feat: youtube loader language env var

This commit is contained in:
Timothy J. Baek
2024-05-08 10:51:29 -07:00
parent d3822f782c
commit 06cbe337de
31 changed files with 130 additions and 66 deletions

View File

@@ -92,6 +92,7 @@ from config import (
CHUNK_OVERLAP,
RAG_TEMPLATE,
ENABLE_RAG_LOCAL_WEB_FETCH,
YOUTUBE_LOADER_LANGUAGE,
)
from constants import ERROR_MESSAGES
@@ -124,7 +125,7 @@ app.state.OPENAI_API_KEY = RAG_OPENAI_API_KEY
app.state.PDF_EXTRACT_IMAGES = PDF_EXTRACT_IMAGES
app.state.YOUTUBE_LOADER_LANGUAGE = ["en"]
app.state.YOUTUBE_LOADER_LANGUAGE = YOUTUBE_LOADER_LANGUAGE
app.state.YOUTUBE_LOADER_TRANSLATION = None

View File

@@ -493,13 +493,6 @@ RAG_RERANKING_MODEL_TRUST_REMOTE_CODE = (
os.environ.get("RAG_RERANKING_MODEL_TRUST_REMOTE_CODE", "").lower() == "true"
)
# 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")
if USE_CUDA.lower() == "true":
DEVICE_TYPE = "cuda"
else:
DEVICE_TYPE = "cpu"
if CHROMA_HTTP_HOST != "":
CHROMA_CLIENT = chromadb.HttpClient(
@@ -519,6 +512,16 @@ else:
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")
if USE_CUDA.lower() == "true":
DEVICE_TYPE = "cuda"
else:
DEVICE_TYPE = "cpu"
CHUNK_SIZE = int(os.environ.get("CHUNK_SIZE", "1500"))
CHUNK_OVERLAP = int(os.environ.get("CHUNK_OVERLAP", "100"))
@@ -545,6 +548,8 @@ ENABLE_RAG_LOCAL_WEB_FETCH = (
os.getenv("ENABLE_RAG_LOCAL_WEB_FETCH", "False").lower() == "true"
)
YOUTUBE_LOADER_LANGUAGE = os.getenv("YOUTUBE_LOADER_LANGUAGE", "en").split(",")
####################################
# Transcribe
####################################