Implement direct LLM integration with Groq and Gemini providers#2
Open
Dev0907 wants to merge 2 commits into
Open
Implement direct LLM integration with Groq and Gemini providers#2Dev0907 wants to merge 2 commits into
Dev0907 wants to merge 2 commits into
Conversation
- Added `direct_llm.py` for handling chat completions with Groq and Gemini APIs. - Introduced error handling for authentication and provider errors. - Implemented model selection logic with fallbacks for Groq. - Created utility functions for parsing JSON responses and managing API requests. - Developed `llm_config.py` to manage LLM provider configurations and model normalization. - Added `prompting.py` for safe variable substitution in prompt templates and prompt size reduction. Need to check some final working there are issues due to model limit.
smitngandhi
reviewed
Feb 5, 2026
smitngandhi
left a comment
smitngandhi
left a comment
Owner
There was a problem hiding this comment.
AI enhance feature is really useful but please maintain the system design i created i mentioned inside main.py
Thanks
| except Exception as e: | ||
| raise _llm_error_to_http(e) | ||
|
|
||
| external_interfaces_section = clean_interface_diagrams(external_interfaces_section) |
Owner
There was a problem hiding this comment.
main idea is to run first four agents parallely based on user_inputs and other two after that because it is based on the first output here all are running sequential which will not follow the design properly
| <script src="{{ url_for('static', path='home.js') }}"></script> | ||
| </body> | ||
| </html> No newline at end of file | ||
| </html> |
Owner
There was a problem hiding this comment.
This one here is a really a good idea
| if not v or not v.strip(): | ||
| raise ValueError("content cannot be empty") | ||
| return v.strip() | ||
|
|
| return (raw or "").strip() | ||
|
|
||
|
|
||
| @app.post("/enhance_section", response_model=SectionEnhancementResponse) |
Owner
There was a problem hiding this comment.
no mention of the section_enchancer_agent
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
direct_llm.pyfor handling chat completions with Groq and Gemini APIs.llm_config.pyto manage LLM provider configurations and model normalization.prompting.pyfor safe variable substitution in prompt templates and prompt size reduction.