mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 00:16:23 +02:00
24bbe94136
- Schema - ChunkEmbeddings now uses chunk_id: str instead of chunk: bytes
- Schema - DocumentEmbeddingsResponse now returns chunk_ids: list[str]
instead of chunks
- Translators - Updated to serialize/deserialize chunk_id
- Clients - DocumentEmbeddingsClient.query() returns chunk_ids
- SDK/API - flow.py, socket_client.py, bulk_client.py updated
- Document embeddings service - Stores chunk_id (document ID) instead
of chunk text
- Storage writers - Qdrant, Milvus, Pinecone store chunk_id in payload
- Query services - Return chunk_id from vector store searches
- Gateway dispatchers - Serialize chunk_id in API responses
- Document RAG - Added librarian client to fetch chunk content from
Garage using chunk_ids
- CLI tools - Updated all three tools:
- invoke_document_embeddings.py - displays chunk_ids, removed
max_chunk_length
- save_doc_embeds.py - exports chunk_id
- load_doc_embeds.py - imports chunk_id
109 lines
2.5 KiB
Python
109 lines
2.5 KiB
Python
"""
|
|
Queries document chunks by text similarity using vector embeddings.
|
|
Returns a list of matching chunk IDs.
|
|
"""
|
|
|
|
import argparse
|
|
import os
|
|
from trustgraph.api import Api
|
|
|
|
default_url = os.getenv("TRUSTGRAPH_URL", 'http://localhost:8088/')
|
|
default_token = os.getenv("TRUSTGRAPH_TOKEN", None)
|
|
|
|
def query(url, flow_id, query_text, user, collection, limit, token=None):
|
|
|
|
# Create API client
|
|
api = Api(url=url, token=token)
|
|
socket = api.socket()
|
|
flow = socket.flow(flow_id)
|
|
|
|
try:
|
|
# Call document embeddings query service
|
|
result = flow.document_embeddings_query(
|
|
text=query_text,
|
|
user=user,
|
|
collection=collection,
|
|
limit=limit
|
|
)
|
|
|
|
chunk_ids = result.get("chunk_ids", [])
|
|
if not chunk_ids:
|
|
print("No matching chunks found.")
|
|
else:
|
|
for i, chunk_id in enumerate(chunk_ids, 1):
|
|
print(f"{i}. {chunk_id}")
|
|
|
|
finally:
|
|
# Clean up socket connection
|
|
socket.close()
|
|
|
|
def main():
|
|
|
|
parser = argparse.ArgumentParser(
|
|
prog='tg-invoke-document-embeddings',
|
|
description=__doc__,
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-u', '--url',
|
|
default=default_url,
|
|
help=f'API URL (default: {default_url})',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-t', '--token',
|
|
default=default_token,
|
|
help='Authentication token (default: $TRUSTGRAPH_TOKEN)',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-f', '--flow-id',
|
|
default="default",
|
|
help=f'Flow ID (default: default)'
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-U', '--user',
|
|
default="trustgraph",
|
|
help='User/keyspace (default: trustgraph)',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-c', '--collection',
|
|
default="default",
|
|
help='Collection (default: default)',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'-l', '--limit',
|
|
type=int,
|
|
default=10,
|
|
help='Maximum number of results (default: 10)',
|
|
)
|
|
|
|
parser.add_argument(
|
|
'query',
|
|
nargs=1,
|
|
help='Query text to search for similar document chunks',
|
|
)
|
|
|
|
args = parser.parse_args()
|
|
|
|
try:
|
|
|
|
query(
|
|
url=args.url,
|
|
flow_id=args.flow_id,
|
|
query_text=args.query[0],
|
|
user=args.user,
|
|
collection=args.collection,
|
|
limit=args.limit,
|
|
token=args.token,
|
|
)
|
|
|
|
except Exception as e:
|
|
|
|
print("Exception:", e, flush=True)
|
|
|
|
if __name__ == "__main__":
|
|
main()
|