Feat/llm responses #376
Open
Feat/llm responses #376
+2,720
−123
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
… type annotations
…alog_flow_framework into feat/llm_responses
RLKRo
reviewed
Aug 7, 2024
|
I got an idea for more complex prompts: we can allow passing responses as prompts instead of just strings. And then it'd be possible to incorporate slots into a prompt: model = LLM_API(prompt=rsp.slots.FilledTemplate("You are an experienced barista in a local coffeshop."
"Answer your customers questions about coffee and barista work.\n"
"Customer data:\nAge {person.age}\nGender: {person.gender}\nFavorite drink: {person.habits.drink}"
)) |
… "prompt" to "message" in Prompt class
RLKRo
reviewed
Feb 6, 2025
RLKRo
reviewed
Feb 7, 2025
Comment on lines
+6
to
+11
| class PositionConfig(BaseModel): | ||
| system_prompt: float = 0 | ||
| history: float = 1 | ||
| misc_prompt: float = 2 | ||
| call_prompt: float = 3 | ||
| last_request: float = 4 |
There was a problem hiding this comment.
Allow None positions to disable certain prompts.
| call_prompt_message = await message_to_langchain(call_prompt_text, ctx, source="human") | ||
| prompts.append(([call_prompt_message], call_prompt.position or position_config.call_prompt)) | ||
|
|
||
| prompts.append(([await message_to_langchain(ctx.last_request, ctx, source="human")], position_config.last_request)) |
There was a problem hiding this comment.
Remove last turn from history; add last turn here instead of last request.
RLKRo
reviewed
Feb 10, 2025
|
|
||
| pattern: str | ||
| """ | ||
| pattern that will be searched in model_result. |
Comment on lines
+61
to
+62
| :param str target_token: token to check (e.g. `"TRUE"`) | ||
| :param float threshold: threshold to bypass. by default `-0.5` |
There was a problem hiding this comment.
Move these out of the class docstring as well.
chatsky/llm/llm_api.py
Outdated
| result.annotations = {"__generated_by_model__": self.name} | ||
| return result | ||
|
|
||
| async def condition(self, prompt: str, method: BaseMethod, return_schema=None): |
| return self.__dict_to_extracted_slots(nested_result) | ||
|
|
||
| # Convert nested dict to ExtractedGroupSlot structure | ||
| def __dict_to_extracted_slots(self, d): |
There was a problem hiding this comment.
Make the name start with a single underscore.
chatsky/llm/filters.py
Outdated
| raise NotImplemented | ||
|
|
||
| def __call__(self, ctx, request, response, model_name): | ||
| return self.call(ctx, request, model_name) + self.call(ctx, response, model_name) |
There was a problem hiding this comment.
Group test cases in classes.
E.g.
async def test_llm_slot(pipeline, context):
..
async def test_llm_group_slot(pipeline, context):
..====>
class TestSlots:
async def test_llm_slot(self, pipeline, context):
..
async def test_llm_group_slot(self, pipeline, context):
..
Comment on lines
+74
to
+75
| # misc_prompt is the default position for misc prompts | ||
| # Misc prompts may override it and be ordered in a different way |
There was a problem hiding this comment.
This needs clarification. And needs to be clearly different from the previous sentence (e.g. separated with a period).
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Added functionality for calling LLMs via langchain API for utilizing them in responses and conditions.
Checklist
List here tasks to complete in order to mark this PR as ready for review.
To Consider