Fixed Bugs and Added some useful functions.... #491

Rawknee-69 · 2024-04-26T10:29:11Z

No description provided.

ARajgor · 2024-04-26T12:28:21Z

remove the lock file

ARajgor · 2024-04-26T16:37:58Z

can you give me access to contribute to this pr?

Rawknee-69 · 2024-04-26T17:14:04Z

what you wanna contribute

ARajgor · 2024-04-26T17:43:28Z

resolve the conflict and merge the main to this. also, where do you use the knowledge function I couldn't find it.

obliviousz · 2024-04-26T18:44:50Z

"You are an angelic AI Software Engineer, remarkable in intelligence and devoted to establishing a welcoming ambiance for users. Demonstrating perpetual politeness, grace, and acute awareness, you adeptly interpret and cater to user necessities. Taking into account earlier dialogues:"

Is all these very necessary? What I feel is it might be using up some extra tokens. Because this was under actions. It anyways just have to provide the action for subsequent execute. Let me know if I am wrong.

obliviousz

I just had these queries regarding your PR. We can discuss about these. Thanks!

obliviousz · 2024-04-26T18:46:33Z

src/agents/action/prompt.jinja2

@@ -1,31 +1,45 @@
-You are Devika, an AI Software Engineer. You have been talking to the user and this is your exchanges so far:
+You are an angelic AI Software Engineer, remarkable in intelligence and devoted to establishing a welcoming ambiance for users. Demonstrating perpetual politeness, grace, and acute awareness, you adeptly interpret and cater to user necessities. Taking into account earlier dialogues:


I feel it's not so much necessary as it is instructed to just give the action and not really interact with the user. I agree there is a response too, but as an Software engineer, its not gonna bash the user with something and that's why we do we really need these terms like "angelic" or "politeness, grace, ..." etc.

obliviousz · 2024-04-26T18:46:58Z

src/agents/action/prompt.jinja2


-You are now going to respond to the user's last message according to the specific request.
+YFormulate a response tailored to the user's last message, limiting superfluous communications.


"YFormulate"?

Sorry, just a typo ! Fixed it

src/agents/agent.py

obliviousz · 2024-04-26T18:50:27Z

src/agents/coder/prompt.jinja2

+Special Rules:
+The most important rule is that you have to understand what the user is aksing for and then give the code no rubbish code will be tolerated.
+
+1. Never miss any imports , if you are not sure you can check about it on web.


How can offline models like gpt3.5,4 or llama2/3 check it in the web unless we add web functionality?

yup it may not check it , but gpt 4 , groq and gemini 1.0 can do so , well gpt 4 is not offline acc. to me it searches the web for results on backgroud if your api plans supports it

gpt4 is an offline model : https://community.openai.com/t/does-gpt-4-api-have-access-to-the-internet/468615#:~:text=Other%20Filler%20Text.,-jwatte%20November%203&text=No%2C%20GPT%2D4%20is%20just,services%20that%20drive%20this%20model.

Also groq uses mistral, llama2, llama3,etc which are offline models

okay i get it , sorry i was wrong there , but adding this line decreased the rate of bugs and now it more frequently looks on the web to be sure and also if like we use gemini 1.0 we would be able to surf the web at the model inference it self and on the browser also hence more quality answers we get

We can take opinion from @ARajgor or @nalaso for this one

I wanted to point out, which models work with ollama, by adding to this piece of prompt:
"Your response should only be in the following Markdown format"
this other piece:
"like this example obviously replacing the example code with your own code:"
The models can complete the tasks well, otherwise they simply write the example as completing the task.

on this link I demonstrate the completion of "the game of life" task completed correctly.
#347 (comment)

obliviousz · 2024-04-26T18:53:38Z

src/bert/sentence.py

@@ -12,6 +12,6 @@ def extract_keywords(self, top_n: int = 5) -> list:
            stop_words='english',
            top_n=top_n,
            use_mmr=True,
-            diversity=0.7
+            diversity=0.6


why is the diversity changed here?

it gives a better understanding and more the diversity more creative answers and less precise one , if we want a precise result we have to make it less to the point which is prefect for the code understanding

Rawknee-69 · 2024-04-26T18:56:02Z

"You are an angelic AI Software Engineer, remarkable in intelligence and devoted to establishing a welcoming ambiance for users. Demonstrating perpetual politeness, grace, and acute awareness, you adeptly interpret and cater to user necessities. Taking into account earlier dialogues:"

Is all these very necessary? What I feel is it might be using up some extra tokens. Because this was under actions. It anyways just have to provide the action for subsequent execute. Let me know if I am wrong.

actually there is a problem that after some replies the llm's starts to hallucinate and the responses it give degrades it quality , sure it takes some extra token but this helps llms to make sure they are in their character and doesn't hallucinate and it also reflects the personality of the llm's

obliviousz · 2024-04-26T19:02:17Z

"You are an angelic AI Software Engineer, remarkable in intelligence and devoted to establishing a welcoming ambiance for users. Demonstrating perpetual politeness, grace, and acute awareness, you adeptly interpret and cater to user necessities. Taking into account earlier dialogues:"
Is all these very necessary? What I feel is it might be using up some extra tokens. Because this was under actions. It anyways just have to provide the action for subsequent execute. Let me know if I am wrong.

actually there is a problem that after some replies the llm's starts to hallucinate and the responses it give degrades it quality , sure it takes some extra token but this helps llms to make sure they are in their character and doesn't hallucinate and it also reflects the personality of the llm's

But everytime we set the context again no? With every prompt. How is it possible?

Rawknee-69 · 2024-04-26T19:20:45Z

resolve the conflict and merge the main to this. also, where do you use the knowledge function I couldn't find it.

actually i have modified the knowledge function and didn't changed anything on part of variables so the knowledge function where you have used it previously is there but only the style to store and to extract it is changed by using the a llm that run's locally and using faiss

Rawknee-69 · 2024-04-26T19:24:21Z

resolve the conflict and merge the main to this. also, where do you use the knowledge function I couldn't find it.

done resloved the conflicts and also explaied about the knowledge part

obliviousz

I havent gone deep into each prompt and each instruction but I've added comments where ever I felt it could be changed. Thanks!

obliviousz · 2024-04-26T22:36:42Z

src/agents/agent.py

-        )
+
+        self.project_manager.add_message_from_devika(project_name,
+                                                     "I have completed the my task and after this many work i am going to sleep ,wake me whenever i am needed\n"


English could be improved if we really want to keep this thing. Something like

"... sleep. Do not hesitate to wake me up if you need me at any time"

obliviousz · 2024-04-26T22:38:03Z

src/agents/coder/prompt.jinja2

+
+4. Accurately specify nested directory structures in the Markdown filenames. Organize the code structure appropriately.
+
+5. Include necessary files such as `requirements.txt`, `Cargo.toml`, or `readme.md`. These files are essential for successful execution.


Also add "As per the requirement and tech stack of the project"

obliviousz · 2024-04-26T22:41:45Z

src/bert/sentence.py

@@ -12,6 +12,6 @@ def extract_keywords(self, top_n: int = 5) -> list:
            stop_words='english',
            top_n=top_n,
            use_mmr=True,
-            diversity=0.7
+            diversity=0.6


obliviousz · 2024-04-26T22:42:09Z

src/agents/coder/prompt.jinja2

+Special Rules:
+The most important rule is that you have to understand what the user is aksing for and then give the code no rubbish code will be tolerated.
+
+1. Never miss any imports , if you are not sure you can check about it on web.


We can take opinion from @ARajgor or @nalaso for this one

Updated some prompts

ARajgor · 2024-04-27T06:45:17Z

I mean you write the knowledge_base.py file integrating with faiss. but where are you using those functions in the agent.py files. @Rawknee-69

darrassi1 · 2024-04-27T13:47:20Z

#485 I tested this PR intensively and it's working like magic .
I added this after commit knowledge
session.refresh(knowledge) # Reload the object from the session
To add_knowledge function
and change the logic of storing multiple results for same query
And concatenate them using join function

obliviousz · 2024-04-27T13:54:27Z

#485 I tested this PR intensively and it's working like magic . I added this after commit knowledge session.refresh(knowledge) # Reload the object from the session To add_knowledge function and change the logic of storing multiple results for same query And concatenate them using join function

What are the changes which you see if you can let us know?

darrassi1 · 2024-04-27T15:14:17Z

It's enhancing retrieval of memory from the local database , and my approche is combining
Context from knowledge base and results from web browser and feed it to a LLM for better compréhension .

Rawknee-69 added 3 commits April 24, 2024 17:51

updated code and file names and fixed bugs

38bcfc1

updated code and file names and fixed bugs

256751d

updated code and file names and fixed bugs

bd71e4e

Delete ui/package-lock.json

cfb59d8

obliviousz reviewed Apr 26, 2024

View reviewed changes

Rawknee-69 added 4 commits April 27, 2024 00:33

Update prompt.jinja2

29e61fb

Update prompt.jinja2

cdb6c36

Update agent.py

754e874

Merge branch 'main' into lates_update

3a341d0

Rawknee-69 requested a review from obliviousz April 26, 2024 19:23

obliviousz reviewed Apr 26, 2024

View reviewed changes

Rawknee-69 added 2 commits April 27, 2024 10:30

Update prompt.jinja2

927abbd

Updated some prompts

Update agent.py

4ef326a

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Fixed Bugs and Added some useful functions.... #491

Fixed Bugs and Added some useful functions.... #491

Rawknee-69 commented Apr 26, 2024

ARajgor commented Apr 26, 2024

ARajgor commented Apr 26, 2024

Rawknee-69 commented Apr 26, 2024

ARajgor commented Apr 26, 2024

obliviousz commented Apr 26, 2024

obliviousz left a comment

obliviousz Apr 26, 2024

obliviousz Apr 26, 2024

Rawknee-69 Apr 26, 2024

obliviousz Apr 26, 2024

Rawknee-69 Apr 26, 2024

obliviousz Apr 26, 2024

Rawknee-69 Apr 26, 2024

obliviousz Apr 26, 2024

amonpaike Apr 28, 2024

obliviousz Apr 26, 2024

Rawknee-69 Apr 26, 2024

obliviousz Apr 26, 2024

Rawknee-69 commented Apr 26, 2024

obliviousz commented Apr 26, 2024

Rawknee-69 commented Apr 26, 2024

Rawknee-69 commented Apr 26, 2024

obliviousz left a comment

obliviousz Apr 26, 2024

Rawknee-69 Apr 27, 2024

obliviousz Apr 26, 2024

Rawknee-69 Apr 27, 2024

obliviousz Apr 26, 2024

obliviousz Apr 26, 2024

ARajgor commented Apr 27, 2024 •

edited

Loading

darrassi1 commented Apr 27, 2024

obliviousz commented Apr 27, 2024

darrassi1 commented Apr 27, 2024

		@@ -1,31 +1,45 @@
		You are Devika, an AI Software Engineer. You have been talking to the user and this is your exchanges so far:
		You are an angelic AI Software Engineer, remarkable in intelligence and devoted to establishing a welcoming ambiance for users. Demonstrating perpetual politeness, grace, and acute awareness, you adeptly interpret and cater to user necessities. Taking into account earlier dialogues:


		You are now going to respond to the user's last message according to the specific request.
		YFormulate a response tailored to the user's last message, limiting superfluous communications.


		4. Accurately specify nested directory structures in the Markdown filenames. Organize the code structure appropriately.

		5. Include necessary files such as `requirements.txt`, `Cargo.toml`, or `readme.md`. These files are essential for successful execution.

Fixed Bugs and Added some useful functions.... #491

Are you sure you want to change the base?

Fixed Bugs and Added some useful functions.... #491

Conversation

Rawknee-69 commented Apr 26, 2024

ARajgor commented Apr 26, 2024

ARajgor commented Apr 26, 2024

Rawknee-69 commented Apr 26, 2024

ARajgor commented Apr 26, 2024

obliviousz commented Apr 26, 2024

obliviousz left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Rawknee-69 commented Apr 26, 2024

obliviousz commented Apr 26, 2024

Rawknee-69 commented Apr 26, 2024

Rawknee-69 commented Apr 26, 2024

obliviousz left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

ARajgor commented Apr 27, 2024 • edited Loading

darrassi1 commented Apr 27, 2024

obliviousz commented Apr 27, 2024

darrassi1 commented Apr 27, 2024

ARajgor commented Apr 27, 2024 •

edited

Loading