feat: 🎸 telegram

[StanGirard]

added loaders and compatibility

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 1, 2023 9:09pm
quivr-strapi	🔄 Building (Inspect)	Visit Preview	Nov 1, 2023 9:09pm
quivrapp	🔄 Building (Inspect)	Visit Preview	Nov 1, 2023 9:09pm

[github-actions]

Risk Level 2 - /home/runner/work/quivr/quivr/backend/loaders/telegram.py

The code is generally well-written and follows good practices. However, there is a potential issue with the concatenate_rows function. If the text_content is neither a string nor a list, it is set to an empty string. This could potentially lead to loss of data if text_content is of a different type. Consider adding an else clause to handle other types of text_content.

---

Risk Level 3 - /home/runner/work/quivr/quivr/backend/repository/brain/get_question_context_from_brain.py

The code has a potential bug in the loop where it removes documents after reaching a certain token limit. Modifying a list while iterating over it can lead to unexpected behavior. Consider creating a new list for the documents that should be kept instead of removing from the existing list. For example:

kept_documents = []
for doc in documents:
    tokens += len(doc.page_content) * 1.5
    if tokens > 3000:
        break
    kept_documents.append(doc)
documents = kept_documents

---

📝🐛🔄

---

Powered by Code Review GPT