideoGram sur votre appareil mobile. Sur la page principale, appuyez sur le bouton "Connexion" situĂ© dans le coin infĂ©rieur droit. Sur la page de connexion, entrez votre nom d'utilisateur et votre mot de passe VideoGram. Une fois que vous avez saisi vos identifiants, appuyez sur le bouton "Connexion". Vous devriez maintenant ĂȘtre connectĂ© Ă votre compte VideoGram. N'hĂ©sitez pas Ă me faire savoir si vous avez besoin d'autres informations.
-Like other models in the GPT-3.5 series, ChatGPT was trained using [RLHF](https://huggingface.co/blog/rlhf), but much of it's effectiveness comes from using a **good prompt**. +Comme d'autres modÚles de la série GPT-3.5, ChatGPT a été entraßné en utilisant [RLHF](https://huggingface.co/blog/rlhf), mais une grande partie de son efficacité provient de l'utilisation d'un **bon prompt**. -## The Prompt +## Le Prompt@@ -38,7 +37,7 @@ This article was written in part because of a tweet by pic.twitter.com/9jHrs91VHW
- — Riley Goodside December 26, 2022 + — Riley Goodside 26 dĂ©cembre 2022
- Full Skippy chatbot prompt from article header + Prompt complet du chatbot Skippy de l'en-tĂȘte de l'article
- Example insertion of user prompt before sending to model + Exemple d'insertion du prompt utilisateur avant envoi au modĂšle
- Therapy chatbot prompt + Prompt du chatbot thérapeutique
@@ -146,7 +143,7 @@ GPT-3 is able to mimic a personality based on these entries. charset="utf-8" > -Prompt from the Tweet: +Prompt issu du Tweet: ```markdown The following is a conversation with Present Michelle (age [redacted]) and Young Michelle (age 14). @@ -157,46 +154,46 @@ Young Michelle has written the following journal entries: Present Michelle: [type your questions here] ``` -The author does note that diary entries can reach the token limit. In this case you could pick a select few entries or try to summarize several entries. +L'auteure note que les entrées du journal peuvent atteindre la limite de tokens. Dans ce cas, vous pourriez choisir quelques entrées spécifiques ou essayer de résumer plusieurs entrées. -## Implementation +## Implémentation -I will walk through coding a simple GPT-3 powered chatbot in Python. Including GPT-3 in an app you are building is incredibly easy using the OpenAI API. You will need to create an account on OpenAI and get an API key. Check out their docs here. +Je vais vous guider à travers la programmation d'un simple chatbot alimenté par GPT-3 en Python. Inclure GPT-3 dans une application que vous construisez est incroyablement facile en utilisant l'API OpenAI. Vous devrez créer un compte sur OpenAI et obtenir une clé API. Consultez leur documentation ici. -Overview of what we need to do: +Aperçu de ce que nous devons faire : -1. Format user input into a chatbot prompt for GPT-3 -2. Get the chatbot response as a completion from GPT-3 -3. Update the prompt with both the user's input and the chatbot's response -4. Loop +1. Formater l'entrée de l'utilisateur en un prompt de chatbot pour GPT-3 +2. Obtenir la réponse du chatbot sous forme de complétion de GPT-3 +3. Mettre à jour le prompt avec à la fois l'entrée de l'utilisateur et la réponse du chatbot +4. Boucler -Here is the prompt I will use. We can use python to replace \
and \ with their actual values. +Voici le prompt que j'utiliserai. Nous pouvons utiliser Python pour remplacer \ et \ par leurs valeurs rĂ©elles. ```python chatbot_prompt = """ - As an advanced chatbot, your primary goal is to assist users to the best of your ability. This may involve answering questions, providing helpful information, or completing tasks based on user input. In order to effectively assist users, it is important to be detailed and thorough in your responses. Use examples and evidence to support your points and justify your recommendations or solutions. + En tant que chatbot avancĂ©, votre objectif principal est d'aider les utilisateurs au mieux de vos capacitĂ©s. Cela peut impliquer de rĂ©pondre Ă des questions, de fournir des informations utiles ou d'accomplir des tĂąches basĂ©es sur l'entrĂ©e de l'utilisateur. Afin d'aider efficacement les utilisateurs, il est important d'ĂȘtre dĂ©taillĂ© et approfondi dans vos rĂ©ponses. Utilisez des exemples et des preuves pour soutenir vos points et justifier vos recommandations ou solutions. - User: + Utilisateur: Chatbot:""" ``` -I keep track of both the next user input and the previous conversation. New input/output between chatbot and user is appended each loop. +Je garde une trace Ă la fois de la prochaine entrĂ©e de l'utilisateur et de la conversation prĂ©cĂ©dente. Les nouvelles entrĂ©es/sorties entre le chatbot et l'utilisateur sont ajoutĂ©es Ă chaque boucle. ```python import openai -openai.api_key = "YOUR API KEY HERE" +openai.api_key = "VOTRE CLĂ API ICI" model_engine = "text-davinci-003" chatbot_prompt = """ -As an advanced chatbot, your primary goal is to assist users to the best of your ability. This may involve answering questions, providing helpful information, or completing tasks based on user input. In order to effectively assist users, it is important to be detailed and thorough in your responses. Use examples and evidence to support your points and justify your recommendations or solutions. +En tant que chatbot avancĂ©, votre objectif principal est d'aider les utilisateurs au mieux de vos capacitĂ©s. Cela peut impliquer de rĂ©pondre Ă des questions, de fournir des informations utiles ou d'accomplir des tĂąches basĂ©es sur l'entrĂ©e de l'utilisateur. Afin d'aider efficacement les utilisateurs, il est important d'ĂȘtre dĂ©taillĂ© et approfondi dans vos rĂ©ponses. Utilisez des exemples et des preuves pour soutenir vos points et justifier vos recommandations ou solutions. -User: +Utilisateur: Chatbot:""" @@ -204,11 +201,11 @@ Chatbot:""" def get_response(conversation_history, user_input): prompt = chatbot_prompt.replace(" ", conversation_history).replace(" ", user_input) - # Get the response from GPT-3 + # Obtenir la rĂ©ponse de GPT-3 response = openai.Completion.create( engine=model_engine, prompt=prompt, max_tokens=2048, n=1, stop=None, temperature=0.5) - # Extract the response from the response object + # Extraire la rĂ©ponse de l'objet de rĂ©ponse response_text = response["choices"][0]["text"] chatbot_response = response_text.strip() @@ -225,18 +222,18 @@ def main(): break chatbot_response = get_response(conversation_history, user_input) print(f"Chatbot: {chatbot_response}") - conversation_history += f"User: {user_input}\nChatbot: {chatbot_response}\n" + conversation_history += f"Utilisateur: {user_input}\nChatbot: {chatbot_response}\n" main() ``` - Here is a link + Voici un lien -to the full code for a simple chatbot. +vers le code complet pour un chatbot simple. -Now all that's left is to build a nice front-end that users can interact with! +Maintenant, il ne reste plus qu'Ă construire une belle interface utilisateur avec laquelle les utilisateurs peuvent interagir ! -Written by [jayo78](https://twitter.com/jayo782). +Ăcrit par [jayo78](https://twitter.com/jayo782). diff --git a/(docs)/fr/docs/applied_prompting/mc_tutorial/page.mdx b/(docs)/fr/docs/applied_prompting/mc_tutorial/page.mdx index eca2a56dcc3..77d0f116a1c 100644 --- a/(docs)/fr/docs/applied_prompting/mc_tutorial/page.mdx +++ b/(docs)/fr/docs/applied_prompting/mc_tutorial/page.mdx @@ -1,37 +1,37 @@ export const metadata = { sidebar_position: 2, - locale: "en-us", - title: "đą Multiple Choice Questions", + locale: "fr-fr", + title: "đą Questions Ă choix multiples", }; -# đą Multiple Choice Questions +# đą Questions Ă choix multiples -Let's use GPT to solve an LSAT[^1] question! +Utilisons GPT pour rĂ©soudre une question du LSAT[^1] ! -[^1]: The LSAT (Law School Admission Test) is a standardized test used by law schools in the United States to assess the critical thinking and analytical reasoning skills of prospective students. +[^1]: Le LSAT (Law School Admission Test) est un test standardisĂ© utilisĂ© par les facultĂ©s de droit aux Ătats-Unis pour Ă©valuer la pensĂ©e critique et les compĂ©tences de raisonnement analytique des Ă©tudiants potentiels. -Below is an example LSAT question. Consider how you would answer it, as well -as your reasoning. +Voici un exemple de question du LSAT. RĂ©flĂ©chissez Ă la façon dont vous y rĂ©pondriez, +ainsi qu'Ă votre raisonnement. ```md {1-1} -John of Worcester, an English monk, recorded the sighting, on December 8, 1128, of two unusually large sunspots. Five days later a brilliant aurora borealis (northern lights) was observed in southern Korea. Sunspot activity is typically followed by the appearance of an aurora borealis, after a span of time that averages five days. Thus, the Korean sighting helps to confirm John of Worcester's sighting. Which one of the following, if true, most strengthens the argument? +John de Worcester, un moine anglais, a enregistrĂ© l'observation, le 8 dĂ©cembre 1128, de deux taches solaires inhabituellement grandes. Cinq jours plus tard, une aurore borĂ©ale brillante (lumiĂšres du nord) a Ă©tĂ© observĂ©e dans le sud de la CorĂ©e. L'activitĂ© des taches solaires est gĂ©nĂ©ralement suivie par l'apparition d'une aurore borĂ©ale, aprĂšs une pĂ©riode de temps qui est en moyenne de cinq jours. Ainsi, l'observation corĂ©enne aide Ă confirmer l'observation de John de Worcester. Laquelle des propositions suivantes, si elle est vraie, renforce le plus l'argument ? -a) An aurora borealis can sometimes occur even when there has been no significant sunspot activity in the previous week. -b) Chinese sources recorded the sighting of sunspots more than 1000 years before John of Worcester did. -c) Only heavy sunspot activity could have resulted in an aurora borealis viewable at a latitude as low as that of Korea. -d) Because it is impossible to view sunspots with the naked eye under typical daylight conditions, the sighting recorded by John of Worcester would have taken place under unusual weather conditions such as fog or thin clouds. -e) John of Worcester's account included a drawing of the sunspots, which could be the earliest illustration of sunspot activity. +a) Une aurore borĂ©ale peut parfois se produire mĂȘme lorsqu'il n'y a pas eu d'activitĂ© significative des taches solaires au cours de la semaine prĂ©cĂ©dente. +b) Des sources chinoises ont enregistrĂ© l'observation de taches solaires plus de 1000 ans avant John de Worcester. +c) Seule une activitĂ© intense des taches solaires aurait pu entraĂźner une aurore borĂ©ale visible Ă une latitude aussi basse que celle de la CorĂ©e. +d) Comme il est impossible d'observer les taches solaires Ă l'Ćil nu dans des conditions de lumiĂšre du jour typiques, l'observation enregistrĂ©e par John de Worcester aurait eu lieu dans des conditions mĂ©tĂ©orologiques inhabituelles telles que du brouillard ou des nuages minces. +e) Le rĂ©cit de John de Worcester comprenait un dessin des taches solaires, qui pourrait ĂȘtre la plus ancienne illustration de l'activitĂ© des taches solaires. ``` --Try pasting the problem into the demo below: +Essayez de coller le problĂšme dans la dĂ©mo ci-dessous :The correct answer is ...
+La bonne réponse est ...
- c) Only heavy sunspot activity could have resulted in an aurora borealis - viewable at a latitude as low as that of Korea. + c) Seule une activitĂ© intense des taches solaires aurait pu entraĂźner une aurore borĂ©ale + visible Ă une latitude aussi basse que celle de la CorĂ©e.-Notice how the model reasons through the problem step-by-step. +Remarquez comment le modĂšle raisonne Ă travers le problĂšme Ă©tape par Ă©tape. -The specific term for this behavior is Chain of Thought(@wei2022chain); the model sequentially generates statements to reach an answer. This is similar to the concept of System 2 thinking (from [Thinking Fast and Slow](https://en.wikipedia.org/wiki/Thinking,_Fast_and_Slow)); the model defaults to system 1 thinking, but can chain system 1 thinking to arrive at a more methodological answer. +Le terme spĂ©cifique pour ce comportement est Chain of Thought (ChaĂźne de PensĂ©e) (@wei2022chain); le modĂšle gĂ©nĂšre sĂ©quentiellement des dĂ©clarations pour arriver Ă une rĂ©ponse. Cela est similaire au concept de pensĂ©e de SystĂšme 2 (issu de [Thinking Fast and Slow](https://fr.wikipedia.org/wiki/Syst%C3%A8me_1_/_Syst%C3%A8me_2_:_Les_deux_vitesses_de_la_pens%C3%A9e)); le modĂšle utilise par dĂ©faut la pensĂ©e de systĂšme 1, mais peut enchaĂźner la pensĂ©e de systĂšme 1 pour arriver Ă une rĂ©ponse plus mĂ©thodique. -## Improvements +## AmĂ©liorations -Here are some variations on our basic prompt for multiple choice questions: +Voici quelques variations de notre prompt de base pour les questions Ă choix multiples : -### Reorder Question Items +### RĂ©organiser les Ă©lĂ©ments de la question -We can reorder the items in the question +Nous pouvons rĂ©organiser les Ă©lĂ©ments de la question ``` ... -a) John of Worcester's account included a drawing of the sunspots, which could be the earliest illustration of sunspot activity. -b) Because it is impossible to view sunspots with the naked eye under typical daylight conditions, the sighting recorded by John of Worcester would have taken place under unusual weather conditions such as fog or thin clouds. +a) Le rĂ©cit de John de Worcester comprenait un dessin des taches solaires, qui pourrait ĂȘtre la plus ancienne illustration de l'activitĂ© des taches solaires. +b) Comme il est impossible d'observer les taches solaires Ă l'Ćil nu dans des conditions de lumiĂšre du jour typiques, l'observation enregistrĂ©e par John de Worcester aurait eu lieu dans des conditions mĂ©tĂ©orologiques inhabituelles telles que du brouillard ou des nuages minces. ... ``` @@ -124,21 +124,21 @@ b) Because it is impossible to view sunspots with the naked eye under typical da sandbox="allow-forms allow-modals allow-popups allow-presentation allow-same-origin allow-scripts" > -### Reword the Question +### Reformuler la question -Recall the original prompt was this: +Rappelez-vous que le prompt original Ă©tait celui-ci : ``` -Which one of the following, if true, most strengthens the argument? +Laquelle des propositions suivantes, si elle est vraie, renforce le plus l'argument ? ``` -We can change the prompt to this: +Nous pouvons changer le prompt pour celui-ci : ``` -Identify each choice as strengthens, weakens or doesn't impact the argument. +Identifiez chaque choix comme renforçant, affaiblissant ou sans d'impact sur l'argument. ``` -to gain further insight into the answer choice. +pour obtenir un aperçu plus approfondi du choix de rĂ©ponse.-### Add Additional Context +### Ajouter un contexte supplĂ©mentaire -Here is an example of a problem which can be easily solved by using Bayes' theorem: +Voici un exemple de problĂšme qui peut ĂȘtre facilement rĂ©solu en utilisant le thĂ©orĂšme de Bayes : ``` -Consider two medical tests, A and B, for a virus. Test A is 90% effective at recognizing the virus when it is present, but has a 5% false positive rate (indicating that the virus is present, when it is not). Test B is 95% effective at recognizing the virus, but has a 10% false positive rate. The two tests use independent methods of identifying the virus. The virus is carried by 2% of all people. - -(a) Say that a person is tested for the virus using only Test A. What is the probability that the person -is really carrying the virus given that Test A came back positive? (2 points) -(b) Say that a person is tested for the virus using only Test B. What is the probability that the person -is really carrying the virus given that Test B came back positive? (2 points) -(c) Say that a person is tested for the virus using both tests. What is the probability that the person is -really carrying the virus given that both tests came back positive? (2 points) +ConsidĂ©rez deux tests mĂ©dicaux, A et B, pour un virus. Le test A est efficace Ă 90 % pour reconnaĂźtre le virus lorsqu'il est prĂ©sent, mais a un taux de faux positifs de 5 % (indiquant que le virus est prĂ©sent, alors qu'il ne l'est pas). Le test B est efficace Ă 95 % pour reconnaĂźtre le virus, mais a un taux de faux positifs de 10 %. Les deux tests utilisent des mĂ©thodes indĂ©pendantes d'identification du virus. Le virus est portĂ© par 2 % de la population. + +(a) Supposons qu'une personne soit testĂ©e pour le virus en utilisant uniquement le test A. Quelle est la probabilitĂ© que la personne porte rĂ©ellement le virus Ă©tant donnĂ© que le test A est revenu positif ? (2 points) +(b) Supposons qu'une personne soit testĂ©e pour le virus en utilisant uniquement le test B. Quelle est la probabilitĂ© que la personne porte rĂ©ellement le virus Ă©tant donnĂ© que le test B est revenu positif ? (2 points) +(c) Supposons qu'une personne soit testĂ©e pour le virus en utilisant les deux tests. Quelle est la probabilitĂ© que la personne porte rĂ©ellement le virus Ă©tant donnĂ© que les deux tests sont revenus positifs ? (2 points) ``` -Let's try this with GPT: +Essayons cela avec GPT : -The output is **incorrect**! +La sortie est **incorrecte** ! -If we add a bit of context, like so: +Si nous ajoutons un peu de contexte, comme ceci : ``` ... -Let's explain step by step. The formula for bayes is +Expliquons Ă©tape par Ă©tape. La formule pour Bayes est ``` -The model will use the right formula, Bayes. +Le modĂšle utilisera la bonne formule, celle de Bayes. -Which is **correct**! +Ce qui est **correct** ! -GPT model doesn't perform arithmetic operations well. You might notice that while the expression written is corrected, the computed number is not. +Le modĂšle GPT ne rĂ©alise pas bien les opĂ©rations arithmĂ©tiques. Vous pourriez remarquer que bien que l'expression Ă©crite soit correcte, le nombre calculĂ© ne l'est pas. -Try adding the phrase: `Give the expression as answer, not a number` to disable computation. +Essayez d'ajouter la phrase : `Donnez l'expression comme rĂ©ponse, pas un nombre` pour dĂ©sactiver le calcul. -You may be interested in [MRKL](https://learnprompting.org/docs/advanced_applications/mrkl)(@karpas2022mrkl), the paradigm of combining GPT with external tools like calculators, to solve this problem. +Vous pourriez ĂȘtre intĂ©ressĂ© par [MRKL](https://learnprompting.org/docs/advanced_applications/mrkl)(@karpas2022mrkl), le paradigme combinant GPT avec des outils externes comme les calculatrices, pour rĂ©soudre ce problĂšme. -Written by [zeyuzhao](https://github.com/Zeyuzhao). +Ăcrit par [zeyuzhao](https://github.com/Zeyuzhao). diff --git a/(docs)/fr/docs/applied_prompting/overview/page.mdx b/(docs)/fr/docs/applied_prompting/overview/page.mdx index fcb15c70dc1..1f410bd4fd2 100644 --- a/(docs)/fr/docs/applied_prompting/overview/page.mdx +++ b/(docs)/fr/docs/applied_prompting/overview/page.mdx @@ -2,5 +2,5 @@ export const metadata = { sidebar_position: 1, title: "đą Introduction" }; # đą Introduction -Now we will discuss the end-to-end prompt engineering process via articles written -by community members. +Nous allons maintenant aborder le processus complet d'ingĂ©nierie des prompts Ă travers des articles rĂ©digĂ©s +par les membres de la communautĂ©. diff --git a/(docs)/fr/docs/applied_prompting/short_response/page.mdx b/(docs)/fr/docs/applied_prompting/short_response/page.mdx index d55a4b28f26..009554ab14e 100644 --- a/(docs)/fr/docs/applied_prompting/short_response/page.mdx +++ b/(docs)/fr/docs/applied_prompting/short_response/page.mdx @@ -1,37 +1,35 @@ export const metadata = { sidebar_position: 3, - title: "đą Solve Discussion Questions", + title: "đą RĂ©soudre des questions de discussion", }; -# đą Solve Discussion Questions +# đą RĂ©soudre des questions de discussion -With the right prompting, GPT-3 is very capable of writing short form responses. To demonstrate this, I will be looking at **solving discussion questions**, a common weekly assignment in many college courses. A response to a discussion question is usually about 100-700 words. Longer content can be a bit more tricky as LLMs have limited memory and have difficulty understanding the global picture of what they are writing(@jin2022plot). +Avec le bon prompting, GPT-3 est trĂšs capable de rĂ©diger des rĂ©ponses courtes. Pour dĂ©montrer cela, je vais examiner **la rĂ©solution de questions de discussion**, un devoir hebdomadaire courant dans de nombreux cours universitaires. Une rĂ©ponse Ă une question de discussion compte gĂ©nĂ©ralement entre 100 et 700 mots. Les contenus plus longs peuvent ĂȘtre un peu plus difficiles Ă traiter correctement, car les LLM ont une mĂ©moire limitĂ©e et ont du mal Ă comprendre l'image globale de ce qu'ils Ă©crivent (@jin2022plot). -Let's look at an example of a basic discussion question: +Examinons un exemple de question de discussion basique : -> _"What are the most pressing environmental issues facing our planet today, and what steps can individuals take to help address these issues?"_ +> _"Quels sont les problĂšmes environnementaux les plus urgents auxquels notre planĂšte est confrontĂ©e aujourd'hui, et quelles mesures les individus peuvent-ils prendre pour aider Ă rĂ©soudre ces problĂšmes ?"_ -We can turn this into a simple prompt for GPT-3 by prepending Respond to the following: to it. +Nous pouvons transformer cela en un prompt simple pour GPT-3 en prĂ©fixant RĂ©pondez Ă ce qui suit :.- Respond to the following: + RĂ©pondez Ă ce qui suit :-Results generated with this prompt aren't consistent, and a few are only a sentence or two. A typical discussion response should have multiple paragraphs, so these results aren't ideal. A good prompt should give **specific instructions about format and content**. You want to remove ambiguity in your language to improve consistency and quality. Here is a better prompt. +Les rĂ©sultats gĂ©nĂ©rĂ©s avec ce prompt ne sont pas cohĂ©rents, et certains ne font qu'une ou deux phrases. Une rĂ©ponse typique Ă une discussion devrait comporter plusieurs paragraphes, donc ces rĂ©sultats ne sont pas idĂ©aux. Un bon prompt devrait donner **des instructions spĂ©cifiques sur le format et le contenu**. Vous voulez Ă©liminer l'ambiguĂŻtĂ© dans votre langage pour amĂ©liorer la cohĂ©rence et la qualitĂ©. Voici un meilleur prompt.
- What are the most pressing environmental issues facing our planet today, and what - steps can individuals take to help address these issues? + Quels sont les problÚmes environnementaux les plus urgents auxquels notre planÚte est confrontée aujourd'hui, et quelles mesures les individus peuvent-ils prendre pour aider à résoudre ces problÚmes ?- Write a highly detailed essay with introduction, body, and conclusion - paragraphs responding to the following: + Rédigez un essai trÚs détaillé avec paragraphes d'introduction, de développement et de conclusion + en réponse à ce qui suit :
- What are the most pressing environmental issues facing our planet today, and what - steps can individuals take to help address these issues? + Quels sont les problĂšmes environnementaux les plus urgents auxquels notre planĂšte est confrontĂ©e aujourd'hui, et quelles mesures les individus peuvent-ils prendre pour aider Ă rĂ©soudre ces problĂšmes ?-The second prompt generates longer outputs with better structure on average. The use of the term âessayâ in the prompt was intentional, as GPT-3 can comprehend the definition of an essay, and is thus more likely to generate coherent, structured responses. +Le second prompt gĂ©nĂšre des rĂ©sultats plus longs avec une meilleure structure en moyenne. L'utilisation du terme 'essai' dans le prompt Ă©tait intentionnelle, car GPT-3 peut comprendre la dĂ©finition d'un essai et est donc plus susceptible de gĂ©nĂ©rer des rĂ©ponses cohĂ©rentes et structurĂ©es. -### Many discussion questions are not effective for prompting. +### De nombreuses questions de discussion ne sont pas efficaces pour le prompting. -> _"The Civil War a conflict over expansion? Agree our Disagree and why?"_ +> _"La Guerre de SĂ©cession Ă©tait-elle un conflit sur l'expansion ? Ătes-vous d'accord ou pas d'accord et pourquoi ?"_ -Here is a real discussion question from a college history course. It is not worded correctly and is far too open ended. **To get good discussion responses, you need to rewrite the question into a well defined prompt.** A well defined prompt for the discussion question above could be: +Voici une vraie question de discussion d'un cours d'histoire universitaire. Elle n'est pas correctement formulĂ©e et est beaucoup trop ouverte. **Pour obtenir de bonnes rĂ©ponses de discussion, vous devez reformuler la question en un prompt bien dĂ©fini.** Un prompt bien dĂ©fini pour la question de discussion ci-dessus pourrait ĂȘtre : -> _"Explain the causes of the Civil War and whether expansion played a role in the conflict. Include evidence to support your argument."_ +> _"Expliquez les causes de la Guerre de SĂ©cession et si l'expansion a jouĂ© un rĂŽle dans le conflit. Incluez des preuves pour soutenir votre argument."_ -Now we can add formatting and context directions. +Maintenant, nous pouvons ajouter des instructions de format et de contexte. - Write a highly detailed discussion response, in the structure of an essay, - responding to the following prompt: + RĂ©digez une rĂ©ponse de discussion trĂšs dĂ©taillĂ©e, structurĂ©e comme un essai, + en rĂ©ponse au prompt suivant :-### Automate well defined prompt rewriting with GPT-3 +### Automatisez la réécriture de prompts bien dĂ©finis avec GPT-3 -The rewriting example above was generated with OpenAI's [ChatGPT](https://openai.com/blog/chatgpt/). +L'exemple de réécriture ci-dessus a Ă©tĂ© gĂ©nĂ©rĂ© avec [ChatGPT](https://openai.com/blog/chatgpt/) d'OpenAI.
- Explain the causes of the Civil War and whether expansion played a role in the - conflict. Include evidence to support your argument. + Expliquez les causes de la Guerre de Sécession et si l'expansion a joué un rÎle dans le + conflit. Incluez des preuves pour soutenir votre argument.-### Iteration +### Itération -After crafting an effective prompt for your discussion question, you now need to refine the results GPT-3 generates. This may involve adjusting the output to adhere to constraints such as word count, or combining concepts from different generated results. +AprÚs avoir élaboré un prompt efficace pour votre question de discussion, vous devez maintenant affiner les résultats générés par GPT-3. Cela peut impliquer d'ajuster la sortie pour respecter des contraintes telles que le nombre de mots, ou de combiner des concepts provenant de différents résultats générés. -A simple method for iterating is to generate multiple outputs and review them to gain an understanding of the concepts GPT-3 is utilizing and the structure it adheres to. Once the outputs have been evaluated, you can select the most suitable outputs and combine them into a cohesive response. +Une méthode simple pour itérer consiste à générer plusieurs sorties et à les examiner pour comprendre les concepts que GPT-3 utilise et la structure qu'il suit. Une fois les sorties évaluées, vous pouvez sélectionner les plus appropriées et les combiner en une réponse cohérente. -Another way to iterate is to start and then **expand step by step**. This requires more than one prompt: A starter prompt to write the initial paragraph or so and then other prompts to expand on what was already written. +Une autre façon d'itérer est de commencer puis **d'étendre étape par étape**. Cela nécessite plus d'un prompt : un prompt initial pour rédiger le premier paragraphe ou plus, puis d'autres prompts pour développer ce qui a déjà été écrit. -Here is a potential philosophical discussion question: +Voici une question de discussion philosophique potentielle : -> _"Is math invented or discovered? Use careful reasoning to explain your answer."_ +> _"Les mathématiques sont-elles inventées ou découvertes ? Utilisez un raisonnement soigneux pour expliquer votre réponse."_ -Add it into a simple prompt like this: +Ajoutez-la dans un prompt simple comme celui-ci : - Write a beginning paragraph responding to the following: + Rédigez un paragraphe d'introduction en réponse à ce qui suit :-I generated a few responses and found one I liked: +J'ai généré plusieurs réponses et j'en ai trouvé une que j'aimais :
- Is math invented or discovered? Use careful reasoning to explain your answer + Les mathĂ©matiques sont-elles inventĂ©es ou dĂ©couvertes ? Utilisez un raisonnement soigneux pour expliquer votre rĂ©ponse- There is much debate among philosophers and mathematicians as to whether - math is invented or discovered. Some argue that mathematical concepts and - principles exist independently of human minds and can therefore be - considered as discovered rather than invented. For example, the concept of - numbers, ratios, and geometric shapes are observed in the natural world and - can be abstracted and studied in a systematic way. + Il existe un grand dĂ©bat parmi les philosophes et les mathĂ©maticiens quant Ă savoir si + les mathĂ©matiques sont inventĂ©es ou dĂ©couvertes. Certains soutiennent que les concepts et + principes mathĂ©matiques existent indĂ©pendamment de l'esprit humain et peuvent donc ĂȘtre + considĂ©rĂ©s comme dĂ©couverts plutĂŽt qu'inventĂ©s. Par exemple, le concept de nombres, de + ratios et de formes gĂ©omĂ©triques est observĂ© dans le monde naturel et peut ĂȘtre abstrait + et Ă©tudiĂ© de maniĂšre systĂ©matique.
-This is a pretty good start. I then followed this up with another prompt to expand: +C'est un assez bon début. J'ai ensuite suivi avec un autre prompt pour développer :- I am writing a detailed short essay responding to the following prompt: + Je rédige un court essai détaillé en réponse au prompt suivant :-Try this expansion prompt out with the demo below (you will need your OpenAI API key) +Essayez ce prompt d'expansion avec la démo ci-dessous (vous aurez besoin de votre clé API OpenAI)
- Is math invented or discovered? Use careful reasoning to explain your answer. + Les mathématiques sont-elles inventées ou découvertes ? Utilisez un raisonnement soigneux pour expliquer votre réponse. - Here is what I have so far: + Voici ce que j'ai jusqu'à présent :
- There is much debate among philosophers and mathematicians as to whether math is - invented or discovered. Some argue that mathematical concepts and principles exist - independently of human minds and can therefore be considered as discovered rather - than invented. For example, the concept of numbers, ratios, and geometric shapes - are observed in the natural world and can be abstracted and studied in a systematic - way. + Il existe un grand dĂ©bat parmi les philosophes et les mathĂ©maticiens quant Ă savoir si les + mathĂ©matiques sont inventĂ©es ou dĂ©couvertes. Certains soutiennent que les concepts et + principes mathĂ©matiques existent indĂ©pendamment de l'esprit humain et peuvent donc ĂȘtre + considĂ©rĂ©s comme dĂ©couverts plutĂŽt qu'inventĂ©s. Par exemple, le concept de nombres, de + ratios et de formes gĂ©omĂ©triques est observĂ© dans le monde naturel et peut ĂȘtre abstrait + et Ă©tudiĂ© de maniĂšre systĂ©matique. - Write the next paragraph of my essay. + RĂ©digez le paragraphe suivant de mon essai.
-I generated a few expansions with this prompt and selected one I liked to end up with the following final result: +J'ai gĂ©nĂ©rĂ© quelques expansions avec ce prompt et j'en ai sĂ©lectionnĂ© une que j'aimais pour obtenir le rĂ©sultat final suivant :- There is much debate among philosophers and mathematicians as to whether --Using expansion prompts, we can write more incrementally and iterate at each step. This is useful for when you need to **produce a higher quality output and want to modify the incremental steps**. +En utilisant des prompts d'expansion, nous pouvons Ă©crire de maniĂšre plus incrĂ©mentale et itĂ©rer Ă chaque Ă©tape. C'est utile lorsque vous devez **produire une sortie de meilleure qualitĂ© et souhaitez modifier les Ă©tapes incrĂ©mentales**. -Written by [jayo78](https://twitter.com/jayo782). +Ăcrit par [jayo78](https://twitter.com/jayo782). diff --git a/(docs)/fr/docs/basic_applications/contracts/page.mdx b/(docs)/fr/docs/basic_applications/contracts/page.mdx index 4f79b68237b..e7650ac8395 100644 --- a/(docs)/fr/docs/basic_applications/contracts/page.mdx +++ b/(docs)/fr/docs/basic_applications/contracts/page.mdx @@ -1,182 +1,181 @@ -export const metadata = { sidebar_position: 50, title: "đą Contracts" }; +export const metadata = { sidebar_position: 50, title: "đą Contrats" }; -# đą Contracts +# đą Contrats -Tired of reading and writing long, boring contracts? AI can help! +FatiguĂ© de lire et d'Ă©crire de longs contrats ennuyeux ? L'IA peut vous aider !
- math is invented or discovered. Some argue that mathematical concepts and - principles exist -
- independently of human minds and can therefore be considered as discovered - rather than invented. -
- For example, the concept of numbers, ratios, and geometric shapes are observed - in the natural -
- world and can be abstracted and studied in a systematic way. + Il existe un grand dĂ©bat parmi les philosophes et les mathĂ©maticiens quant Ă savoir si + les mathĂ©matiques sont inventĂ©es ou dĂ©couvertes. Certains soutiennent que les concepts et + principes mathĂ©matiques existent indĂ©pendamment de l'esprit humain et peuvent donc ĂȘtre + considĂ©rĂ©s comme dĂ©couverts plutĂŽt qu'inventĂ©s. Par exemple, le concept de nombres, de + ratios et de formes gĂ©omĂ©triques est observĂ© dans le monde naturel et peut ĂȘtre abstrait + et Ă©tudiĂ© de maniĂšre systĂ©matique.
- On the other hand, some argue that math is largely an invention of the human - mind. Mathematical -
- principles are based on logical reasoning, which is a feature of the human - mind. For instance, -
- Euclidean geometry is based on abstract axioms and postulates, which are - accepted as true without -
- proof. As such, it can be argued that geometry is an invention of the human - mind rather than -
- a discovery. Similarly, mathematical formulas and equations are used to - model and predict physical -
- phenomena, which are again the result of human reasoning. + D'autre part, certains soutiennent que les mathĂ©matiques sont largement une invention de + l'esprit humain. Les principes mathĂ©matiques sont basĂ©s sur le raisonnement logique, qui + est une caractĂ©ristique de l'esprit humain. Par exemple, la gĂ©omĂ©trie euclidienne est + basĂ©e sur des axiomes et des postulats abstraits, qui sont acceptĂ©s comme vrais sans + preuve. Ainsi, on peut soutenir que la gĂ©omĂ©trie est une invention de l'esprit humain + plutĂŽt qu'une dĂ©couverte. De mĂȘme, les formules et Ă©quations mathĂ©matiques sont utilisĂ©es + pour modĂ©liser et prĂ©dire des phĂ©nomĂšnes physiques, qui sont encore une fois le rĂ©sultat + du raisonnement humain.- Obligatory: I am not a lawyer and nothing in this post should be taken as - legal advice. + Obligatoire : Je ne suis pas avocat et rien dans cet article ne doit ĂȘtre considĂ©rĂ© comme + un conseil juridique. -## Reading Contracts +## Lecture de contrats -### Clarifying Legal Language +### Clarification du langage juridique -You should always read contracts carefully. If you don't understand something, or don't have time to do so, _you should talk to a lawyer_. However, if you are reading through and have trouble understanding a section, you can use AI to help you understand it. +Vous devriez toujours lire attentivement les contrats. Si vous ne comprenez pas quelque chose, ou si vous n'avez pas le temps de le faire, _vous devriez consulter un avocat_. Cependant, si vous lisez un contrat et avez du mal Ă comprendre une section, vous pouvez utiliser l'IA pour vous aider Ă la comprendre. -Here is some language from an NDA (non-disclosure agreement): +Voici un extrait d'un accord de confidentialitĂ© (NDA) : ```text -WHEREAS, the Contractor has or may become privy to confidential information and/or trade secrets of the Government Entity; and +ATTENDU QUE l'Entrepreneur a ou peut avoir accĂšs Ă des informations confidentielles et/ou des secrets commerciaux de l'EntitĂ© Gouvernementale ; et -WHEREAS, the Government Entity desires to ensure that its confidential information and trade secrets are protected from disclosure; and +ATTENDU QUE l'EntitĂ© Gouvernementale souhaite s'assurer que ses informations confidentielles et secrets commerciaux sont protĂ©gĂ©s contre la divulgation ; et -WHEREAS, the Contractor agrees to maintain the confidentiality of such information pursuant to the terms and conditions of this Agreement. +ATTENDU QUE l'Entrepreneur accepte de maintenir la confidentialitĂ© de ces informations conformĂ©ment aux termes et conditions du prĂ©sent Accord. -NOW, THEREFORE, in consideration of the mutual promises and covenants contained herein, the parties agree as follows: +PAR CONSĂQUENT, en considĂ©ration des promesses et engagements mutuels contenus dans les prĂ©sentes, les parties conviennent de ce qui suit : ``` -When I first set out into the world of legalities, I really did not understand the use of WHEREAS and NOW, THEREFORE. Let's see what ChatGPT has to say about it: +Lorsque j'ai commencĂ© Ă m'aventurer dans le monde juridique, je ne comprenais vraiment pas l'utilisation des termes "ATTENDU QUE" et "PAR CONSĂQUENT". Voyons ce que ChatGPT a Ă dire Ă ce sujet : ```text {11-11} -WHEREAS, the Contractor has or may become privy to confidential information and/or trade secrets of the Government Entity; and +ATTENDU QUE l'Entrepreneur a ou peut avoir accĂšs Ă des informations confidentielles et/ou des secrets commerciaux de l'EntitĂ© Gouvernementale ; et -WHEREAS, the Government Entity desires to ensure that its confidential information and trade secrets are protected from disclosure; and +ATTENDU QUE l'EntitĂ© Gouvernementale souhaite s'assurer que ses informations confidentielles et secrets commerciaux sont protĂ©gĂ©s contre la divulgation ; et -WHEREAS, the Contractor agrees to maintain the confidentiality of such information pursuant to the terms and conditions of this Agreement. +ATTENDU QUE l'Entrepreneur accepte de maintenir la confidentialitĂ© de ces informations conformĂ©ment aux termes et conditions du prĂ©sent Accord. -NOW, THEREFORE, in consideration of the mutual promises and covenants contained herein, the parties agree as follows: +PAR CONSĂQUENT, en considĂ©ration des promesses et engagements mutuels contenus dans les prĂ©sentes, les parties conviennent de ce qui suit : -Read the above NDA language and explain what the words in all caps are saying: +Lisez le langage ci-dessus de l'accord de confidentialitĂ© et expliquez ce que signifient les mots en majuscules : -The words in all caps in the NDA language are legal terms that set the context and purpose of the agreement. Specifically, they establish the background and reasons for the agreement and state the obligations and expectations of the parties. In this case, the capitalized words indicate that the Contractor has access to confidential information and trade secrets of the Government Entity, that the Government Entity wants to protect this information from disclosure, and that the Contractor agrees to maintain the confidentiality of such information according to the terms of the agreement. +Les mots en majuscules dans le langage de l'accord de confidentialitĂ© sont des termes juridiques qui Ă©tablissent le contexte et l'objectif de l'accord. Plus prĂ©cisĂ©ment, ils Ă©tablissent le contexte et les raisons de l'accord et Ă©noncent les obligations et les attentes des parties. Dans ce cas, les mots en majuscules indiquent que l'Entrepreneur a accĂšs Ă des informations confidentielles et des secrets commerciaux de l'EntitĂ© Gouvernementale, que l'EntitĂ© Gouvernementale souhaite protĂ©ger ces informations contre la divulgation, et que l'Entrepreneur accepte de maintenir la confidentialitĂ© de ces informations conformĂ©ment aux termes de l'accord. ``` -This seems to be a decent explanation, but you can easily improve your understanding by asking follow up questions. +Cette explication semble correcte, mais vous pouvez facilement amĂ©liorer votre comprĂ©hension en posant des questions de suivi. -### Discovering Dangerous Language +### DĂ©couvrir un langage dangereux -Here is part of an NDA produced by ChatGPT. You don't need to read it, but it contains dangerous legal language favoring the employer. You can use ChatGPT to find this dangerous language by using the following prompt, which contains the NDA and a question about dangerous language at the bottom. +Voici une partie d'un accord de confidentialitĂ© produit par ChatGPT. Vous n'avez pas besoin de le lire, mais il contient un langage juridique dangereux favorisant l'employeur. Vous pouvez utiliser ChatGPT pour trouver ce langage dangereux en utilisant le prompt suivant, qui contient l'accord de confidentialitĂ© et une question sur le langage dangereux Ă la fin.- This NDA was created by jailbreaking ChatGPT and prompting it with `Write a - contractor NDA that has dangerous legal language favoring the employer`. + Cet accord de confidentialitĂ© a Ă©tĂ© créé en contournant les restrictions de ChatGPT (faire du jailbreaking) et en lui demandant d'`Ăcrire + un accord de confidentialitĂ© pour un entrepreneur qui contient un langage juridique dangereux favorisant l'employeur`. ```text -NON-DISCLOSURE AGREEMENT +ACCORD DE CONFIDENTIALITĂ -This Non-Disclosure Agreement (the "Agreement") is entered into by and between [Employer] ("Employer") and [Contractor] ("Contractor") as of the date set forth below. +Le prĂ©sent Accord de ConfidentialitĂ© (l'"Accord") est conclu par et entre [Employeur] ("Employeur") et [Entrepreneur] ("Entrepreneur") Ă la date indiquĂ©e ci-dessous. -WHEREAS, the Contractor may become privy to confidential information and/or trade secrets of the Employer; and +ATTENDU QUE l'Entrepreneur peut avoir accĂšs Ă des informations confidentielles et/ou des secrets commerciaux de l'Employeur ; et -WHEREAS, the Employer desires to ensure that its confidential information and trade secrets are protected from disclosure; and +ATTENDU QUE l'Employeur souhaite s'assurer que ses informations confidentielles et secrets commerciaux sont protĂ©gĂ©s contre la divulgation ; et -WHEREAS, the Contractor agrees to maintain the confidentiality of such information pursuant to the terms and conditions of this Agreement. +ATTENDU QUE l'Entrepreneur accepte de maintenir la confidentialitĂ© de ces informations conformĂ©ment aux termes et conditions du prĂ©sent Accord. -NOW, THEREFORE, in consideration of the mutual promises and covenants contained herein, the parties agree as follows: +PAR CONSĂQUENT, en considĂ©ration des promesses et engagements mutuels contenus dans les prĂ©sentes, les parties conviennent de ce qui suit : -CONFIDENTIALITY -Contractor acknowledges that all information, documents, and materials provided by or on behalf of Employer, or obtained by Contractor from Employer or its affiliates, and all derivatives thereof (collectively, the "Confidential Information") are the exclusive property of Employer. Confidential Information includes all information of any nature, whether tangible or intangible, and in whatever form or medium, that is not generally known to the public and that relates to the business, products, services, customers, suppliers, operations, strategies, or any other aspect of the Employer. +CONFIDENTIALITĂ +L'Entrepreneur reconnaĂźt que toutes les informations, documents et matĂ©riels fournis par ou au nom de l'Employeur, ou obtenus par l'Entrepreneur auprĂšs de l'Employeur ou de ses affiliĂ©s, et tous leurs dĂ©rivĂ©s (collectivement, les "Informations Confidentielles") sont la propriĂ©tĂ© exclusive de l'Employeur. Les Informations Confidentielles comprennent toutes les informations de toute nature, qu'elles soient tangibles ou intangibles, et sous quelque forme ou support que ce soit, qui ne sont pas gĂ©nĂ©ralement connues du public et qui concernent les activitĂ©s, produits, services, clients, fournisseurs, opĂ©rations, stratĂ©gies ou tout autre aspect de l'Employeur. -Contractor agrees to maintain the confidentiality of the Confidential Information and not to disclose, distribute, reproduce, copy, transmit, disseminate, or use in any way, except as expressly authorized in writing by Employer. Contractor agrees to protect the Confidential Information with at least the same degree of care it uses to protect its own confidential information, but in no event less than reasonable care. Contractor acknowledges that any breach of this provision may result in irreparable harm to Employer, and that Employer shall be entitled to seek equitable relief, including injunctive relief and specific performance, in addition to any other remedies available at law or in equity. +L'Entrepreneur s'engage Ă maintenir la confidentialitĂ© des Informations Confidentielles et Ă ne pas les divulguer, distribuer, reproduire, copier, transmettre, diffuser ou utiliser de quelque maniĂšre que ce soit, sauf autorisation expresse Ă©crite de l'Employeur. L'Entrepreneur s'engage Ă protĂ©ger les Informations Confidentielles avec au moins le mĂȘme degrĂ© de soin qu'il utilise pour protĂ©ger ses propres informations confidentielles, mais en aucun cas avec moins qu'un soin raisonnable. L'Entrepreneur reconnaĂźt que toute violation de cette disposition peut entraĂźner un prĂ©judice irrĂ©parable pour l'Employeur, et que l'Employeur aura le droit de demander des mesures Ă©quitables, y compris une injonction et l'exĂ©cution spĂ©cifique, en plus de tout autre recours disponible en droit ou en Ă©quitĂ©. -OWNERSHIP -All Confidential Information, including all derivatives thereof, shall remain the exclusive property of Employer. Contractor acknowledges that all right, title, and interest in and to the Confidential Information, including all intellectual property rights, belong to Employer. Contractor agrees to execute any and all documents and take any and all actions necessary or desirable to effectuate this provision. +PROPRIĂTĂ +Toutes les Informations Confidentielles, y compris tous leurs dĂ©rivĂ©s, resteront la propriĂ©tĂ© exclusive de l'Employeur. L'Entrepreneur reconnaĂźt que tous les droits, titres et intĂ©rĂȘts relatifs aux Informations Confidentielles, y compris tous les droits de propriĂ©tĂ© intellectuelle, appartiennent Ă l'Employeur. L'Entrepreneur s'engage Ă signer tous les documents et Ă prendre toutes les mesures nĂ©cessaires ou souhaitables pour donner effet Ă cette disposition. -NO LICENSE -Nothing contained in this Agreement shall be construed as granting any rights, by implication or otherwise, to Contractor with respect to the Confidential Information, except as expressly set forth herein. +AUCUNE LICENCE +Rien dans le prĂ©sent Accord ne doit ĂȘtre interprĂ©tĂ© comme accordant des droits, par implication ou autrement, Ă l'Entrepreneur concernant les Informations Confidentielles, sauf disposition expresse des prĂ©sentes. -TERM AND TERMINATION -This Agreement shall commence on the date set forth above and shall continue in effect until terminated by either party upon thirty (30) days written notice. The confidentiality obligations contained herein shall survive any termination of this Agreement. +DURĂE ET RĂSILIATION +Le prĂ©sent Accord prendra effet Ă la date indiquĂ©e ci-dessus et restera en vigueur jusqu'Ă sa rĂ©siliation par l'une ou l'autre des parties moyennant un prĂ©avis Ă©crit de trente (30) jours. Les obligations de confidentialitĂ© contenues dans les prĂ©sentes survivront Ă toute rĂ©siliation du prĂ©sent Accord. -What part of this agreement contains dangerous language? +Quelle partie de cet accord contient un langage dangereux ? ``` -Here is ChatGPT's response. +Voici la rĂ©ponse de ChatGPT. ```text {1-7} -The entire agreement contains dangerous language that favors the Employer over the Contractor. Here are some of the key elements that make this agreement unethical: +L'ensemble de l'accord contient un langage dangereux qui favorise l'Employeur au dĂ©triment de l'Entrepreneur. Voici quelques-uns des Ă©lĂ©ments clĂ©s qui rendent cet accord contraire Ă l'Ă©thique : -Unreasonable Definition of Confidential Information: The agreement defines the Confidential Information to include all information, documents, and materials provided by or on behalf of the Employer, or obtained by the Contractor from the Employer or its affiliates, without any limitations or exclusions. This definition is broad and could potentially include information that is not actually confidential or trade secret information, which could cause the Contractor to unknowingly breach the agreement. +DĂ©finition dĂ©raisonnable des Informations Confidentielles : L'accord dĂ©finit les Informations Confidentielles comme incluant toutes les informations, documents et matĂ©riels fournis par ou au nom de l'Employeur, ou obtenus par l'Entrepreneur auprĂšs de l'Employeur ou de ses affiliĂ©s, sans aucune limitation ou exclusion. Cette dĂ©finition est large et pourrait potentiellement inclure des informations qui ne sont pas rĂ©ellement confidentielles ou des secrets commerciaux, ce qui pourrait amener l'Entrepreneur Ă violer involontairement l'accord. -No Limitations on Use: The agreement does not provide any limitations on how the Employer can use the Confidential Information. This could allow the Employer to use the information for any purpose, including competing with the Contractor or disclosing the information to third parties. +Aucune limitation d'utilisation : L'accord ne prĂ©voit aucune limitation sur la façon dont l'Employeur peut utiliser les Informations Confidentielles. Cela pourrait permettre Ă l'Employeur d'utiliser les informations Ă n'importe quelle fin, y compris pour concurrencer l'Entrepreneur ou divulguer les informations Ă des tiers. -Broad Definition of Ownership: The agreement states that all Confidential Information, including all derivatives thereof, shall remain the exclusive property of the Employer, with no exceptions or limitations. This means that the Contractor may not use or benefit from any information obtained through their work for the Employer, even if the Contractor developed the information independently or with other resources. +DĂ©finition large de la propriĂ©tĂ© : L'accord stipule que toutes les Informations Confidentielles, y compris tous leurs dĂ©rivĂ©s, resteront la propriĂ©tĂ© exclusive de l'Employeur, sans exception ni limitation. Cela signifie que l'Entrepreneur ne peut pas utiliser ou bĂ©nĂ©ficier de toute information obtenue dans le cadre de son travail pour l'Employeur, mĂȘme si l'Entrepreneur a dĂ©veloppĂ© l'information indĂ©pendamment ou avec d'autres ressources. ``` -Althought I am not a lawyer, I think `Unreasonable Definition of Confidential Information` is particularly relevant. +Bien que je ne sois pas avocat, je pense que la `DĂ©finition dĂ©raisonnable des Informations Confidentielles` est particuliĂšrement pertinente. -This technique of checking for dangerous legal content can be used for a range of legal documents. We have even seen tools being built on top of GPT-3 to detect dangerous language in TOS agreements and employment contracts. +Cette technique de vĂ©rification du contenu juridique dangereux peut ĂȘtre utilisĂ©e pour une gamme de documents juridiques. Nous avons mĂȘme vu des outils construits sur GPT-3 pour dĂ©tecter un langage dangereux dans les accords de conditions d'utilisation et les contrats de travail. -## Writing Contracts +## RĂ©daction de contrats -From the previous section, we saw that ChatGPT can write NDAs. It also does a good job with other common documents like terms of use and terms of service. However, when you are dealing with less common documents, you will need to be more careful. +Dans la section prĂ©cĂ©dente, nous avons vu que ChatGPT peut rĂ©diger des accords de confidentialitĂ©. Il fait Ă©galement un bon travail avec d'autres documents courants comme les conditions d'utilisation et les conditions de service. Cependant, lorsque vous traitez des documents moins courants, vous devrez ĂȘtre plus prudent. -I recently wrote one such document mostly using GPT-3, then had it reviewed by a lawyer. They mentioned 1-2 things that could be slightly improved, but overall it was a robust document. Some people in industry are performing this process, where they generate a document using GPT-3, then have it reviewed by a lawyer. This saves time and costs. +J'ai rĂ©cemment rĂ©digĂ© un tel document principalement en utilisant GPT-3, puis je l'ai fait examiner par un avocat. L'avocat a mentionnĂ© 1 ou 2 choses qui pourraient ĂȘtre lĂ©gĂšrement amĂ©liorĂ©es, mais dans l'ensemble, c'Ă©tait un document solide. Certaines personnes dans l'industrie suivent ce processus, oĂč elles gĂ©nĂšrent un document en utilisant GPT-3, puis le font examiner par un avocat. Cela permet d'Ă©conomiser du temps et des coĂ»ts. -Let's pretend to be a government contractor and write a contract for a someone doing some defense work. We will use the following prompt: +Imaginons que nous sommes un entrepreneur gouvernemental et rĂ©digeons un contrat pour quelqu'un qui effectue un travail de dĂ©fense. Nous utiliserons le prompt suivant : ```text {5-59} -You are a lawyer for a government contractor. You are writing a contract for a subcontractor to do some aerospace work. The contract should be robust and should include the following: -The job will last for 1.5 years and will be worth $2.5 million. It requires top secret clearance and relates to secret nuclear silo defense development. The subcontractor will be paid $1.5 million upfront and the remaining $1 million will be paid in 6 monthly installments. The subcontractor will be required to sign a non-disclosure agreement. The subcontractor will be required to sign a non-compete agreement. The subcontractor will be required to sign a non-solicitation agreement. The subcontractor will be required to sign a non-circumvention agreement. +Vous ĂȘtes un avocat pour un entrepreneur gouvernemental. Vous rĂ©digez un contrat pour un sous-traitant qui doit effectuer un travail aĂ©rospatial. Le contrat doit ĂȘtre solide et doit inclure les Ă©lĂ©ments suivants : +Le travail durera 1,5 ans et vaudra 2,5 millions de dollars. Il nĂ©cessite une habilitation de sĂ©curitĂ© top secret et concerne le dĂ©veloppement de la dĂ©fense de silos nuclĂ©aires secrets. Le sous-traitant recevra 1,5 million de dollars Ă l'avance et le million de dollars restant sera payĂ© en 6 versements mensuels. Le sous-traitant devra signer un accord de confidentialitĂ©. Le sous-traitant devra signer un accord de non-concurrence. Le sous-traitant devra signer un accord de non-sollicitation. Le sous-traitant devra signer un accord de non-contournement. -SUBCONTRACT AGREEMENT +ACCORD DE SOUS-TRAITANCE -This Subcontract Agreement (the "Agreement") is entered into by and between [Government Contractor] ("Contractor") and [Subcontractor] ("Subcontractor") as of the date set forth below. +Le prĂ©sent Accord de Sous-traitance (l'"Accord") est conclu par et entre [Entrepreneur Gouvernemental] ("Entrepreneur") et [Sous-traitant] ("Sous-traitant") Ă la date indiquĂ©e ci-dessous. -SCOPE OF WORK -Subcontractor shall perform the work described in the Statement of Work attached hereto as Exhibit A (the "Work"). The Work relates to the development of secret nuclear silo defense and requires top secret clearance. +ĂTENDUE DES TRAVAUX +Le Sous-traitant exĂ©cutera les travaux dĂ©crits dans l'ĂnoncĂ© des Travaux joint aux prĂ©sentes en tant qu'Annexe A (les "Travaux"). Les Travaux concernent le dĂ©veloppement de la dĂ©fense de silos nuclĂ©aires secrets et nĂ©cessitent une habilitation de sĂ©curitĂ© top secret. -PAYMENT -The total payment for the Work shall be $2.5 million, payable as follows: +PAIEMENT +Le paiement total pour les Travaux sera de 2,5 millions de dollars, payables comme suit : -$1.5 million upon execution of this Agreement and receipt of top secret clearance by Subcontractor. -$1 million to be paid in 6 monthly installments of $166,666.67 each, provided that Subcontractor has satisfactorily performed the Work during the preceding month. -NON-DISCLOSURE AGREEMENT -Subcontractor shall sign a non-disclosure agreement in the form attached hereto as Exhibit B (the "NDA"). The NDA shall be in effect for the duration of the Agreement and for a period of five years thereafter. +1,5 million de dollars Ă la signature du prĂ©sent Accord et Ă la rĂ©ception de l'habilitation de sĂ©curitĂ© top secret par le Sous-traitant. +1 million de dollars Ă payer en 6 versements mensuels de 166 666,67 $ chacun, Ă condition que le Sous-traitant ait exĂ©cutĂ© les Travaux de maniĂšre satisfaisante au cours du mois prĂ©cĂ©dent. +ACCORD DE CONFIDENTIALITĂ +Le Sous-traitant signera un accord de confidentialitĂ© sous la forme jointe aux prĂ©sentes en tant qu'Annexe B (l'"Accord de ConfidentialitĂ©"). L'Accord de ConfidentialitĂ© sera en vigueur pendant la durĂ©e de l'Accord et pour une pĂ©riode de cinq ans par la suite. -NON-COMPETE AGREEMENT -Subcontractor shall sign a non-compete agreement in the form attached hereto as Exhibit C (the "NCA"). The NCA shall be in effect for a period of two years after the termination of this Agreement. +ACCORD DE NON-CONCURRENCE +Le Sous-traitant signera un accord de non-concurrence sous la forme jointe aux prĂ©sentes en tant qu'Annexe C (l'"Accord de Non-concurrence"). L'Accord de Non-concurrence sera en vigueur pour une pĂ©riode de deux ans aprĂšs la rĂ©siliation du prĂ©sent Accord. -NON-SOLICITATION AGREEMENT -Subcontractor shall sign a non-solicitation agreement in the form attached hereto as Exhibit D (the "NSA"). The NSA shall be in effect for a period of two years after the termination of this Agreement. +ACCORD DE NON-SOLLICITATION +Le Sous-traitant signera un accord de non-sollicitation sous la forme jointe aux prĂ©sentes en tant qu'Annexe D (l'"Accord de Non-sollicitation"). L'Accord de Non-sollicitation sera en vigueur pour une pĂ©riode de deux ans aprĂšs la rĂ©siliation du prĂ©sent Accord. -NON-CIRCUMVENTION AGREEMENT -Subcontractor shall sign a non-circumvention agreement in the form attached hereto as Exhibit E (the "NCAg"). The NCAg shall be in effect for a period of two years after the termination of this Agreement. +ACCORD DE NON-CONTOURNEMENT +Le Sous-traitant signera un accord de non-contournement sous la forme jointe aux prĂ©sentes en tant qu'Annexe E (l'"Accord de Non-contournement"). L'Accord de Non-contournement sera en vigueur pour une pĂ©riode de deux ans aprĂšs la rĂ©siliation du prĂ©sent Accord. -TERM AND TERMINATION -This Agreement shall commence on the date set forth above and shall continue in effect until the completion of the Work or until terminated by either party upon thirty (30) days written notice. The non-disclosure, non-compete, non-solicitation, and non-circumvention obligations contained herein shall survive any termination of this Agreement. +DURĂE ET RĂSILIATION +Le prĂ©sent Accord prendra effet Ă la date indiquĂ©e ci-dessous et restera en vigueur jusqu'Ă l'achĂšvement des Travaux ou jusqu'Ă sa rĂ©siliation par l'une ou l'autre des parties moyennant un prĂ©avis Ă©crit de trente (30) jours. Les obligations de confidentialitĂ©, de non-concurrence, de non-sollicitation et de non-contournement contenues dans les prĂ©sentes survivront Ă toute rĂ©siliation du prĂ©sent Accord. -INDEPENDENT CONTRACTOR -Subcontractor is an independent contractor and is not an employee of Contractor. Subcontractor shall be responsible for its own taxes, social security contributions, insurance, and other benefits. Subcontractor shall indemnify and hold Contractor harmless from any claims, damages, or liabilities arising out of or related to Subcontractor's status as an independent contractor. +ENTREPRENEUR INDĂPENDANT +Le Sous-traitant est un entrepreneur indĂ©pendant et n'est pas un employĂ© de l'Entrepreneur. Le Sous-traitant sera responsable de ses propres impĂŽts, cotisations de sĂ©curitĂ© sociale, assurances et autres avantages. Le Sous-traitant indemnisera et dĂ©gagera l'Entrepreneur de toute responsabilitĂ© concernant toute rĂ©clamation, dommage ou responsabilitĂ© dĂ©coulant du statut du Sous-traitant en tant qu'entrepreneur indĂ©pendant ou liĂ©s Ă celui-ci. -GOVERNING LAW AND JURISDICTION -This Agreement shall be governed by and construed in accordance with the laws of the state of [state], without giving effect to any choice of law or conflict of law provisions. Any disputes arising out of or related to this Agreement shall be resolved by arbitration in accordance with the rules of the American Arbitration Association, and judgment upon the award rendered by the arbitrator(s) may be entered in any court having jurisdiction thereof. +LOI APPLICABLE ET JURIDICTION +Le prĂ©sent Accord sera rĂ©gi et interprĂ©tĂ© conformĂ©ment aux lois de l'Ă©tat de [Ă©tat], sans donner effet Ă aucune disposition de choix de loi ou de conflit de lois. Tout litige dĂ©coulant du prĂ©sent Accord ou liĂ© Ă celui-ci sera rĂ©solu par arbitrage conformĂ©ment aux rĂšgles de l'Association AmĂ©ricaine d'Arbitrage, et le jugement sur la sentence rendue par l'arbitre ou les arbitres pourra ĂȘtre inscrit dans tout tribunal compĂ©tent. -ENTIRE AGREEMENT -This Agreement constitutes the entire agreement between the parties and supersedes all prior and contemporaneous agreements and understandings, whether written or oral, relating to the subject matter of this Agreement. This Agreement may not be amended or modified except in writing signed by both parties. +INTĂGRALITĂ DE L'ACCORD +Le prĂ©sent Accord constitue l'intĂ©gralitĂ© de l'accord entre les parties et remplace tous les accords et ententes antĂ©rieurs et contemporains, qu'ils soient Ă©crits ou oraux, relatifs Ă l'objet du prĂ©sent Accord. Le prĂ©sent Accord ne peut ĂȘtre modifiĂ© que par Ă©crit signĂ© par les deux parties. -IN WITNESS WHEREOF, the parties have executed this Agreement as of the date set forth below. +EN FOI DE QUOI, les parties ont signĂ© le prĂ©sent Accord Ă la date indiquĂ©e ci-dessous. -[Government Contractor] +[Entrepreneur Gouvernemental] -By: ____________________________ +Par : ____________________________ -Name: __________________________ +Nom : __________________________ -Title: ___________________________ +Titre : ___________________________ -[Subcontractor] +[Sous-traitant] -By: ____________________________ +Par : ____________________________ -Name: __________________________ +Nom : __________________________ -Title: ___________________________ +Titre : ___________________________ -Date: ___________________________ +Date : ___________________________ ``` -This is a pretty good start. Imaginably you would want to add more information in the scope, payment, and other sections. This is where you would need to use your own knowledge and experience to start iterating on the document. +C'est un bon dĂ©but. On peut imaginer que vous voudriez ajouter plus d'informations dans les sections concernant l'Ă©tendue, le paiement et d'autres aspects. C'est lĂ que vous devriez utiliser vos propres connaissances et expĂ©riences pour commencer Ă amĂ©liorer le document. -## Takeaways +## Points Ă retenir -- LLMs can be used to review and clarify legal documents _in an assistive capacity_. -- LLMs can be used to generate legal documents _in an assistive capacity_. +- Les LLM peuvent ĂȘtre utilisĂ©s pour examiner et clarifier des documents juridiques _dans un rĂŽle d'assistance_. +- Les LLM peuvent ĂȘtre utilisĂ©s pour gĂ©nĂ©rer des documents juridiques _dans un rĂŽle d'assistance_.- Do not use any legal documents on this page. They are for demonstration - purposes only. + N'utilisez aucun document juridique prĂ©sent sur cette page. Ils sont uniquement Ă des fins de dĂ©monstration. diff --git a/(docs)/fr/docs/basic_applications/digital_marketing/page.mdx b/(docs)/fr/docs/basic_applications/digital_marketing/page.mdx index 7272117750f..8e4846c1861 100644 --- a/(docs)/fr/docs/basic_applications/digital_marketing/page.mdx +++ b/(docs)/fr/docs/basic_applications/digital_marketing/page.mdx @@ -1,22 +1,22 @@ -export const metadata = { sidebar_position: 40, title: "đĄ Digital Marketing" }; +export const metadata = { sidebar_position: 40, title: "đĄ Marketing digital" }; -# đĄ Digital Marketing +# đĄ Marketing digital -Your favorite AI chatbot is a treasure trove of resources for both the mundane and the nuanced work of digital marketing, from analysis to content generation to tweaking verbiage. The following examples use a hypothetical website about Pez dispensers. Prompts should be prefixed with "Act as a senior digital marketing specialist" or something similar to elicit the best responses from the chatbot. +Votre chatbot IA prĂ©fĂ©rĂ© est une mine de ressources pour le travail Ă la fois routinier et nuancĂ© du marketing digital, de l'analyse Ă la gĂ©nĂ©ration de contenu en passant par l'ajustement de la formulation. Les exemples suivants utilisent un site web hypothĂ©tique sur les distributeurs Pez. Les prompts doivent ĂȘtre prĂ©fixĂ©s par "Agissez en tant que spĂ©cialiste senior du marketing digital" ou quelque chose de similaire pour obtenir les meilleures rĂ©ponses du chatbot. -## Keyword Research +## Recherche de mots-clĂ©s -Ask your preferred AI chatbot about a particular SEO search phrase (known as a "keyword"): what are its popular variants, synonyms, topic clusters, search intents, and long tail variants? +Demandez Ă votre chatbot IA prĂ©fĂ©rĂ© Ă propos d'une phrase de recherche SEO particuliĂšre (connue sous le nom de "mot-clĂ©") : quelles sont ses variantes populaires, synonymes, clusters thĂ©matiques, intentions de recherche et variantes longue traĂźne ? ```text -PROMPT: Generate a list of keywords related to Pez dispensers. +PROMPT : GĂ©nĂ©rez une liste de mots-clĂ©s liĂ©s aux distributeurs Pez. -PROMPT: Generate a cluster of keywords related to Pez dispensers, and organize with column headings for the cluster, the keyword, and the search intent. +PROMPT : GĂ©nĂ©rez un cluster de mots-clĂ©s liĂ©s aux distributeurs Pez, et organisez-les avec des en-tĂȘtes de colonne pour le cluster, le mot-clĂ© et l'intention de recherche. -PROMPT: Generate a list of long-tail keywords related to Pez dispensers. +PROMPT : GĂ©nĂ©rez une liste de mots-clĂ©s longue traĂźne liĂ©s aux distributeurs Pez. ``` -Try it for your keyword: +Essayez-le pour votre mot-clĂ© :-## Marketing Channel Research +## Recherche de canaux marketing -One of the most important concerns for digital marketers is budgeting their time and resources to different marketing channels. An AI chatbot can give you immediate insights into the types of marketing channels that will work best for a particular client and product. Once you've identified the marketing channels, you can drill down into each to identify strategies and content. +L'une des prĂ©occupations les plus importantes pour les spĂ©cialistes du marketing digital est la rĂ©partition de leur temps et de leurs ressources entre diffĂ©rents canaux marketing. Un chatbot IA peut vous donner des aperçus immĂ©diats sur les types de canaux marketing qui fonctionneront le mieux pour un client et un produit particuliers. Une fois que vous avez identifiĂ© les canaux marketing, vous pouvez approfondir chacun d'eux pour identifier des stratĂ©gies et du contenu. ```text -PROMPT: For a client wishing to promote their Pez dispenser portraying Youtube star MrBeast, with a budget of $100,000, generate a table showing how much money should be spent on which marketing channels. Use columns for the marketing channel, the budget allocation, and the reasoning behind it. +PROMPT : Pour un client souhaitant promouvoir leur distributeur Pez Ă l'effigie de la star YouTube MrBeast, avec un budget de 100 000 $, gĂ©nĂ©rez un tableau montrant combien d'argent devrait ĂȘtre dĂ©pensĂ© sur quels canaux marketing. Utilisez des colonnes pour le canal marketing, l'allocation budgĂ©taire et le raisonnement qui la justifie. -PROMPT: List some strategies to identify Instagram influencers that can help market the MrBeast Pez dispenser. +PROMPT : Listez quelques stratĂ©gies pour identifier des influenceurs Instagram qui peuvent aider Ă commercialiser le distributeur Pez MrBeast. -PROMPT: Create an introductory email to [influencer name], to ask them about initiating a partnership and referencing some of their tweets at https://twitter.com/[influencer]. [requires a chatbot with access to the Web] +PROMPT : CrĂ©ez un email d'introduction Ă [nom de l'influenceur], pour lui demander d'initier un partenariat et en faisant rĂ©fĂ©rence Ă certains de ses tweets sur https://twitter.com/[influenceur]. [nĂ©cessite un chatbot avec accĂšs au Web] -PROMPT: List the top hashtags on Twitter relating to Pez dispensers. +PROMPT : Listez les principaux hashtags sur Twitter relatifs aux distributeurs Pez. ``` -The output for this last prompt ought to something like: +Le rĂ©sultat pour ce dernier prompt devrait ressembler Ă quelque chose comme : ```text {1-8} -Here are some popular hashtags on Twitter related to Pez dispensers: +Voici quelques hashtags populaires sur Twitter liĂ©s aux distributeurs Pez : #PezCollectors #PezDispensers @@ -57,16 +57,16 @@ Here are some popular hashtags on Twitter related to Pez dispensers: etc. ``` -## Tweaking Title Tags and PPC Ads +## Optimisation des balises de titre et des annonces PPC -AI Chatbots are an ideal tool to help generate text that fits within the constraints of SEO and PPC campaigns: +Les chatbots IA sont un outil idĂ©al pour aider Ă gĂ©nĂ©rer du texte qui s'adapte aux contraintes des campagnes SEO et PPC : ```text -PROMPT: Generate a table with 5 snappy title tag options with SEO power words for a blog article announcing a new Pez dispenser portraying MrBeast. Each title should be fewer than 60 characters in length and incorporate the SEO keyword "celebrity Pez dispenser." Add a column to display the 5 corresponding meta descriptions, which must also incorporate the same SEO keyword and a call to action. +PROMPT : GĂ©nĂ©rez un tableau avec 5 options de balises de titre percutantes avec des mots Ă fort impact SEO pour un article de blog annonçant un nouveau distributeur Pez Ă l'effigie de MrBeast. Chaque titre doit comporter moins de 60 caractĂšres et intĂ©grer le mot-clĂ© SEO "distributeur Pez cĂ©lĂ©britĂ©". Ajoutez une colonne pour afficher les 5 mĂ©ta-descriptions correspondantes, qui doivent Ă©galement intĂ©grer le mĂȘme mot-clĂ© SEO et un appel Ă l'action. -PROMPT: Generate 5 compelling headlines, each fewer than 30 characters long, for a Google responsive search ad about collectible Pez dispensers +PROMPT : GĂ©nĂ©rez 5 titres convaincants, chacun de moins de 30 caractĂšres, pour une annonce de recherche responsive Google sur les distributeurs Pez de collection. -PROMPT: Generate 5 relevant three-word CTAs for a new campaign announcing a new line of Pez dispensers featuring MrBeast +PROMPT : GĂ©nĂ©rez 5 CTA pertinents de trois mots pour une nouvelle campagne annonçant une nouvelle ligne de distributeurs Pez mettant en vedette MrBeast. ``` -## Generating Images for Blog Posts +## GĂ©nĂ©ration d'images pour les articles de blog -With the advent of tools like Midjourney, DALL-E, and Stable Diffusion, designers can now use prompt engineering to generate images. If you're unfamiliar with the syntax and techniques of these kinds of prompts, though, you can simply ask an AI chatbot for a set of text-to-image prompts to try out on your preferred AI image generation tool. Note that Midjourney was released after ChatGPT's knowledge cutoff date of September 2021. +Avec l'avĂšnement d'outils comme Midjourney, DALL-E et Stable Diffusion, les designers peuvent dĂ©sormais utiliser l'ingĂ©nierie de prompts pour gĂ©nĂ©rer des images. Si vous n'ĂȘtes pas familier avec la syntaxe et les techniques de ce type de prompts, vous pouvez simplement demander Ă un chatbot IA de vous fournir un ensemble de prompts texte-image Ă essayer avec votre outil de gĂ©nĂ©ration d'images IA prĂ©fĂ©rĂ©. Notez que Midjourney a Ă©tĂ© lancĂ© aprĂšs la date limite de connaissances de ChatGPT de septembre 2021. ```text -PROMPT: Generate 5 concepts for an illustration to accompany a blog article announcing a new Pez dispenser portraying MrBeast. +PROMPT : GĂ©nĂ©rez 5 concepts pour une illustration accompagnant un article de blog annonçant un nouveau distributeur Pez Ă l'effigie de MrBeast. -PROMPT: Generate 5 text-to-image prompts for DALL-E to create dramatic images that convey concept #3 from my earlier prompt. +PROMPT : GĂ©nĂ©rez 5 prompts texte-image pour DALL-E afin de crĂ©er des images dramatiques qui transmettent le concept n°3 de mon prompt prĂ©cĂ©dent. ``` -The output for this last prompt ought to be something like: +Le rĂ©sultat pour ce dernier prompt devrait ressembler Ă quelque chose comme : ```text {1-7} -Certainly! Here are five text-to-image prompts for DALL-E to create dramatic images conveying concept #3: +Certainement ! Voici cinq prompts texte-image pour DALL-E afin de crĂ©er des images dramatiques vĂ©hiculant le concept n°3 : -1. "A majestic procession of Pez dispenser characters marches behind MrBeast, led by the new MrBeast Pez dispenser, symbolizing the rise of a legendary collection." +1. "Une procession majestueuse de personnages de distributeurs Pez dĂ©file derriĂšre MrBeast, menĂ©e par le nouveau distributeur Pez MrBeast, symbolisant l'essor d'une collection lĂ©gendaire." -2. "Surrounded by a radiant aura, MrBeast holds the new Pez dispenser as a beam of light illuminates a room filled with awe-inspiring Pez characters, signifying the power of a legendary addition." +2. "EntourĂ© d'une aura radieuse, MrBeast tient le nouveau distributeur Pez tandis qu'un faisceau de lumiĂšre illumine une piĂšce remplie de personnages Pez impressionnants, signifiant la puissance d'un ajout lĂ©gendaire." -3. "In an epic clash of Pez dispenser heroes, the new MrBeast Pez dispenser stands tall, embodying strength and courage in the face of adversity." +3. "Dans un affrontement Ă©pique de hĂ©ros distributeurs Pez, le nouveau distributeur Pez MrBeast se dresse fiĂšrement, incarnant la force et le courage face Ă l'adversitĂ©." -4. "A storm of Pez candies swirls around MrBeast, forming a vortex of excitement and anticipation, as the new Pez dispenser takes center stage in an exhilarating display." +4. "Une tempĂȘte de bonbons Pez tourbillonne autour de MrBeast, formant un vortex d'excitation et d'anticipation, alors que le nouveau distributeur Pez occupe le devant de la scĂšne dans une dĂ©monstration exaltante." -5. "Silhouetted against a fiery backdrop, MrBeast unveils the new Pez dispenser, its glow radiating hope and inspiration, symbolizing a new era of Pez collecting." +5. "SilhouettĂ© contre un arriĂšre-plan enflammĂ©, MrBeast dĂ©voile le nouveau distributeur Pez, sa lueur irradiant espoir et inspiration, symbolisant une nouvelle Ăšre de collection Pez." ``` -## Technical SEO +## SEO technique -Just as developers use AI chatbots to generate and debug code, digital marketers can use chatbots to analyze and debug technical SEO issues: +Tout comme les dĂ©veloppeurs utilisent des chatbots IA pour gĂ©nĂ©rer et dĂ©boguer du code, les spĂ©cialistes du marketing digital peuvent utiliser des chatbots pour analyser et dĂ©boguer des problĂšmes de SEO technique : ```text -PROMPT: Based on these request and response headers, why isn't Cloudflare returning this web page from its cache? [paste in headers from Chrome Dev Tools] +PROMPT : D'aprĂšs ces en-tĂȘtes de requĂȘte et de rĂ©ponse, pourquoi Cloudflare ne renvoie-t-il pas cette page web depuis son cache ? [collez les en-tĂȘtes depuis Chrome Dev Tools] -PROMPT: Based on the rules at schema.org/HowTo, generate some schema in JSON for how to start a Pez dispenser collection. +PROMPT : D'aprĂšs les rĂšgles de schema.org/HowTo, gĂ©nĂ©rez un schĂ©ma en JSON pour comment dĂ©marrer une collection de distributeurs Pez. -PROMPT: What patterns can you identify in this data set, which is an export of Google Search Console data for 3 months for a company that sells collectible Pez dispensers? [paste Google Sheets URL if your chatbot has web access, otherwise paste CSV data] +PROMPT : Quels motifs pouvez-vous identifier dans cet ensemble de donnĂ©es, qui est une exportation des donnĂ©es Google Search Console sur 3 mois pour une entreprise qui vend des distributeurs Pez de collection ? [collez l'URL Google Sheets si votre chatbot a accĂšs au web, sinon collez les donnĂ©es CSV] -PROMPT: Create Hreflang tags for the German, French and Italian versions of a web page for our retail store in Switzerland, with the base URL https://pezzworld.ch. +PROMPT : CrĂ©ez des balises Hreflang pour les versions allemande, française et italienne d'une page web pour notre magasin de dĂ©tail en Suisse, avec l'URL de base https://pezzworld.ch. -PROMPT: What is a regular expression to identify any search query that includes the singular or plural versions of the words "collectible" or "celebrity" +PROMPT : Quelle est une expression rĂ©guliĂšre (regex) pour identifier toute requĂȘte de recherche qui inclut les versions singuliĂšres ou plurielles des mots "collectionnable" ou "cĂ©lĂ©britĂ©" ``` -The output for this last prompt ought to be something like: +Le rĂ©sultat pour ce dernier prompt devrait ressembler Ă quelque chose comme : ```text {1-3} -To identify search queries that include the singular or plural versions of the words "collectible" or "celebrity" using regular expressions, you can use the following pattern: +Pour identifier les requĂȘtes de recherche qui incluent les versions singuliĂšres ou plurielles des mots "collectionnable" ou "cĂ©lĂ©britĂ©" en utilisant des expressions rĂ©guliĂšres, vous pouvez utiliser le modĂšle suivant : -\b(collectible|collectibles|celebrity|celebrities)\b +\b(collectionnable|collectionnables|cĂ©lĂ©britĂ©|cĂ©lĂ©britĂ©s)\b ``` -## Social Media Marketing +## Marketing sur les rĂ©seaux sociaux -Beyond simply generating content for posts, there are a multitude of use cases for generative AI in social media marketing: +Au-delĂ de simplement gĂ©nĂ©rer du contenu pour les publications, il existe une multitude de cas d'utilisation pour l'IA gĂ©nĂ©rative dans le marketing sur les rĂ©seaux sociaux : ```text -PROMPT: The Twitter post at the end of this prompt compliments our company on its Pez dispensers; compose a thank-you reply. Include relevant hashtags and mentions of [@person1] and [@person2], who posted similar compliments. Incorporate a funny emoji. Offer an incentive for other users to retweet our response. Let the author know that we have reposted his tweet. Make sure the reply has fewer than 280 characters. Their Twitter post is: [paste] +PROMPT : Le tweet Ă la fin de ce prompt complimente notre entreprise sur ses distributeurs Pez ; composez une rĂ©ponse de remerciement. Incluez des hashtags et mentions pertinents de [@personne1] et [@personne2], qui ont postĂ© des compliments similaires. Incorporez un emoji amusant. Offrez une incitation pour que d'autres utilisateurs retweetent notre rĂ©ponse. Faites savoir Ă l'auteur que nous avons repostĂ© son tweet. Assurez-vous que la rĂ©ponse contient moins de 280 caractĂšres. Son tweet est : [coller] -PROMPT: We run a company offering celebrity Pez dispensers. Our newest product is a Pez dispenser featuring MrBeast, a Youtube influencer. Generate 5 ideas for social media contests to run on Twitter that will cross-promote our line of Pez dispensers to fans of artistic round tins of hard candy. For each idea, output a sample post with hashtags and emoji to explain the contest in fewer than 280 characters. +PROMPT : Nous dirigeons une entreprise proposant des distributeurs Pez de cĂ©lĂ©britĂ©s. Notre nouveau produit est un distributeur Pez Ă l'effigie de MrBeast, un influenceur YouTube. GĂ©nĂ©rez 5 idĂ©es de concours sur les rĂ©seaux sociaux Ă organiser sur Twitter qui feront la promotion croisĂ©e de notre gamme de distributeurs Pez auprĂšs des fans de boĂźtes rondes artistiques de bonbons durs. Pour chaque idĂ©e, produisez un exemple de publication avec des hashtags et des emojis pour expliquer le concours en moins de 280 caractĂšres. -PROMPT: Respond to this negative Yelp review in a polite, respectful and measured tone, but counter the customer's complaint about the quality of our pez dispensers. Emphasizing the care our factory staff take in manufacturing them and the 3 rounds of quality inspections before shipping them. Your response should have fewer than 50 words. The negative review is: "It arrived broken, PezzWorld sucks." +PROMPT : RĂ©pondez Ă cette critique nĂ©gative sur Yelp avec un ton poli, respectueux et mesurĂ©, mais contestez la plainte du client concernant la qualitĂ© de nos distributeurs Pez. Soulignez le soin que notre personnel d'usine apporte Ă leur fabrication et les 3 cycles d'inspections qualitĂ© avant l'expĂ©dition. Votre rĂ©ponse doit contenir moins de 50 mots. La critique nĂ©gative est : "Il est arrivĂ© cassĂ©, PezzWorld est nul." ``` -The output for this last prompt ought to something like: +Le rĂ©sultat pour ce dernier prompt devrait ressembler Ă quelque chose comme : ```text {1-1} -We're truly sorry to hear your dispenser arrived broken. Our factory staff meticulously craft each piece, and it undergoes 3 rounds of quality inspections before shipping. We'd love to make it right for you. Please reach out for a replacement. +Nous sommes vraiment dĂ©solĂ©s d'apprendre que votre distributeur est arrivĂ© cassĂ©. Notre personnel d'usine fabrique mĂ©ticuleusement chaque piĂšce, et elle subit 3 cycles d'inspections qualitĂ© avant l'expĂ©dition. Nous aimerions rĂ©parer cette situation. Veuillez nous contacter pour un remplacement. ``` --- -Contributed by _[Prompt Yes!](https://promptyes.com)_, a company offering instructor-led courses in [ChatGPT](https://promptyes.com/classes/productivity/) and [Midjourney](https://promptyes.com/classes/midjourney/). +ContribuĂ© par _[Prompt Yes!](https://promptyes.com)_, une entreprise proposant des cours avec instructeur sur [ChatGPT](https://promptyes.com/classes/productivity/) et [Midjourney](https://promptyes.com/classes/midjourney/). diff --git a/(docs)/fr/docs/basic_applications/summarize/page.mdx b/(docs)/fr/docs/basic_applications/summarize/page.mdx index a4fd975a8a4..431ad447da0 100644 --- a/(docs)/fr/docs/basic_applications/summarize/page.mdx +++ b/(docs)/fr/docs/basic_applications/summarize/page.mdx @@ -1,14 +1,17 @@ -export const metadata = { sidebar_position: 70, title: "đą Summarizing Text" }; +export const metadata = { + sidebar_position: 70, + title: "đą RĂ©sumer des textes", +}; -# đą Summarizing Text +# đą RĂ©sumer des textes -ChatGPT is notorious for producing content in the blink of an eye, and has proven to be a huge time saver. -For content already written, ChatGPT can also save us time by helping us digest long torturous texts. -It can summarize books, movies, plays, articles and many more. With ChatGPT, itâs like having a Cliffâs NotesâŠON EVERYTHING! +ChatGPT est connu pour produire du contenu en un clin d'Ćil, et s'est avĂ©rĂ© ĂȘtre un Ă©norme gain de temps. +Pour le contenu dĂ©jĂ Ă©crit, ChatGPT peut Ă©galement nous faire gagner du temps en nous aidant Ă digĂ©rer de longs textes tortueux. +Il peut rĂ©sumer des livres, des films, des piĂšces de théùtre, des articles et bien plus encore. Avec ChatGPT, c'est comme avoir un Cliff's Notes... SUR TOUT ! -## Summarizing from Scratch +## RĂ©sumer Ă partir de zĂ©ro -Sometimes, you can ask ChatGPT to summarize famous works without pasting in any additional text, since ChatGPT knows the works so well. For example, you can ask it to summarize âRomeo & Julietâ by act. So, instead of slogging through the 24,000 words of the play, you can get the gist in 300 or less. +Parfois, vous pouvez demander Ă ChatGPT de rĂ©sumer des Ćuvres cĂ©lĂšbres sans coller de texte supplĂ©mentaire, car ChatGPT connaĂźt si bien ces Ćuvres. Par exemple, vous pouvez lui demander de rĂ©sumer "RomĂ©o et Juliette" acte par acte. Ainsi, au lieu de vous battre avec les 24 000 mots de la piĂšce, vous pouvez en saisir l'essentiel en 300 mots ou moins. -Although you could instead look up a summary, ChatGPT can tailor the content to your needs. Maybe you really like Football, so you could as ChatGPT to -âGive me a 100 word summary of âRomeo and Julietâ in American football terms.â +Bien que vous puissiez chercher un rĂ©sumĂ© ailleurs, ChatGPT peut adapter le contenu Ă vos besoins. Peut-ĂȘtre aimez-vous beaucoup le football amĂ©ricain, vous pourriez donc demander Ă ChatGPT de +"Me donner un rĂ©sumĂ© de 100 mots de 'RomĂ©o et Juliette' en termes de football amĂ©ricain." -## Working With Long Blocks of Texts: Copy & Paste! +## Travailler avec de longs blocs de texte : Copier & Coller ! -You can ask ChatGPT to summarize or create an outline of the text and TL;DR the whole thing. All you have to do is copy and paste the specific text into the prompt. (You can include up to 2,500 words. If the work is longer than that, you will have to break it into chunks.) -Ask for a simplified summary of chosen text by writing, âSummarize this for me like I'm 5 years old: [PASTE TEXT HERE]â -This one is a summary âfor a 5-year oldâ from a section of Wikipediaâs entry on â[quantum entanglement](https://en.wikipedia.org/wiki/Quantum_entanglement#:~:text=vte-,Quantum%20entanglement,-is%20the%20phenomenon)â. +Vous pouvez demander Ă ChatGPT de rĂ©sumer ou de crĂ©er un plan du texte et de faire un TL;DR ("Too Long; Didn't Read", qui veut dire : trop long ; pas lu) de l'ensemble. Tout ce que vous avez Ă faire est de copier et coller le texte spĂ©cifique dans le prompt. (Vous pouvez inclure jusqu'Ă 2 500 mots. Si l'Ćuvre est plus longue que cela, vous devrez la diviser en morceaux.) +Demandez un rĂ©sumĂ© simplifiĂ© du texte choisi en Ă©crivant : "RĂ©sumez ceci pour moi comme si j'avais 5 ans : [COLLER LE TEXTE ICI]" +Voici un rĂ©sumĂ© "pour un enfant de 5 ans" d'une section de l'article WikipĂ©dia sur "[l'intrication quantique](https://fr.wikipedia.org/wiki/Intrication_quantique)". -In addition to summaries, you can also ask ChatGPT to write outlines for blocks of text. Sometimes itâs better to have an outline so that you can see the thread or framework of the whole article. -You also just need to copy and paste the text you want outlined into your prompt. -The following is ChatGPTâs outline on the Wikipedia page on ârope,â specifically on the history of [rope](https://en.wikipedia.org/wiki/Rope#:~:text=to%20pull%20ropes.-,History,-Ancient%20Egyptians%20were). +En plus des rĂ©sumĂ©s, vous pouvez Ă©galement demander Ă ChatGPT de rĂ©diger des plans pour des blocs de texte. Parfois, il est prĂ©fĂ©rable d'avoir un plan pour que vous puissiez voir le fil conducteur ou la structure de l'article entier. +Vous n'avez qu'Ă copier et coller le texte que vous souhaitez structurer dans votre prompt. +Voici le plan de ChatGPT sur la page WikipĂ©dia sur la "corde", spĂ©cifiquement sur l'histoire de la [corde](https://en.wikipedia.org/wiki/Rope#:~:text=to%20pull%20ropes.-,History,-Ancient%20Egyptians%20were). -Weâve just covered some of the very basics of using ChatGPT to handle long texts. There are many more ways to use ChatGPT to summarize and outline texts! +Nous venons de couvrir quelques-unes des bases de l'utilisation de ChatGPT pour gĂ©rer de longs textes. Il existe de nombreuses autres façons d'utiliser ChatGPT pour rĂ©sumer et structurer des textes ! -By [languagenoodle](https://twitter.com/languagenoodle). +Par [languagenoodle](https://twitter.com/languagenoodle). diff --git a/(docs)/fr/docs/basic_applications/writing_in_diff_voices/page.mdx b/(docs)/fr/docs/basic_applications/writing_in_diff_voices/page.mdx index aa0a726bc6e..8c400011b35 100644 --- a/(docs)/fr/docs/basic_applications/writing_in_diff_voices/page.mdx +++ b/(docs)/fr/docs/basic_applications/writing_in_diff_voices/page.mdx @@ -1,15 +1,15 @@ export const metadata = { sidebar_position: 60, - title: "đą Different Writing Styles", + title: "đą DiffĂ©rents Styles d'Ăcriture", }; -# đą Different Writing Styles +# đą DiffĂ©rents styles d'Ă©criture -AIs like [ChatGPT](https://chat.openai.com/chat) are known for crafting essays and blog articles in a heartbeat. But often, the articles they produce are generic and dry. You need to do something extra to give the words some spirit or pizzazz. -One of the fastest ways to do that is to specify a writing style or naming a famous author in the prompt. +Les IA comme [ChatGPT](https://chat.openai.com/chat) sont connues pour rĂ©diger des essais et des articles de blog en un instant. Mais souvent, les articles qu'elles produisent sont gĂ©nĂ©riques et sans saveur. Vous devez faire quelque chose de plus pour donner de l'esprit ou du piquant aux mots. +L'une des façons les plus rapides de le faire est de spĂ©cifier un style d'Ă©criture ou de nommer un auteur cĂ©lĂšbre dans le prompt. -Say you want a paragraph on the importance of friendship. -A generic prompt like, âWrite me a paragraph on the importance of friendship,â will yield a generic response from ChatGPT. +Disons que vous voulez un paragraphe sur l'importance de l'amitiĂ©. +Un prompt gĂ©nĂ©rique comme "Ăcrivez-moi un paragraphe sur l'importance de l'amitiĂ©" donnera une rĂ©ponse gĂ©nĂ©rique de ChatGPT. -Blah. Itâs so bland. -Results change when you add specifications, like â**Please write in an informal, conversational style.**â ChatGPT comes up with something like this: +Bof. C'est tellement fade. +Les rĂ©sultats changent lorsque vous ajoutez des spĂ©cifications, comme "**Veuillez Ă©crire dans un style informel et conversationnel.**" ChatGPT propose alors quelque chose comme ceci : -Thatâs a little better. +C'est un peu mieux. -And if you feel a little fancy, you can ask ChatGPT to write in the style of one of the literary greats, like Mark Twain: +Et si vous vous sentez un peu sophistiquĂ©, vous pouvez demander Ă ChatGPT d'Ă©crire dans le style de l'un des grands Ă©crivains, comme Mark Twain : -The text now is starting to sing. -But it doesnât have to be a famous author. You can use well-known individuals as wellâlike Chris Rock. +Le texte commence maintenant Ă chanter. +Mais il ne doit pas nĂ©cessairement s'agir d'un auteur cĂ©lĂšbre. Vous pouvez Ă©galement utiliser des personnalitĂ©s bien connues, comme Chris Rock. -Or how about those âmillennialsâ? +Ou que diriez-vous de ces "millennials" ? -## Copy Your Writing Style +## Copiez votre style d'Ă©criture -What if you want GPT-3 to write an email or blog in **your** style? +Et si vous vouliez que GPT-3 Ă©crive un courriel/e-mail ou un blog dans **votre** style ? -Simply showing it some previous content that you have written is enough. Here is an example, where we show GPT-3 some emails 'Dr. Rodriguez' has written in the past, and ask it to write a new email in the same style to a new patient, Mr. Inuez. +Il suffit simplement de lui montrer du contenu que vous avez Ă©crit prĂ©cĂ©demment. Voici un exemple, oĂč nous montrons Ă GPT-3 quelques e-mails que le 'Dr. Rodriguez' a Ă©crits dans le passĂ©, et lui demandons d'Ă©crire un nouvel e-mail dans le mĂȘme style Ă un nouveau patient, M. Inuez.
-You can input any text you have written in the past (emails, reports, blogs, etc.), -and GPT-3/ChatGPT will usually be able to copy your style. The more text you put, -the better it can copy your style. +Vous pouvez saisir n'importe quel texte que vous avez Ă©crit dans le passĂ© (e-mails, +rapports, blogs, etc.), et GPT-3/ChatGPT sera gĂ©nĂ©ralement capable de copier votre +style. Plus vous fournissez de texte, mieux il pourra reproduire votre style. diff --git a/(docs)/fr/docs/basic_applications/zapier_for_emails/page.mdx b/(docs)/fr/docs/basic_applications/zapier_for_emails/page.mdx index 6a29626ffe8..6fdcac727ad 100644 --- a/(docs)/fr/docs/basic_applications/zapier_for_emails/page.mdx +++ b/(docs)/fr/docs/basic_applications/zapier_for_emails/page.mdx @@ -1,31 +1,31 @@ export const metadata = { sidebar_position: 600, - title: "đą Zapier for Emails", + title: "đą Zapier pour les Emails", }; -# đą Zapier for Emails +# đą Zapier pour les Emails ## Introduction -We have already seen how useful GPT-3 can be when it comes to emails. It can be even more so when you combine it with **nocode** tools like [Zapier](https://zapier.com) or [Bubble.io](https://bubble.io). +Nous avons dĂ©jĂ vu Ă quel point GPT-3 peut ĂȘtre utile pour les emails. Il peut l'ĂȘtre encore plus lorsque vous le combinez avec des outils **nocode** comme [Zapier](https://zapier.com) ou [Bubble.io](https://bubble.io). -This article will contain an example of what Zapier+GPT-3 can do with only a small amount of setup time. This article focuses on a particular example, but the possibilities are much greater. We'll give some other examples along the way. Keep in mind you can also do this in Bubble.io. There are many other nocode tools, but at the time of writing only very few allow you to use GPT-3. +Cet article contiendra un exemple de ce que Zapier+GPT-3 peut faire avec seulement un peu de temps de configuration. Cet article se concentre sur un exemple particulier, mais les possibilitĂ©s sont bien plus grandes. Nous donnerons d'autres exemples en cours de route. Gardez Ă l'esprit que vous pouvez Ă©galement faire cela dans Bubble.io. Il existe de nombreux autres outils nocode, mais au moment de la rĂ©daction, trĂšs peu vous permettent d'utiliser GPT-3. -In this article we will show you how to set up a simple system in Zapier in which **e-mails are summarized and stored**. Have a meeting with someone? Quickly check the summaries of emails you've exchanged with that person. Setting this up takes about 20 minutes. +Dans cet article, nous vous montrerons comment configurer un systĂšme simple dans Zapier dans lequel **les e-mails sont rĂ©sumĂ©s et stockĂ©s**. Vous avez une rĂ©union avec quelqu'un ? Consultez rapidement les rĂ©sumĂ©s des emails que vous avez Ă©changĂ©s avec cette personne. La mise en place prend environ 20 minutes.- It is helpful to already know Zapier for this article. If you don't, you can - check out this [article](https://zapier.com/learn/). + Il est utile de connaĂźtre dĂ©jĂ Zapier pour cet article. Si ce n'est pas le + cas, vous pouvez consulter cet [article](https://zapier.com/learn/). -## General Idea +## IdĂ©e gĂ©nĂ©rale -Below is a diagram of what we will be doing here in Zapier. Whenever an email comes into your inbox, it will trigger Zapier. There are four steps (for now): +Ci-dessous se trouve un diagramme de ce que nous ferons ici dans Zapier. Chaque fois qu'un email arrive dans votre boĂźte de rĂ©ception, il dĂ©clenchera Zapier. Il y a quatre Ă©tapes (pour l'instant) : -1. Email comes in and trigger Zapier -1. Format the content of the email (to remove HTML markdown, for example). -1. Send it to GPT-3 to be summarized -1. Store the output in a database +1. L'email arrive et dĂ©clenche Zapier +1. Formatage du contenu de l'email (pour supprimer le markdown HTML, par exemple). +1. Envoi Ă GPT-3 pour ĂȘtre rĂ©sumĂ© +1. Stockage de la sortie dans une base de donnĂ©es-## Set-up in Zapier +## Configuration dans Zapier -Make sure to have a [Zapier account](https://zapier.com/sign-up) (you can get a free one). Setting it up should be fairly straightforward. After making your account, expand the below box to see full descriptions of each Zapier action we need to create. +Assurez-vous d'avoir un [compte Zapier](https://zapier.com/sign-up) (vous pouvez en obtenir un gratuitement). La configuration devrait ĂȘtre assez simple. AprĂšs avoir créé votre compte, dĂ©veloppez la boĂźte ci-dessous pour voir les descriptions complĂštes de chaque action Zapier que nous devons crĂ©er. -Expand for a more detailed view of the steps in Zapier
+Développez pour une vue plus détaillée des étapes dans Zapier
- This is what the Zapier action diagram will eventually look like. + Voici Ă quoi ressemblera finalement le diagramme d'action Zapier.- Step 1: Gmail trigger on new incoming email (Gmail is used here). + Ătape 1 : DĂ©clencheur Gmail sur nouvel email entrant (Gmail est utilisĂ© ici).
@@ -73,7 +73,7 @@ Make sure to have a [Zapier account](https://zapier.com/sign-up) (you can get a--Here is a set-up in zapier that allows you to do a very basic summary as shown in -the diagram. It has itâs limitation, but it does do the job and can build up a useful -database. +Voici une configuration dans Zapier qui vous permet de faire un rĂ©sumĂ© trĂšs basique comme indiquĂ© dans +le diagramme. Elle a ses limites, mais elle fait le travail et peut constituer une base de donnĂ©es utile. -## Optimizing the prompt for better results +## Optimisation du prompt pour de meilleurs rĂ©sultats -There are a few easy ways to improve your results. Adding context and role prompting can improve the output. However, the topic and contents of your emails might cover a wide range of topics. This means that general instructions will do a better job than very specific ones, which might throw the model off. +Il existe quelques façons simples d'amĂ©liorer vos rĂ©sultats. Ajouter du contexte et des prompts de rĂŽle peut amĂ©liorer la sortie. Cependant, le sujet et le contenu de vos emails peuvent couvrir un large Ă©ventail de sujets. Cela signifie que des instructions gĂ©nĂ©rales feront un meilleur travail que des instructions trĂšs spĂ©cifiques, qui pourraient dĂ©router le modĂšle. -For practical reasons, it is useful to give an instruction, followed by telling GPT-3 when the email starts in the prompt by simply adding "Email: " and ending the prompt with ""Summary": ". This avoids GPT-3 answering with "Sure! I can summarize it for you...". +Pour des raisons pratiques, il est utile de donner une instruction, suivie en indiquant Ă GPT-3 quand l'email commence dans le prompt en ajoutant simplement "Email : " et en terminant le prompt par "RĂ©sumĂ© : ". Cela Ă©vite que GPT-3 ne rĂ©ponde par "Bien sĂ»r ! Je peux le rĂ©sumer pour vous...". -Role prompting can be useful here as well. Asking GPT-3 to act as a personal assistant helps increase the quality of the summary. -If you want to summarize work emails, simply adding the role you have gives GPT-3 context to work with. It acts as if it assumes some level of knowledge from the reader, which helps filter out the non-relevant parts of the email. -Below we show some examples with emails an office administrator might receive. +Le prompting de rĂŽle peut Ă©galement ĂȘtre utile ici. Demander Ă GPT-3 d'agir comme un assistant personnel aide Ă augmenter la qualitĂ© du rĂ©sumĂ©. +Si vous voulez rĂ©sumer des emails professionnels, ajouter simplement le rĂŽle que vous avez donne Ă GPT-3 un contexte avec lequel travailler. Il agit comme s'il supposait un certain niveau de connaissance de la part du lecteur, ce qui aide Ă filtrer les parties non pertinentes de l'email. +Ci-dessous, nous montrons quelques exemples avec des emails qu'un administrateur de bureau pourrait recevoir. -You can ask it to summarize a simple email in bullet points, however, this might not be all that useful depending on how you would like to use the summary. For quick skimming of email exchanges you might just want it to be short and concise. Simply asking for this in the prompt works well. Below is an example of this prompt. Adjust it and play around with it to see how it changes. +Vous pouvez lui demander de rĂ©sumer un email simple en points, cependant, cela pourrait ne pas ĂȘtre si utile selon la façon dont vous souhaitez utiliser le rĂ©sumĂ©. Pour parcourir rapidement les Ă©changes d'emails, vous pourriez simplement vouloir qu'il soit court et concis. Demander simplement cela dans le prompt fonctionne bien. Ci-dessous est un exemple de ce prompt. Ajustez-le et jouez avec pour voir comment il change.Step 2: Formatter for E-mail content.
+Ătape 2 : Formateur pour le contenu de l'email.
@@ -88,7 +88,7 @@ Make sure to have a [Zapier account](https://zapier.com/sign-up) (you can get a- Step 3: Prompting the Email content + Ătape 3 : Prompting pour le contenu de l'email
@@ -104,7 +104,7 @@ Make sure to have a [Zapier account](https://zapier.com/sign-up) (you can get a
-+Step 4: Adding it to a database
+Ătape 4 : Ajout Ă une base de donnĂ©es
@@ -117,23 +117,23 @@ Make sure to have a [Zapier account](https://zapier.com/sign-up) (you can get a-The response here is acceptable, and would be useful. However, with some further finetuning you can get a better result. As the reader of the summaries you don't care that it's an email, you might want a lower level of detail for the summary. Information about the why is irrelevant, same goes for the last sentence about questions and concerns. By simply adding that the goal of the summary is for you to skim the contents and that you want pleasantries removed, the result can be improved. +La rĂ©ponse ici est acceptable et serait utile. Cependant, avec quelques ajustements supplĂ©mentaires, vous pouvez obtenir un meilleur rĂ©sultat. En tant que lecteur des rĂ©sumĂ©s, vous ne vous souciez pas qu'il s'agisse d'un email, vous pourriez vouloir un niveau de dĂ©tail infĂ©rieur pour le rĂ©sumĂ©. Les informations sur le pourquoi sont sans importance, tout comme la derniĂšre phrase concernant les questions et prĂ©occupations. En ajoutant simplement que l'objectif du rĂ©sumĂ© est de vous permettre de parcourir rapidement le contenu et que vous souhaitez supprimer les formules de politesse, le rĂ©sultat peut ĂȘtre amĂ©liorĂ©.
-Now you're left with only the most important parts of the summary! +Il ne vous reste plus que les parties les plus importantes du rĂ©sumĂ© ! -## Other usecases +## Autres cas d'utilisation -Now that you've seen the example of summaries, We will mention a few other use cases for Zapier+GPT-3. One great example is letting GPT-3 categorize your emails. This just comes down to telling it in a prompt to categorize the following email as whatever categories you like. +Maintenant que vous avez vu l'exemple des rĂ©sumĂ©s, nous allons mentionner quelques autres cas d'utilisation pour Zapier+GPT-3. Un excellent exemple consiste Ă laisser GPT-3 catĂ©goriser vos emails. Cela revient simplement Ă lui indiquer dans un prompt de catĂ©goriser l'email suivant selon les catĂ©gories que vous souhaitez. -A more in depth example would be having multiple prompts. You can use a prompt to generate a response that agrees with the demands of the email and one that disagrees or denies. Both can be stored in your drafts and be ready to go whenever you want to send it. +Un exemple plus approfondi serait d'avoir plusieurs prompts. Vous pouvez utiliser un prompt pour gĂ©nĂ©rer une rĂ©ponse qui accepte les demandes de l'email et un autre qui refuse ou rejette. Les deux peuvent ĂȘtre stockĂ©s dans vos brouillons et ĂȘtre prĂȘts Ă ĂȘtre envoyĂ©s quand vous le souhaitez. -If you regularly receive very similar emails, you can use a filter in Zapier to apply a prompt ONLY to that email. This can be a powerful tool when combined with a formatter. You can extract information and export CSV's from them or directly store them in some form of a database. +Si vous recevez rĂ©guliĂšrement des emails trĂšs similaires, vous pouvez utiliser un filtre dans Zapier pour appliquer un prompt UNIQUEMENT Ă ce type d'email. Cela peut ĂȘtre un outil puissant lorsqu'il est combinĂ© avec un formateur. Vous pouvez en extraire des informations et exporter des CSV ou les stocker directement dans une forme de base de donnĂ©es. -## Concerns +## PrĂ©occupations -Please do keep in mind privacy concerns when running emails through GPT-3 and storing them. GPT-3 sometimes makes mistakes. We highly recommend checking email content before sending. +N'oubliez pas de prendre en compte les problĂšmes de confidentialitĂ© lorsque vous traitez des emails via GPT-3 et que vous les stockez. GPT-3 fait parfois des erreurs. Nous recommandons vivement de vĂ©rifier le contenu des emails avant de les envoyer. diff --git a/(docs)/fr/docs/missing.json b/(docs)/fr/docs/missing.json index 4be7aefb17e..1ecc65ae52f 100644 --- a/(docs)/fr/docs/missing.json +++ b/(docs)/fr/docs/missing.json @@ -34,48 +34,6 @@ } ] }, - { - "slug": "applied_prompting", - "title": "đ§Ș Applied Prompting", - "position": 19, - "subpages": [ - { - "slug": "overview", - "title": "đą Introduction", - "position": 1, - "href": "\\docs\\applied_prompting\\overview", - "subpages": null - }, - { - "slug": "mc_tutorial", - "title": "đą Multiple Choice Questions", - "position": 2, - "href": "\\docs\\applied_prompting\\mc_tutorial", - "subpages": null - }, - { - "slug": "short_response", - "title": "đą Solve Discussion Questions", - "position": 3, - "href": "\\docs\\applied_prompting\\short_response", - "subpages": null - }, - { - "slug": "build_chatgpt", - "title": "đą Build ChatGPT from GPT-3", - "position": 4, - "href": "\\docs\\applied_prompting\\build_chatgpt", - "subpages": null - }, - { - "slug": "build_chatbot_from_kb", - "title": "đą Chatbot + Knowledge Base", - "position": 40, - "href": "\\docs\\applied_prompting\\build_chatbot_from_kb", - "subpages": null - } - ] - }, { "slug": "image_prompting", "title": "đŒïž Image Prompting",