idchlife/rag-solution
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

evaluation for rag systems

Browse Source
This commit is contained in:
idchlife
2026-03-11 22:30:02 +03:00
parent 5721bad117
commit 6c953a327f
11 changed files with 31897 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
services/rag/langchain/PLANNING.md
View File

@@ -125,3 +125,7 @@ During this Phase we create asynchronous process of enrichment, utilizing async/
- [x] Make tabbed UI with top level tabs. First tab exists and is selected. Each tab should have copy of demo ui, meaning the chat window with ability to specify the api url
- [x] At the end of the tabs there should be button with plus sign, which will add new tab. Tabs to be called by numbers.
- [x] There should predefined 3 tabs opened. First one should have predefined api url "https://rag.langchain.overwatch.su/api/test-query", second "https://rag.llamaindex.overwatch.su/api/test-query", third "https://rag.haystack.overwatch.su/api/test-query"
# Phase 17 (creating json with list of documents that are supported for import)
- [x] Make cli command that takes json file with list of paths, filters them to only those that are being imported into the vector storage (can be checked in enrichment), then this file should be saved in the current folder as "yadisk_imported_paths.json" and in "yadisk_imported_paths.csv" file. In case of CSV - it should be formatted as csv of course.