Commit graph

3 commits

Author SHA1 Message Date
Cyber MacGeddon
da37738478 Make sure nul output is specific 2026-03-07 21:09:08 +00:00
Cyber MacGeddon
04e03c0707 - 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
2026-03-07 20:15:15 +00:00
cybermaggedon
6bf08c3ace
Feature/more cli diags (#624)
* CLI tools for tg-invoke-graph-embeddings, tg-invoke-document-embeddings,
and tg-invoke-embeddings.  Just useful for diagnostics.

* Fix tg-load-knowledge
2026-02-04 14:10:30 +00:00