phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-09 23:25:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Enable ingestion of precomputed embeddings (#2317)

Browse source
This commit is contained in:
Francisco Arceo 2025-05-31 04:03:37 -06:00 • committed by Sumit Jaiswal
parent dfdf854865
commit 2818e444f2
No known key found for this signature in database
GPG key ID: A4604B39D64D6AEC
9 changed files with 366 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/inline/tool_runtime/rag/memory.py
View file

@ -146,7 +146,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti
]
for i, chunk in enumerate(chunks):
metadata = chunk.metadata
tokens += metadata["token_count"]
tokens += metadata.get("token_count", 0)
tokens += metadata.get("metadata_token_count", 0)
if tokens > query_config.max_tokens_in_context: