Merge pull request #3582 from nickovs/tika-document-text

feat: Support Tika for document text extraction
This commit is contained in:
Timothy Jaeryang Baek
2024-07-01 17:07:40 -07:00
committed by GitHub
5 changed files with 181 additions and 41 deletions
+16
View File
@@ -885,6 +885,22 @@ WEBUI_SESSION_COOKIE_SECURE = os.environ.get(
if WEBUI_AUTH and WEBUI_SECRET_KEY == "":
raise ValueError(ERROR_MESSAGES.ENV_VAR_NOT_FOUND)
####################################
# RAG document text extraction
####################################
TEXT_EXTRACTION_ENGINE = PersistentConfig(
"TEXT_EXTRACTION_ENGINE",
"rag.text_extraction_engine",
os.environ.get("TEXT_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
####################################