Files
Charles Englebert 8e491074ac multi-embedding and chuncking (#25)
* (backend) add evaluate-search-engine command

I want to automize the search evaluation. This new command
computes performance metrics.

* (backend) improve evaluation

I add more data to my evaluations.

* 📝(backend) add changelog

add changelog and various fixes.

* (backend) add evaluation data from service-public.fr

I need better data with longer content to work on chuncking

* (backend) handle multi-embedding

I breack document content into peaces and embed each peace separatly.
Search is them based on the mest match.

* 📝(docs) add documentation

I add documentation about chunking

* 🚨(backend) fix things

thigs were broken. I fixed this.

* 📝(backend) documentation

I document the documentation of it

* 🚨(backend) fix rebase

the rebase has messed things up. I fixed those things.

* ♻️(backend) refactor language code handling and improve test cases

I fix things to fix things

* ♻️(backend) refactor

I am doing refactoooooooooooor
2025-12-08 15:34:42 +01:00

62 lines
2.1 KiB
Plaintext

# Django
DJANGO_ALLOWED_HOSTS=*
DJANGO_SECRET_KEY=ThisIsAnExampleKeyForDevPurposeOnly
DJANGO_SETTINGS_MODULE=find.settings
DJANGO_SUPERUSER_PASSWORD=admin
# Python
PYTHONPATH=/app
# find settings
# Backend url
FIND_BASE_URL="http://localhost:8072"
# Opensearch
OPENSEARCH_PASSWORD=find.PASS123
OPENSEARCH_USE_SSL=false
OPENSEARCH_INDEX_PREFIX=find
# OIDC
OIDC_OP_JWKS_ENDPOINT=http://nginx:8083/realms/impress/protocol/openid-connect/certs
OIDC_OP_AUTHORIZATION_ENDPOINT=http://nginx:8083/realms/impress/protocol/openid-connect/auth
OIDC_OP_TOKEN_ENDPOINT=http://nginx:8083/realms/impress/protocol/openid-connect/token
OIDC_OP_USER_ENDPOINT=http://nginx:8083/realms/impress/protocol/openid-connect/userinfo
OIDC_OP_INTROSPECTION_ENDPOINT=http://nginx:8083/realms/impress/protocol/openid-connect/token/introspect
# To run Find in development mode along other projects like docs/impress
# we should to use OIDC endpoints on a common keycloak realm. e.g :
# OIDC_OP_URL = http://nginx:8083/realms/impress
#
# This will cause a conflict with the 'iss' claim validation rule because the docs realm
# gives {'iss': 'http://localhost:8083/realms/impress'} so it must be the same
OIDC_OP_URL=http://localhost:8083/realms/impress
OIDC_RP_CLIENT_ID=find
OIDC_RP_CLIENT_SECRET=ThisIsAnExampleKeyForDevPurposeOnly
OIDC_RP_SIGN_ALGO=RS256
OIDC_RP_SCOPES="openid email"
OIDC_REDIRECT_ALLOWED_HOSTS=["http://localhost:8083", "http://localhost:3000"]
OIDC_AUTH_REQUEST_EXTRA_PARAMS={"acr_values": "eidas1"}
# OIDC Resource server
OIDC_DRF_AUTH_BACKEND="lasuite.oidc_login.backends.OIDCAuthenticationBackend"
OIDC_RS_SCOPES="openid"
OIDC_RS_CLIENT_ID=impress
OIDC_RS_CLIENT_SECRET=ThisIsAnExampleKeyForDevPurposeOnly
OIDC_RS_SIGN_ALGO=RS256
OIDC_RS_BACKEND_CLASS="core.authentication.FinderResourceServerBackend"
OIDC_RS_ENCRYPTION_KEY_TYPE="RSA"
# Hybrid Search settings
HYBRID_SEARCH_ENABLED=True
EMBEDDING_API_KEY=ThisIsAnExampleKeyForDevPurposeOnly
EMBEDDING_API_PATH=https://albert.api.etalab.gouv.fr/v1/embeddings
## Multi-embedding: chunk documents and embed each chunk
CHUNK_SIZE=512
CHUNK_OVERLAP=50