Document chunks not stored in vector store (#665)

- 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

trustgraph-cli/trustgraph/cli/invoke_document_embeddings.py

@@ -1,6 +1,6 @@
 """
 Queries document chunks by text similarity using vector embeddings.
-Returns a list of matching document chunks, truncated to the specified length.
+Returns a list of matching chunk IDs.
 """
 
 import argparse
@@ -10,13 +10,7 @@ from trustgraph.api import Api
 default_url = os.getenv("TRUSTGRAPH_URL", 'http://localhost:8088/')
 default_token = os.getenv("TRUSTGRAPH_TOKEN", None)
 
-def truncate_chunk(chunk, max_length):
-    """Truncate a chunk to max_length characters, adding ellipsis if needed."""
-    if len(chunk) <= max_length:
-        return chunk
-    return chunk[:max_length] + "..."
-
-def query(url, flow_id, query_text, user, collection, limit, max_chunk_length, token=None):
+def query(url, flow_id, query_text, user, collection, limit, token=None):
 
     # Create API client
     api = Api(url=url, token=token)
@@ -32,10 +26,12 @@ def query(url, flow_id, query_text, user, collection, limit, max_chunk_length, t
             limit=limit
         )
 
-        chunks = result.get("chunks", [])
-        for i, chunk in enumerate(chunks, 1):
-            truncated = truncate_chunk(chunk, max_chunk_length)
-            print(f"{i}. {truncated}")
+        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
@@ -85,13 +81,6 @@ def main():
         help='Maximum number of results (default: 10)',
     )
 
-    parser.add_argument(
-        '--max-chunk-length',
-        type=int,
-        default=200,
-        help='Truncate chunks to N characters (default: 200)',
-    )
-
     parser.add_argument(
         'query',
         nargs=1,
@@ -109,7 +98,6 @@ def main():
             user=args.user,
             collection=args.collection,
             limit=args.limit,
-            max_chunk_length=args.max_chunk_length,
             token=args.token,
         )