feat: 🎸 source documents

[StanGirard]

are kept only once

Description

Please include a summary of the changes and the related issue. Please also include relevant motivation and context.

Checklist before requesting a review

Please delete options that are not relevant.

• My code follows the style guidelines of this project
• I have performed a self-review of my code
• I have commented hard-to-understand areas
• I have ideally added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• Any dependent changes have been merged

Screenshots (if appropriate):

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Updated (UTC)
docs	🔄 Building (Inspect)	Visit Preview	Nov 6, 2023 4:19pm
quivr-strapi	🔄 Building (Inspect)	Visit Preview	Nov 6, 2023 4:19pm
quivrapp	🔄 Building (Inspect)	Visit Preview	Nov 6, 2023 4:19pm

[github-actions]

Risk Level 2 - /home/runner/work/quivr/quivr/backend/llm/qa_base.py

The code changes in this pull request are relatively safe, with a risk score of 2. The changes involve deduplication of source documents, which is a good practice to avoid redundancy. However, there are a few areas that could be improved for better code quality and maintainability:

1. Error Handling: The code uses a broad Exception in several places for error handling. This is generally not a good practice as it can make debugging difficult. It's better to catch specific exceptions that you expect might be raised in the try block. For example, instead of:

   try:
       # some code
   except Exception as e:
       logger.error(\"Error during streaming tokens: %s\", e)

   You could use:

   try:
       # some code
   except (SpecificException1, SpecificException2) as e:
       logger.error(\"Error during streaming tokens: %s\", e)

2. Code Comments: The code could benefit from more comments explaining the purpose of the functions and the logic behind certain operations. This would make the code easier to understand and maintain.

3. Use of Magic Strings: The code contains magic strings (strings that are directly used in the code). It's better to define these strings as constants at the top of your file or in a separate configuration file. For example, instead of using 'Unnamed Document' directly in the code, define a constant like DEFAULT_DOCUMENT_NAME = 'Unnamed Document' and use this constant in your code.

---

🔍📝🪄

---

Powered by Code Review GPT