mirror of
https://github.com/MODSetter/SurfSense.git
synced 2025-09-10 14:28:57 +00:00
Fixed all ruff lint and formatting errors
This commit is contained in:
Utkarsh-Patel-13
parent
0a03c42cc5
commit
d359a59f6d
85 changed files with 5520 additions and 3870 deletions
|
|
@ -1,46 +1,49 @@
|
|||
from typing import Optional, List
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
import logging
|
||||
from urllib.parse import parse_qs, urlparse
|
||||
|
||||
import aiohttp
|
||||
import validators
|
||||
from langchain_community.document_loaders import AsyncChromiumLoader, FireCrawlLoader
|
||||
from langchain_community.document_transformers import MarkdownifyTransformer
|
||||
from langchain_core.documents import Document as LangChainDocument
|
||||
from sqlalchemy.exc import SQLAlchemyError
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
from sqlalchemy.future import select
|
||||
from app.db import Document, DocumentType, Chunk
|
||||
from app.schemas import ExtensionDocumentContent
|
||||
from youtube_transcript_api import YouTubeTranscriptApi
|
||||
|
||||
from app.config import config
|
||||
from app.db import Chunk, Document, DocumentType
|
||||
from app.prompts import SUMMARY_PROMPT_TEMPLATE
|
||||
from app.utils.document_converters import convert_document_to_markdown, generate_content_hash
|
||||
from app.schemas import ExtensionDocumentContent
|
||||
from app.services.llm_service import get_user_long_context_llm
|
||||
from app.services.task_logging_service import TaskLoggingService
|
||||
from langchain_core.documents import Document as LangChainDocument
|
||||
from langchain_community.document_loaders import FireCrawlLoader, AsyncChromiumLoader
|
||||
from langchain_community.document_transformers import MarkdownifyTransformer
|
||||
import validators
|
||||
from youtube_transcript_api import YouTubeTranscriptApi
|
||||
from urllib.parse import urlparse, parse_qs
|
||||
import aiohttp
|
||||
import logging
|
||||
from app.utils.document_converters import (
|
||||
convert_document_to_markdown,
|
||||
generate_content_hash,
|
||||
)
|
||||
|
||||
md = MarkdownifyTransformer()
|
||||
|
||||
|
||||
async def add_crawled_url_document(
|
||||
session: AsyncSession, url: str, search_space_id: int, user_id: str
|
||||
) -> Optional[Document]:
|
||||
) -> Document | None:
|
||||
task_logger = TaskLoggingService(session, search_space_id)
|
||||
|
||||
|
||||
# Log task start
|
||||
log_entry = await task_logger.log_task_start(
|
||||
task_name="crawl_url_document",
|
||||
source="background_task",
|
||||
message=f"Starting URL crawling process for: {url}",
|
||||
metadata={"url": url, "user_id": str(user_id)}
|
||||
metadata={"url": url, "user_id": str(user_id)},
|
||||
)
|
||||
|
||||
|
||||
try:
|
||||
# URL validation step
|
||||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Validating URL: {url}",
|
||||
{"stage": "validation"}
|
||||
log_entry, f"Validating URL: {url}", {"stage": "validation"}
|
||||
)
|
||||
|
||||
|
||||
if not validators.url(url):
|
||||
raise ValueError(f"Url {url} is not a valid URL address")
|
||||
|
||||
|
|
@ -48,7 +51,10 @@ async def add_crawled_url_document(
|
|||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Setting up crawler for URL: {url}",
|
||||
{"stage": "crawler_setup", "firecrawl_available": bool(config.FIRECRAWL_API_KEY)}
|
||||
{
|
||||
"stage": "crawler_setup",
|
||||
"firecrawl_available": bool(config.FIRECRAWL_API_KEY),
|
||||
},
|
||||
)
|
||||
|
||||
if config.FIRECRAWL_API_KEY:
|
||||
|
|
@ -68,21 +74,21 @@ async def add_crawled_url_document(
|
|||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Crawling URL content: {url}",
|
||||
{"stage": "crawling", "crawler_type": type(crawl_loader).__name__}
|
||||
{"stage": "crawling", "crawler_type": type(crawl_loader).__name__},
|
||||
)
|
||||
|
||||
url_crawled = await crawl_loader.aload()
|
||||
|
||||
if type(crawl_loader) == FireCrawlLoader:
|
||||
if isinstance(crawl_loader, FireCrawlLoader):
|
||||
content_in_markdown = url_crawled[0].page_content
|
||||
elif type(crawl_loader) == AsyncChromiumLoader:
|
||||
elif isinstance(crawl_loader, AsyncChromiumLoader):
|
||||
content_in_markdown = md.transform_documents(url_crawled)[0].page_content
|
||||
|
||||
# Format document
|
||||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Processing crawled content from: {url}",
|
||||
{"stage": "content_processing", "content_length": len(content_in_markdown)}
|
||||
{"stage": "content_processing", "content_length": len(content_in_markdown)},
|
||||
)
|
||||
|
||||
# Format document metadata in a more maintainable way
|
||||
|
|
@ -117,7 +123,7 @@ async def add_crawled_url_document(
|
|||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Checking for duplicate content: {url}",
|
||||
{"stage": "duplicate_check", "content_hash": content_hash}
|
||||
{"stage": "duplicate_check", "content_hash": content_hash},
|
||||
)
|
||||
|
||||
# Check if document with this content hash already exists
|
||||
|
|
@ -125,21 +131,26 @@ async def add_crawled_url_document(
|
|||
select(Document).where(Document.content_hash == content_hash)
|
||||
)
|
||||
existing_document = existing_doc_result.scalars().first()
|
||||
|
||||
|
||||
if existing_document:
|
||||
await task_logger.log_task_success(
|
||||
log_entry,
|
||||
f"Document already exists for URL: {url}",
|
||||
{"duplicate_detected": True, "existing_document_id": existing_document.id}
|
||||
{
|
||||
"duplicate_detected": True,
|
||||
"existing_document_id": existing_document.id,
|
||||
},
|
||||
)
|
||||
logging.info(
|
||||
f"Document with content hash {content_hash} already exists. Skipping processing."
|
||||
)
|
||||
logging.info(f"Document with content hash {content_hash} already exists. Skipping processing.")
|
||||
return existing_document
|
||||
|
||||
# Get LLM for summary generation
|
||||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Preparing for summary generation: {url}",
|
||||
{"stage": "llm_setup"}
|
||||
{"stage": "llm_setup"},
|
||||
)
|
||||
|
||||
# Get user's long context LLM
|
||||
|
|
@ -151,7 +162,7 @@ async def add_crawled_url_document(
|
|||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Generating summary for URL content: {url}",
|
||||
{"stage": "summary_generation"}
|
||||
{"stage": "summary_generation"},
|
||||
)
|
||||
|
||||
summary_chain = SUMMARY_PROMPT_TEMPLATE | user_llm
|
||||
|
|
@ -165,7 +176,7 @@ async def add_crawled_url_document(
|
|||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Processing content chunks for URL: {url}",
|
||||
{"stage": "chunk_processing"}
|
||||
{"stage": "chunk_processing"},
|
||||
)
|
||||
|
||||
chunks = [
|
||||
|
|
@ -180,13 +191,13 @@ async def add_crawled_url_document(
|
|||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Creating document in database for URL: {url}",
|
||||
{"stage": "document_creation", "chunks_count": len(chunks)}
|
||||
{"stage": "document_creation", "chunks_count": len(chunks)},
|
||||
)
|
||||
|
||||
document = Document(
|
||||
search_space_id=search_space_id,
|
||||
title=url_crawled[0].metadata["title"]
|
||||
if type(crawl_loader) == FireCrawlLoader
|
||||
if isinstance(crawl_loader, FireCrawlLoader)
|
||||
else url_crawled[0].metadata["source"],
|
||||
document_type=DocumentType.CRAWLED_URL,
|
||||
document_metadata=url_crawled[0].metadata,
|
||||
|
|
@ -209,8 +220,8 @@ async def add_crawled_url_document(
|
|||
"title": document.title,
|
||||
"content_hash": content_hash,
|
||||
"chunks_count": len(chunks),
|
||||
"summary_length": len(summary_content)
|
||||
}
|
||||
"summary_length": len(summary_content),
|
||||
},
|
||||
)
|
||||
|
||||
return document
|
||||
|
|
@ -221,7 +232,7 @@ async def add_crawled_url_document(
|
|||
log_entry,
|
||||
f"Database error while processing URL: {url}",
|
||||
str(db_error),
|
||||
{"error_type": "SQLAlchemyError"}
|
||||
{"error_type": "SQLAlchemyError"},
|
||||
)
|
||||
raise db_error
|
||||
except Exception as e:
|
||||
|
|
@ -230,14 +241,17 @@ async def add_crawled_url_document(
|
|||
log_entry,
|
||||
f"Failed to crawl URL: {url}",
|
||||
str(e),
|
||||
{"error_type": type(e).__name__}
|
||||
{"error_type": type(e).__name__},
|
||||
)
|
||||
raise RuntimeError(f"Failed to crawl URL: {str(e)}")
|
||||
raise RuntimeError(f"Failed to crawl URL: {e!s}") from e
|
||||
|
||||
|
||||
async def add_extension_received_document(
|
||||
session: AsyncSession, content: ExtensionDocumentContent, search_space_id: int, user_id: str
|
||||
) -> Optional[Document]:
|
||||
session: AsyncSession,
|
||||
content: ExtensionDocumentContent,
|
||||
search_space_id: int,
|
||||
user_id: str,
|
||||
) -> Document | None:
|
||||
"""
|
||||
Process and store document content received from the SurfSense Extension.
|
||||
|
||||
|
|
@ -250,7 +264,7 @@ async def add_extension_received_document(
|
|||
Document object if successful, None if failed
|
||||
"""
|
||||
task_logger = TaskLoggingService(session, search_space_id)
|
||||
|
||||
|
||||
# Log task start
|
||||
log_entry = await task_logger.log_task_start(
|
||||
task_name="extension_document",
|
||||
|
|
@ -259,10 +273,10 @@ async def add_extension_received_document(
|
|||
metadata={
|
||||
"url": content.metadata.VisitedWebPageURL,
|
||||
"title": content.metadata.VisitedWebPageTitle,
|
||||
"user_id": str(user_id)
|
||||
}
|
||||
"user_id": str(user_id),
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
try:
|
||||
# Format document metadata in a more maintainable way
|
||||
metadata_sections = [
|
||||
|
|
@ -301,14 +315,19 @@ async def add_extension_received_document(
|
|||
select(Document).where(Document.content_hash == content_hash)
|
||||
)
|
||||
existing_document = existing_doc_result.scalars().first()
|
||||
|
||||
|
||||
if existing_document:
|
||||
await task_logger.log_task_success(
|
||||
log_entry,
|
||||
f"Extension document already exists: {content.metadata.VisitedWebPageTitle}",
|
||||
{"duplicate_detected": True, "existing_document_id": existing_document.id}
|
||||
{
|
||||
"duplicate_detected": True,
|
||||
"existing_document_id": existing_document.id,
|
||||
},
|
||||
)
|
||||
logging.info(
|
||||
f"Document with content hash {content_hash} already exists. Skipping processing."
|
||||
)
|
||||
logging.info(f"Document with content hash {content_hash} already exists. Skipping processing.")
|
||||
return existing_document
|
||||
|
||||
# Get user's long context LLM
|
||||
|
|
@ -356,8 +375,8 @@ async def add_extension_received_document(
|
|||
{
|
||||
"document_id": document.id,
|
||||
"content_hash": content_hash,
|
||||
"url": content.metadata.VisitedWebPageURL
|
||||
}
|
||||
"url": content.metadata.VisitedWebPageURL,
|
||||
},
|
||||
)
|
||||
|
||||
return document
|
||||
|
|
@ -368,7 +387,7 @@ async def add_extension_received_document(
|
|||
log_entry,
|
||||
f"Database error processing extension document: {content.metadata.VisitedWebPageTitle}",
|
||||
str(db_error),
|
||||
{"error_type": "SQLAlchemyError"}
|
||||
{"error_type": "SQLAlchemyError"},
|
||||
)
|
||||
raise db_error
|
||||
except Exception as e:
|
||||
|
|
@ -377,24 +396,32 @@ async def add_extension_received_document(
|
|||
log_entry,
|
||||
f"Failed to process extension document: {content.metadata.VisitedWebPageTitle}",
|
||||
str(e),
|
||||
{"error_type": type(e).__name__}
|
||||
{"error_type": type(e).__name__},
|
||||
)
|
||||
raise RuntimeError(f"Failed to process extension document: {str(e)}")
|
||||
raise RuntimeError(f"Failed to process extension document: {e!s}") from e
|
||||
|
||||
|
||||
async def add_received_markdown_file_document(
|
||||
session: AsyncSession, file_name: str, file_in_markdown: str, search_space_id: int, user_id: str
|
||||
) -> Optional[Document]:
|
||||
session: AsyncSession,
|
||||
file_name: str,
|
||||
file_in_markdown: str,
|
||||
search_space_id: int,
|
||||
user_id: str,
|
||||
) -> Document | None:
|
||||
task_logger = TaskLoggingService(session, search_space_id)
|
||||
|
||||
|
||||
# Log task start
|
||||
log_entry = await task_logger.log_task_start(
|
||||
task_name="markdown_file_document",
|
||||
source="background_task",
|
||||
message=f"Processing markdown file: {file_name}",
|
||||
metadata={"filename": file_name, "user_id": str(user_id), "content_length": len(file_in_markdown)}
|
||||
metadata={
|
||||
"filename": file_name,
|
||||
"user_id": str(user_id),
|
||||
"content_length": len(file_in_markdown),
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
try:
|
||||
content_hash = generate_content_hash(file_in_markdown, search_space_id)
|
||||
|
||||
|
|
@ -403,14 +430,19 @@ async def add_received_markdown_file_document(
|
|||
select(Document).where(Document.content_hash == content_hash)
|
||||
)
|
||||
existing_document = existing_doc_result.scalars().first()
|
||||
|
||||
|
||||
if existing_document:
|
||||
await task_logger.log_task_success(
|
||||
log_entry,
|
||||
f"Markdown file document already exists: {file_name}",
|
||||
{"duplicate_detected": True, "existing_document_id": existing_document.id}
|
||||
{
|
||||
"duplicate_detected": True,
|
||||
"existing_document_id": existing_document.id,
|
||||
},
|
||||
)
|
||||
logging.info(
|
||||
f"Document with content hash {content_hash} already exists. Skipping processing."
|
||||
)
|
||||
logging.info(f"Document with content hash {content_hash} already exists. Skipping processing.")
|
||||
return existing_document
|
||||
|
||||
# Get user's long context LLM
|
||||
|
|
@ -459,8 +491,8 @@ async def add_received_markdown_file_document(
|
|||
"document_id": document.id,
|
||||
"content_hash": content_hash,
|
||||
"chunks_count": len(chunks),
|
||||
"summary_length": len(summary_content)
|
||||
}
|
||||
"summary_length": len(summary_content),
|
||||
},
|
||||
)
|
||||
|
||||
return document
|
||||
|
|
@ -470,7 +502,7 @@ async def add_received_markdown_file_document(
|
|||
log_entry,
|
||||
f"Database error processing markdown file: {file_name}",
|
||||
str(db_error),
|
||||
{"error_type": "SQLAlchemyError"}
|
||||
{"error_type": "SQLAlchemyError"},
|
||||
)
|
||||
raise db_error
|
||||
except Exception as e:
|
||||
|
|
@ -479,18 +511,18 @@ async def add_received_markdown_file_document(
|
|||
log_entry,
|
||||
f"Failed to process markdown file: {file_name}",
|
||||
str(e),
|
||||
{"error_type": type(e).__name__}
|
||||
{"error_type": type(e).__name__},
|
||||
)
|
||||
raise RuntimeError(f"Failed to process file document: {str(e)}")
|
||||
raise RuntimeError(f"Failed to process file document: {e!s}") from e
|
||||
|
||||
|
||||
async def add_received_file_document_using_unstructured(
|
||||
session: AsyncSession,
|
||||
file_name: str,
|
||||
unstructured_processed_elements: List[LangChainDocument],
|
||||
unstructured_processed_elements: list[LangChainDocument],
|
||||
search_space_id: int,
|
||||
user_id: str,
|
||||
) -> Optional[Document]:
|
||||
) -> Document | None:
|
||||
try:
|
||||
file_in_markdown = await convert_document_to_markdown(
|
||||
unstructured_processed_elements
|
||||
|
|
@ -503,9 +535,11 @@ async def add_received_file_document_using_unstructured(
|
|||
select(Document).where(Document.content_hash == content_hash)
|
||||
)
|
||||
existing_document = existing_doc_result.scalars().first()
|
||||
|
||||
|
||||
if existing_document:
|
||||
logging.info(f"Document with content hash {content_hash} already exists. Skipping processing.")
|
||||
logging.info(
|
||||
f"Document with content hash {content_hash} already exists. Skipping processing."
|
||||
)
|
||||
return existing_document
|
||||
|
||||
# TODO: Check if file_markdown exceeds token limit of embedding model
|
||||
|
|
@ -555,7 +589,7 @@ async def add_received_file_document_using_unstructured(
|
|||
raise db_error
|
||||
except Exception as e:
|
||||
await session.rollback()
|
||||
raise RuntimeError(f"Failed to process file document: {str(e)}")
|
||||
raise RuntimeError(f"Failed to process file document: {e!s}") from e
|
||||
|
||||
|
||||
async def add_received_file_document_using_llamacloud(
|
||||
|
|
@ -564,7 +598,7 @@ async def add_received_file_document_using_llamacloud(
|
|||
llamacloud_markdown_document: str,
|
||||
search_space_id: int,
|
||||
user_id: str,
|
||||
) -> Optional[Document]:
|
||||
) -> Document | None:
|
||||
"""
|
||||
Process and store document content parsed by LlamaCloud.
|
||||
|
||||
|
|
@ -588,9 +622,11 @@ async def add_received_file_document_using_llamacloud(
|
|||
select(Document).where(Document.content_hash == content_hash)
|
||||
)
|
||||
existing_document = existing_doc_result.scalars().first()
|
||||
|
||||
|
||||
if existing_document:
|
||||
logging.info(f"Document with content hash {content_hash} already exists. Skipping processing.")
|
||||
logging.info(
|
||||
f"Document with content hash {content_hash} already exists. Skipping processing."
|
||||
)
|
||||
return existing_document
|
||||
|
||||
# Get user's long context LLM
|
||||
|
|
@ -638,7 +674,9 @@ async def add_received_file_document_using_llamacloud(
|
|||
raise db_error
|
||||
except Exception as e:
|
||||
await session.rollback()
|
||||
raise RuntimeError(f"Failed to process file document using LlamaCloud: {str(e)}")
|
||||
raise RuntimeError(
|
||||
f"Failed to process file document using LlamaCloud: {e!s}"
|
||||
) from e
|
||||
|
||||
|
||||
async def add_received_file_document_using_docling(
|
||||
|
|
@ -647,7 +685,7 @@ async def add_received_file_document_using_docling(
|
|||
docling_markdown_document: str,
|
||||
search_space_id: int,
|
||||
user_id: str,
|
||||
) -> Optional[Document]:
|
||||
) -> Document | None:
|
||||
"""
|
||||
Process and store document content parsed by Docling.
|
||||
|
||||
|
|
@ -671,9 +709,11 @@ async def add_received_file_document_using_docling(
|
|||
select(Document).where(Document.content_hash == content_hash)
|
||||
)
|
||||
existing_document = existing_doc_result.scalars().first()
|
||||
|
||||
|
||||
if existing_document:
|
||||
logging.info(f"Document with content hash {content_hash} already exists. Skipping processing.")
|
||||
logging.info(
|
||||
f"Document with content hash {content_hash} already exists. Skipping processing."
|
||||
)
|
||||
return existing_document
|
||||
|
||||
# Get user's long context LLM
|
||||
|
|
@ -683,12 +723,11 @@ async def add_received_file_document_using_docling(
|
|||
|
||||
# Generate summary using chunked processing for large documents
|
||||
from app.services.docling_service import create_docling_service
|
||||
|
||||
docling_service = create_docling_service()
|
||||
|
||||
|
||||
summary_content = await docling_service.process_large_document_summary(
|
||||
content=file_in_markdown,
|
||||
llm=user_llm,
|
||||
document_title=file_name
|
||||
content=file_in_markdown, llm=user_llm, document_title=file_name
|
||||
)
|
||||
summary_embedding = config.embedding_model_instance.embed(summary_content)
|
||||
|
||||
|
|
@ -726,7 +765,9 @@ async def add_received_file_document_using_docling(
|
|||
raise db_error
|
||||
except Exception as e:
|
||||
await session.rollback()
|
||||
raise RuntimeError(f"Failed to process file document using Docling: {str(e)}")
|
||||
raise RuntimeError(
|
||||
f"Failed to process file document using Docling: {e!s}"
|
||||
) from e
|
||||
|
||||
|
||||
async def add_youtube_video_document(
|
||||
|
|
@ -749,23 +790,23 @@ async def add_youtube_video_document(
|
|||
RuntimeError: If the video processing fails
|
||||
"""
|
||||
task_logger = TaskLoggingService(session, search_space_id)
|
||||
|
||||
|
||||
# Log task start
|
||||
log_entry = await task_logger.log_task_start(
|
||||
task_name="youtube_video_document",
|
||||
source="background_task",
|
||||
message=f"Starting YouTube video processing for: {url}",
|
||||
metadata={"url": url, "user_id": str(user_id)}
|
||||
metadata={"url": url, "user_id": str(user_id)},
|
||||
)
|
||||
|
||||
|
||||
try:
|
||||
# Extract video ID from URL
|
||||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Extracting video ID from URL: {url}",
|
||||
{"stage": "video_id_extraction"}
|
||||
{"stage": "video_id_extraction"},
|
||||
)
|
||||
|
||||
|
||||
def get_youtube_video_id(url: str):
|
||||
parsed_url = urlparse(url)
|
||||
hostname = parsed_url.hostname
|
||||
|
|
@ -790,14 +831,14 @@ async def add_youtube_video_document(
|
|||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Video ID extracted: {video_id}",
|
||||
{"stage": "video_id_extracted", "video_id": video_id}
|
||||
{"stage": "video_id_extracted", "video_id": video_id},
|
||||
)
|
||||
|
||||
# Get video metadata
|
||||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Fetching video metadata for: {video_id}",
|
||||
{"stage": "metadata_fetch"}
|
||||
{"stage": "metadata_fetch"},
|
||||
)
|
||||
|
||||
params = {
|
||||
|
|
@ -806,21 +847,27 @@ async def add_youtube_video_document(
|
|||
}
|
||||
oembed_url = "https://www.youtube.com/oembed"
|
||||
|
||||
async with aiohttp.ClientSession() as http_session:
|
||||
async with http_session.get(oembed_url, params=params) as response:
|
||||
video_data = await response.json()
|
||||
async with (
|
||||
aiohttp.ClientSession() as http_session,
|
||||
http_session.get(oembed_url, params=params) as response,
|
||||
):
|
||||
video_data = await response.json()
|
||||
|
||||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Video metadata fetched: {video_data.get('title', 'Unknown')}",
|
||||
{"stage": "metadata_fetched", "title": video_data.get('title'), "author": video_data.get('author_name')}
|
||||
{
|
||||
"stage": "metadata_fetched",
|
||||
"title": video_data.get("title"),
|
||||
"author": video_data.get("author_name"),
|
||||
},
|
||||
)
|
||||
|
||||
# Get video transcript
|
||||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Fetching transcript for video: {video_id}",
|
||||
{"stage": "transcript_fetch"}
|
||||
{"stage": "transcript_fetch"},
|
||||
)
|
||||
|
||||
try:
|
||||
|
|
@ -834,25 +881,29 @@ async def add_youtube_video_document(
|
|||
timestamp = f"[{start_time:.2f}s-{start_time + duration:.2f}s]"
|
||||
transcript_segments.append(f"{timestamp} {text}")
|
||||
transcript_text = "\n".join(transcript_segments)
|
||||
|
||||
|
||||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Transcript fetched successfully: {len(captions)} segments",
|
||||
{"stage": "transcript_fetched", "segments_count": len(captions), "transcript_length": len(transcript_text)}
|
||||
{
|
||||
"stage": "transcript_fetched",
|
||||
"segments_count": len(captions),
|
||||
"transcript_length": len(transcript_text),
|
||||
},
|
||||
)
|
||||
except Exception as e:
|
||||
transcript_text = f"No captions available for this video. Error: {str(e)}"
|
||||
transcript_text = f"No captions available for this video. Error: {e!s}"
|
||||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"No transcript available for video: {video_id}",
|
||||
{"stage": "transcript_unavailable", "error": str(e)}
|
||||
{"stage": "transcript_unavailable", "error": str(e)},
|
||||
)
|
||||
|
||||
# Format document
|
||||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Processing video content: {video_data.get('title', 'YouTube Video')}",
|
||||
{"stage": "content_processing"}
|
||||
{"stage": "content_processing"},
|
||||
)
|
||||
|
||||
# Format document metadata in a more maintainable way
|
||||
|
|
@ -890,7 +941,7 @@ async def add_youtube_video_document(
|
|||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Checking for duplicate video content: {video_id}",
|
||||
{"stage": "duplicate_check", "content_hash": content_hash}
|
||||
{"stage": "duplicate_check", "content_hash": content_hash},
|
||||
)
|
||||
|
||||
# Check if document with this content hash already exists
|
||||
|
|
@ -898,21 +949,27 @@ async def add_youtube_video_document(
|
|||
select(Document).where(Document.content_hash == content_hash)
|
||||
)
|
||||
existing_document = existing_doc_result.scalars().first()
|
||||
|
||||
|
||||
if existing_document:
|
||||
await task_logger.log_task_success(
|
||||
log_entry,
|
||||
f"YouTube video document already exists: {video_data.get('title', 'YouTube Video')}",
|
||||
{"duplicate_detected": True, "existing_document_id": existing_document.id, "video_id": video_id}
|
||||
{
|
||||
"duplicate_detected": True,
|
||||
"existing_document_id": existing_document.id,
|
||||
"video_id": video_id,
|
||||
},
|
||||
)
|
||||
logging.info(
|
||||
f"Document with content hash {content_hash} already exists. Skipping processing."
|
||||
)
|
||||
logging.info(f"Document with content hash {content_hash} already exists. Skipping processing.")
|
||||
return existing_document
|
||||
|
||||
# Get LLM for summary generation
|
||||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Preparing for summary generation: {video_data.get('title', 'YouTube Video')}",
|
||||
{"stage": "llm_setup"}
|
||||
{"stage": "llm_setup"},
|
||||
)
|
||||
|
||||
# Get user's long context LLM
|
||||
|
|
@ -924,7 +981,7 @@ async def add_youtube_video_document(
|
|||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Generating summary for video: {video_data.get('title', 'YouTube Video')}",
|
||||
{"stage": "summary_generation"}
|
||||
{"stage": "summary_generation"},
|
||||
)
|
||||
|
||||
summary_chain = SUMMARY_PROMPT_TEMPLATE | user_llm
|
||||
|
|
@ -938,7 +995,7 @@ async def add_youtube_video_document(
|
|||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Processing content chunks for video: {video_data.get('title', 'YouTube Video')}",
|
||||
{"stage": "chunk_processing"}
|
||||
{"stage": "chunk_processing"},
|
||||
)
|
||||
|
||||
chunks = [
|
||||
|
|
@ -953,7 +1010,7 @@ async def add_youtube_video_document(
|
|||
await task_logger.log_task_progress(
|
||||
log_entry,
|
||||
f"Creating YouTube video document in database: {video_data.get('title', 'YouTube Video')}",
|
||||
{"stage": "document_creation", "chunks_count": len(chunks)}
|
||||
{"stage": "document_creation", "chunks_count": len(chunks)},
|
||||
)
|
||||
|
||||
document = Document(
|
||||
|
|
@ -988,8 +1045,8 @@ async def add_youtube_video_document(
|
|||
"content_hash": content_hash,
|
||||
"chunks_count": len(chunks),
|
||||
"summary_length": len(summary_content),
|
||||
"has_transcript": "No captions available" not in transcript_text
|
||||
}
|
||||
"has_transcript": "No captions available" not in transcript_text,
|
||||
},
|
||||
)
|
||||
|
||||
return document
|
||||
|
|
@ -999,7 +1056,10 @@ async def add_youtube_video_document(
|
|||
log_entry,
|
||||
f"Database error while processing YouTube video: {url}",
|
||||
str(db_error),
|
||||
{"error_type": "SQLAlchemyError", "video_id": video_id if 'video_id' in locals() else None}
|
||||
{
|
||||
"error_type": "SQLAlchemyError",
|
||||
"video_id": video_id if "video_id" in locals() else None,
|
||||
},
|
||||
)
|
||||
raise db_error
|
||||
except Exception as e:
|
||||
|
|
@ -1008,7 +1068,10 @@ async def add_youtube_video_document(
|
|||
log_entry,
|
||||
f"Failed to process YouTube video: {url}",
|
||||
str(e),
|
||||
{"error_type": type(e).__name__, "video_id": video_id if 'video_id' in locals() else None}
|
||||
{
|
||||
"error_type": type(e).__name__,
|
||||
"video_id": video_id if "video_id" in locals() else None,
|
||||
},
|
||||
)
|
||||
logging.error(f"Failed to process YouTube video: {str(e)}")
|
||||
logging.error(f"Failed to process YouTube video: {e!s}")
|
||||
raise
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue