Feature 46/add model params #57
Merged
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
…ded for many functions
- This commit extends the `llm_utils` module to provide a function for listing all available OLLAMA models. - Improved the query service and added model list functionality.
- Improved the user interface by adding a select dropdown to filter models. - Addthe ability to send a question along with the model name when pressing enter.
- Implemented enhanced `pydantic` models for increased data modeling and clarity. - Implemented added status field and timestamps for Documents model objects. - The service file has been updated to incorporate document progress tracking and returns the validated DocumentPydantic model object for each document. - Improved document processing for better query response clarity and structure.
- Replaced error handling for document retrieval with a default empty list.
- The codebase now uses a consistent datetime for both `created_at` and `updated_at`.
- Implemented a document upload feature with a popup and modal.
- Added document management functionality to the main store.
- Functionality for clearing the user's authentication token has been added. - The code implements a mechanism to handle unauthorized access attempts and redirect the user to the login page.
- The code implements a new response template for user queries based on the provided context.
- Added support for accepting different file types for document upload.
- The code updates the vectorstore initialization and embedding function to improve efficiency and accuracy. - Implemented an improved prompt template for AI assistant responses.
- Implemented a monitoring system to check for changes in the uploaded documents and update their status.
- The code updates the `watchdog` to use a new vector database and update document status in the background.
- Simplified database configuration for improved consistency and reduced complexity.
- Changed database connection settings to use the 'aora.db' file for SQLite persistence.
- The code rewrites the logic to build and store vector embeddings of PDF documents into a persistent vector database.
- The code defines a method to save documents into the designated directory and hash them for persistence in the database.
- The code implements environment variables loading for the application, then sets up a context manager.
|
This pull request has to be reopened, as I see that there is an error with the requirements. The chormaDB does not support the Sqlite error. The installation of packages according to the readme fails and the backend cannot be started. This error was not noticed previously as the packages were not installed from scratch. @tmeftah Could you please take a look at this? |
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.
No description provided.