Pull Request Checklist

Note to first-time contributors: Please open a discussion post in Discussions and describe your changes before submitting a pull request.

Before submitting, make sure you've checked the following:

• Target branch: Please verify that the pull request targets the dev branch.
• Description: Provide a concise description of the changes made in this pull request.
• Changelog: Ensure a changelog entry following the format of Keep a Changelog is added at the bottom of the PR description.
• Documentation: Have you updated relevant documentation Open WebUI Docs, or other documentation sources?
• Dependencies: Are there any new dependencies? Have you updated the dependency versions in the documentation?
• Testing: Have you written and run sufficient tests for validating the changes?
• Code review: Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?
• Prefix: To cleary categorize this pull request, prefix the pull request title, using one of the following:
  • BREAKING CHANGE: Significant changes that may affect compatibility
  • build: Changes that affect the build system or external dependencies
  • ci: Changes to our continuous integration processes or workflows
  • chore: Refactor, cleanup, or other non-functional code changes
  • docs: Documentation update or addition
  • feat: Introduces a new feature or enhancement to the codebase
  • fix: Bug fix or error correction
  • i18n: Internationalization or localization changes
  • perf: Performance improvement
  • refactor: Code restructuring for better maintainability, readability, or scalability
  • style: Changes that do not affect the meaning of the code (white-space, formatting, missing semi-colons, etc.)
  • test: Adding missing tests or correcting existing tests
  • WIP: Work in progress, a temporary label for incomplete or ongoing work

Changelog Entry

Description

• Each document that is part of the chat is stored within the chat data and is part of each chat completion request
• With this change this overhead is reduced
• For queries with all documents, the collection names are extracted in the backend
• For queries with tags, the collection names are extracted in the backend
• No change for single file selection
• Benefit: Much faster request/response handling. Please see the screenshots of before and after.

Changed

• Reduce the request size and chat history storage size by removing the file checksums from the request

Additional Information

• Example with 10,000 documents
• Browser used: Google Chrome
• Environment: Localhost on MacOS

• Headers before the change. Request size is 88785. Also the UI was a bit lagging around with computing the payload
  

• Headers after the change. Request size is just 237. UI is very usable
  

• Payload before the change. Quite a long list of checksum in payload
  

• Payload after the change. Just the collection type is required
  

• Timing before the change. Processing the request took 35s
  

• Timing after the change. Processing the request took 8s. Side note: I did also a prove of concept by using just one single collection in ChromaDB and got the request down to under a second (after filling some caches, which is not possible storing it in different collections)
  

Script used to create the files

for i in {1..100000}
do
echo "Test file $i" > files/"test-$i.txt"
done