Spaces:
Sleeping
Sleeping
File size: 1,272 Bytes
1fee1c2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | # COST: ZERO OpenAI tokens.
# Reads ChromaDB metadata only — no embedding or similarity search performed.
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent.parent))
from dotenv import load_dotenv
load_dotenv()
from chroma import get_collection # noqa: E402
def list_indexed_documents() -> list[str]:
"""Return the names of all documents that have been indexed in the vector store.
Queries the ChromaDB collection metadata to collect every unique
'source_file' value without loading any embeddings or performing any
similarity search. No LLM call is made.
This is useful for letting the agent know which documents are available
before deciding whether to retrieve chunks or ask the user to upload more
files.
Returns:
A sorted list of unique source file names (e.g. ['manual.pdf', 'notes.docx']).
Returns an empty list if no documents have been indexed yet.
"""
collection = get_collection()
if collection.count() == 0:
return []
result = collection.get(include=["metadatas"])
seen: set[str] = set()
for meta in result["metadatas"]:
source = meta.get("source_file")
if source:
seen.add(source)
return sorted(seen)
|