highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-09-29 21:37:21 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add answers to search (#2020)

Browse Source
This commit is contained in:
pablodanswer
2024-08-04 23:02:55 -07:00
committed by GitHub
parent 76b7792e69
commit 6d67d472cd
47 changed files with 806 additions and 445 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
deployment/docker_compose/env.multilingual.template
View File

@@ -24,7 +24,7 @@ NORMALIZE_EMBEDDINGS="True"
# Use LLM to determine if chunks are relevant to the query
# May not work well for languages that do not have much training data in the LLM training set
# If using a common language like Spanish, French, Chinese, etc. this can be kept turned on
DISABLE_LLM_CHUNK_FILTER="True"
DISABLE_LLM_DOC_RELEVANCE="True"
# The default reranking models are English first
# There are no great quality French/English reranking models currently so turning this off