Dep update #1486
Closed
Dep update #1486
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
- Changed from Toga to FastAPI. - Removed separate Toga files and integrated FastAPI for backend support. - Introduced settings and input handling for a flexible setup. - Enhanced modularity by separating concerns into different components. - Improved error handling for invalid input types and missing configurations. - Added functions for LLM choice and cost calculation. - Updated test cases to reflect new functionality.
Fixed the final report not being sent to the frontend. This commit introduces enhancements to the model and provider parsing logic, making the system more flexible and robust in handling various forms of input. It also refactors the 'GenericLLMProvider' class to use detailed model information, such as model IDs and provider names, for more specific tracking and error handling. Changes: - Implemented 'ModelFactory' to handle model instantiation - 'ModelFactory' extracts the model ID and provider from a string for more precise initialization. - Refactored 'GenericLLMProvider' to track models by ID and provider in a dictionary, rather than just storing the model instances. - Added internal methods in 'GenericLLMProvider' for adding model information, including support for LiteLLM specifications. - Implemented filtering of failed models, preventing repeat attempts with models that have consistently failed. - Integrated cost callback updates to accurately track operational costs. - Enhanced error handling to raise exceptions when no suitable model is found or all models fail. - Added a fallback mechanism using the 'json_repair' library to fix invalid JSON responses from the LLM. - Standardized log messages across the class, improving the consistency of logging output. - Implemented helper function 'get_litellm_models' to handle the use of LiteLLM models inside the backend (allows falling back to a static JSON file if an API key is not given, useful for free models)
revert `master` to last known rock-hard stable.
… len() - Fixed typo in agent.py where 'roll' (numpy function) was assigned instead of 'role' parameter - Added proper type checking and string conversion for agent_role_prompt in report_generation.py - Ensures agent_role_prompt is always a string before calling len() function
Updates the requirements on [unstructured](https://github.com/Unstructured-IO/unstructured) to permit the latest version. - [Release notes](https://github.com/Unstructured-IO/unstructured/releases) - [Changelog](https://github.com/Unstructured-IO/unstructured/blob/main/CHANGELOG.md) - [Commits](Unstructured-IO/unstructured@0.13.0...0.18.1) --- updated-dependencies: - dependency-name: unstructured dependency-version: 0.18.1 dependency-type: direct:production ... Signed-off-by: dependabot[bot] <[email protected]>
Bumps python from 3.13.3-slim-bookworm to 3.13.5-slim-bookworm. --- updated-dependencies: - dependency-name: python dependency-version: 3.13.5-slim-bookworm dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]>
remove discord bot step
…hon-3.13.5-slim-bookworm
….29-and-lt-0.5
…0.13-and-lt-0.19
fix non-imported type
…alysis options in VSCode configuration
…e images and restrict openai version
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.
this pr is a mistake, please ignore