phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

migrate memory banks to Resource and new registration (#411)

Browse source 
* migrate memory banks to Resource and new registration

* address feedback

* address feedback

* fix tests

* pgvector fix

* pgvector fix v2

* remove auto discovery

* change register signature to make params required

* update client

* client fix

* use annotated union to parse

* remove base MemoryBank inheritence

---------

Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
This commit is contained in:
Dinesh Yeduguru 2024-11-11 17:10:44 -08:00 • committed by GitHub
parent 6b9850e11b
commit 38cce97597
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 240 additions and 129 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/inline/agents/meta_reference/agent_instance.py
View file

@ -641,7 +641,7 @@ class ChatAgent(ShieldRunnerMixin):
if session_info.memory_bank_id is None:
bank_id = f"memory_bank_{session_id}"
memory_bank = VectorMemoryBankDef(
memory_bank = VectorMemoryBank(
identifier=bank_id,
embedding_model="all-MiniLM-L6-v2",
chunk_size_in_tokens=512,