phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 19:04:19 +00:00
Code Issues Projects Releases Packages Wiki 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

12
llama_stack/apis/memory/client.py
View file

@ -75,14 +75,22 @@ class MemoryClient(Memory):
async def run_main(host: str, port: int, stream: bool):
banks_client = MemoryBanksClient(f"http://{host}:{port}")
bank = VectorMemoryBankDef(
bank = VectorMemoryBank(
identifier="test_bank",
provider_id="",
embedding_model="all-MiniLM-L6-v2",
chunk_size_in_tokens=512,
overlap_size_in_tokens=64,
)
await banks_client.register_memory_bank(bank)
await banks_client.register_memory_bank(
bank.identifier,
VectorMemoryBankParams(
embedding_model="all-MiniLM-L6-v2",
chunk_size_in_tokens=512,
overlap_size_in_tokens=64,
),
provider_resource_id=bank.identifier,
)
retrieved_bank = await banks_client.get_memory_bank(bank.identifier)
assert retrieved_bank is not None