Add custom OpenAI endpoint support + code refactoring #8
Conversation
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
1. Added support for openAI compatible inference providers 2. Abstracted agent steps from implementation, users can now choose which client/ sdk to use for each step e.g. I can choose to use OpenAI or gemini for all 4 steps: followup, research_plan, query_generation, report_generation 3. Reworked mechanism for saving final report
Feat: seperated implementations of steps by llm sdk Feat: Changed mechanism for saving reports (is now configured by the config file and supports pattern based formatting)
Feat: Added function for json response parsing (for inference providers that do not support the response format argument in openai chat completions)
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Outdated suggestions cannot be applied.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.
What I did
OPENAI_BASE_URLenv varOther improvements
{date}_{time}_{n}.mdNote: I couldn't test with official OpenAI endpoints since they're banned in my region, but the code should work with any OpenAI-compatible API.