Spaces:
Running
Running
Commit History
-
reference
c224647
-
bunch of fixes to get it to work with a single docker cotainer. necessary evil for now.
e258771
-
rename to datasets
edf2758
-
refactor
ca2fff7
-
remove unused imports
3add6e8
-
add the embedding config file
5fa437b -
Complete SentenceTransformer integration
Introduced a way to mix and match embedding. Only marginal improvement with Sentence Embedding. todo: clean up the config mess. new var EMBEDDING introduced1bec7d8 -
add support for different embeddings
9c7a6f3
-
cors add
0760a61
-
change port
86271e0
-
can add different vector stores
12a040e
-
Introduce elastic search as backened store
Idea is to see if it works any better if we use elastic search based lookup. In specific if we use elastic's sparse encoderf2932e2
-
file name & llm verbose for debugging
6de2046
-
fetch relevance from vector store
may be in future have a relevance threshold. added Qdrant url to envc7e10e4
-
add documentation
sort ofcc3240a -
Changes to make search work better
Janar Ramalingam1. Move back to llm qa "stuff" mode as map_reduce is clueless 2. Created more metadata around documents. * allow create different collection spaces for db. /v1/admin/db -d "name={collection}" * within collection allow file names so that answers can be annotated {content: {answer :"I don't know", files:["a1","a2"]}} would mean openAI doesn't know about the question even though embedding returned two files. Lot more work to do92ef095
-
[first-draft] works
Janar Ramalingama0a3c87 -
first cut working version
Janar Ramalingam51a7f02