Skip to content

Fixes #139 #158

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Apr 25, 2025
Merged

Fixes #139 #158

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a06c319
Fixes #139
gotsysdba Apr 25, 2025
24775e4
Remove print
gotsysdba Apr 25, 2025
22aca0b
Merge remote-tracking branch 'origin/main' into 157-add-unstructured
gotsysdba Apr 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions src/server/utils/embedding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
Copyright (c) 2024, 2025, Oracle and/or its affiliates.
Licensed under the Universal Permissive License v1.0 as shown at http://oss.oracle.com/licenses/upl.
"""
# spell-checker:ignore langchain, docstore, docos, vectorstores, oraclevs
# spell-checker:ignore langchain, docstore, docos, vectorstores, oraclevs, genai, hnsw

import json
import copy
Expand All @@ -22,7 +22,7 @@
from langchain_core.language_models.chat_models import BaseChatModel
from langchain.docstore.document import Document as LangchainDocument
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_text_splitters import HTMLSectionSplitter, CharacterTextSplitter
from langchain_text_splitters import HTMLHeaderTextSplitter, CharacterTextSplitter

import server.utils.databases as databases

Expand Down Expand Up @@ -130,20 +130,19 @@ def split_document(
("h4", "Header 4"),
("h5", "Header 5"),
]
html_splitter = HTMLSectionSplitter(headers_to_split_on=headers_to_split_on)
html_splitter = HTMLHeaderTextSplitter(headers_to_split_on=headers_to_split_on)
##################################
# Splitters - End
##################################
match extension.lower():
case "pdf":
doc_split = text_splitter.split_documents(document)
case "html":
try:
html_split = html_splitter.split_documents(document)
except Exception as ex:
logger.exception(ex)
html_split = document
doc_split = text_splitter.split_documents(html_split)
tmp_meta = document[0].metadata
doc_split = html_splitter.split_text(document[0].page_content)
# Update metadata with source
for doc in doc_split:
doc.metadata.update(tmp_meta)
case "pdf" | "md" | "txt" | "csv":
doc_split = text_splitter.split_documents(document)
case _:
Expand Down Expand Up @@ -180,7 +179,8 @@ def load_and_split_documents(
case "pdf":
loader = document_loaders.PyPDFLoader(file)
case "html":
loader = document_loaders.UnstructuredHTMLLoader(file)
# Use TextLoader to preserve for header split
loader = document_loaders.TextLoader(file)
case "md":
loader = document_loaders.TextLoader(file)
case "csv":
Expand Down