phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-31 16:01:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: Setting default value for metadata_token_count in case the key is not found

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-05-18 21:29:55 -04:00
parent 1341916caf
commit 50bc9053f8
1 changed files with 1 additions and 1 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(ToolsProtocolPrivate, ToolRuntime, RAGToolRuntime):
for i, chunk in enumerate(chunks):
metadata = chunk.metadata
tokens += metadata["token_count"]
tokens += metadata["metadata_token_count"]
tokens += metadata.get("metadata_token_count", 0)
if tokens > query_config.max_tokens_in_context:
log.error(