This commit is contained in:
Timothy J. Baek 2024-09-10 01:34:27 +01:00
parent 1023ff8454
commit eb0e683b47

View File

@ -923,24 +923,9 @@ TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE = PersistentConfig(
####################################
# RAG document content extraction
# Vector Database
####################################
CONTENT_EXTRACTION_ENGINE = PersistentConfig(
"CONTENT_EXTRACTION_ENGINE",
"rag.CONTENT_EXTRACTION_ENGINE",
os.environ.get("CONTENT_EXTRACTION_ENGINE", "").lower(),
)
TIKA_SERVER_URL = PersistentConfig(
"TIKA_SERVER_URL",
"rag.tika_server_url",
os.getenv("TIKA_SERVER_URL", "http://tika:9998"), # Default for sidecar deployment
)
####################################
# RAG
####################################
CHROMA_DATA_PATH = f"{DATA_DIR}/vector_db"
CHROMA_TENANT = os.environ.get("CHROMA_TENANT", chromadb.DEFAULT_TENANT)
@ -958,6 +943,43 @@ else:
CHROMA_HTTP_SSL = os.environ.get("CHROMA_HTTP_SSL", "false").lower() == "true"
# this uses the model defined in the Dockerfile ENV variable. If you dont use docker or docker based deployments such as k8s, the default embedding model will be used (sentence-transformers/all-MiniLM-L6-v2)
if CHROMA_HTTP_HOST != "":
CHROMA_CLIENT = chromadb.HttpClient(
host=CHROMA_HTTP_HOST,
port=CHROMA_HTTP_PORT,
headers=CHROMA_HTTP_HEADERS,
ssl=CHROMA_HTTP_SSL,
tenant=CHROMA_TENANT,
database=CHROMA_DATABASE,
settings=Settings(allow_reset=True, anonymized_telemetry=False),
)
else:
CHROMA_CLIENT = chromadb.PersistentClient(
path=CHROMA_DATA_PATH,
settings=Settings(allow_reset=True, anonymized_telemetry=False),
tenant=CHROMA_TENANT,
database=CHROMA_DATABASE,
)
####################################
# RAG
####################################
# RAG Content Extraction
CONTENT_EXTRACTION_ENGINE = PersistentConfig(
"CONTENT_EXTRACTION_ENGINE",
"rag.CONTENT_EXTRACTION_ENGINE",
os.environ.get("CONTENT_EXTRACTION_ENGINE", "").lower(),
)
TIKA_SERVER_URL = PersistentConfig(
"TIKA_SERVER_URL",
"rag.tika_server_url",
os.getenv("TIKA_SERVER_URL", "http://tika:9998"), # Default for sidecar deployment
)
RAG_TOP_K = PersistentConfig(
"RAG_TOP_K", "rag.top_k", int(os.environ.get("RAG_TOP_K", "5"))
)
@ -1049,25 +1071,6 @@ RAG_RERANKING_MODEL_TRUST_REMOTE_CODE = (
)
if CHROMA_HTTP_HOST != "":
CHROMA_CLIENT = chromadb.HttpClient(
host=CHROMA_HTTP_HOST,
port=CHROMA_HTTP_PORT,
headers=CHROMA_HTTP_HEADERS,
ssl=CHROMA_HTTP_SSL,
tenant=CHROMA_TENANT,
database=CHROMA_DATABASE,
settings=Settings(allow_reset=True, anonymized_telemetry=False),
)
else:
CHROMA_CLIENT = chromadb.PersistentClient(
path=CHROMA_DATA_PATH,
settings=Settings(allow_reset=True, anonymized_telemetry=False),
tenant=CHROMA_TENANT,
database=CHROMA_DATABASE,
)
# device type embedding models - "cpu" (default), "cuda" (nvidia gpu required) or "mps" (apple silicon) - choosing this right can lead to better performance
USE_CUDA = os.environ.get("USE_CUDA_DOCKER", "false")