michel/Philosophy-RAG-demo
1
0
Fork 0
forked from AI_team/Philosophy-RAG-demo
Code Pull Requests Activity

Add some doc-strings

Browse Source
This commit is contained in:
Nielson Janné 2025-03-17 14:25:39 +01:00
parent 3fa0e31521
commit 2ba3eadec4
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
generic_rag/parsers/parser.py
View File

@ -27,6 +27,11 @@ def code_handler(element: Tag) -> str:
def add_urls(vector_store: Chroma, urls: list[str], chunk_size: int) -> None: def add_urls(vector_store: Chroma, urls: list[str], chunk_size: int) -> None:
"""
Adds a list of URLs as vector documents to the provided vector store.
The URL's will be fetched and split into chunks of text with the provided chunk size.
"""
all_splits = [] all_splits = []
for url in urls: for url in urls:
if len(vector_store.get(where={"source": url}, limit=1)["ids"]) > 0: if len(vector_store.get(where={"source": url}, limit=1)["ids"]) > 0:
@ -72,6 +77,11 @@ def add_pdf_files(
add_start_index: bool, add_start_index: bool,
unstructerd: bool, unstructerd: bool,
) -> None: ) -> None:
"""
Adds a list of PDF files as vector documents to the provided vector store.
The PDF file will be parsed per page and split into chunks of text with the provided chunk size and overlap.
"""
pdf_files = get_all_local_pdf_files(file_paths) pdf_files = get_all_local_pdf_files(file_paths)
new_pdfs = [] new_pdfs = []