phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-08 19:10:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

more memory related fixes; memory.client now works

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-06 22:10:24 -07:00 • committed by Ashwin Bharambe
parent 3725e74906
commit 862f8ddb8d
3 changed files with 24 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/utils/memory/vector_store.py
View file

@ -153,15 +153,15 @@ class BankWithIndex:
self,
documents: List[MemoryBankDocument],
) -> None:
model = get_embedding_model(self.bank.config.embedding_model)
model = get_embedding_model(self.bank.embedding_model)
for doc in documents:
content = await content_from_doc(doc)
chunks = make_overlapped_chunks(
doc.document_id,
content,
self.bank.config.chunk_size_in_tokens,
self.bank.config.overlap_size_in_tokens
or (self.bank.config.chunk_size_in_tokens // 4),
self.bank.chunk_size_in_tokens,
self.bank.overlap_size_in_tokens
or (self.bank.chunk_size_in_tokens // 4),
)
if not chunks:
continue
@ -189,6 +189,6 @@ class BankWithIndex:
else:
query_str = _process(query)
model = get_embedding_model(self.bank.config.embedding_model)
model = get_embedding_model(self.bank.embedding_model)
query_vector = model.encode([query_str])[0].astype(np.float32)
return await self.index.query(query_vector, k)