mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-17 20:02:37 +00:00
8de8eb03c8
## What does this PR do?
This is a long-pending change and particularly important to get done
now.
Specifically:
- we cannot "localize" (aka download) any URLs from media attachments
anywhere near our modeling code. it must be done within llama-stack.
- `PIL.Image` is infesting all our APIs via `ImageMedia ->
InterleavedTextMedia` and that cannot be right at all. Anything in the
API surface must be "naturally serializable". We need a standard `{
type: "image", image_url: "<...>" }` which is more extensible
- `UserMessage`, `SystemMessage`, etc. are moved completely to
llama-stack from the llama-models repository.
See https://github.com/meta-llama/llama-models/pull/244 for the
corresponding PR in llama-models.
## Test Plan
```bash
cd llama_stack/providers/tests
pytest -s -v -k "fireworks or ollama or together" inference/test_vision_inference.py
pytest -s -v -k "(fireworks or ollama or together) and llama_3b" inference/test_text_inference.py
pytest -s -v -k chroma memory/test_memory.py \
--env EMBEDDING_DIMENSION=384 --env CHROMA_DB_PATH=/tmp/foobar
pytest -s -v -k fireworks agents/test_agents.py \
--safety-shield=meta-llama/Llama-Guard-3-8B \
--inference-model=meta-llama/Llama-3.1-8B-Instruct
```
Updated the client sdk (see PR ...), installed the SDK in the same
environment and then ran the SDK tests:
```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=together pytest -s -v agents/test_agents.py
LLAMA_STACK_CONFIG=ollama pytest -s -v memory/test_memory.py
# this one needed a bit of hacking in the run.yaml to ensure I could register the vision model correctly
INFERENCE_MODEL=llama3.2-vision:latest LLAMA_STACK_CONFIG=ollama pytest -s -v inference/test_inference.py
```
73 lines
2.1 KiB
Python
73 lines
2.1 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import pytest
|
|
from llama_stack_client.types.memory_insert_params import Document
|
|
|
|
|
|
def test_memory_bank(llama_stack_client):
|
|
providers = llama_stack_client.providers.list()
|
|
if "memory" not in providers:
|
|
pytest.skip("No memory provider available")
|
|
|
|
# get memory provider id
|
|
assert len(providers["memory"]) > 0
|
|
|
|
memory_provider_id = providers["memory"][0].provider_id
|
|
memory_bank_id = "test_bank"
|
|
|
|
llama_stack_client.memory_banks.register(
|
|
memory_bank_id=memory_bank_id,
|
|
params={
|
|
"memory_bank_type": "vector",
|
|
"embedding_model": "all-MiniLM-L6-v2",
|
|
"chunk_size_in_tokens": 512,
|
|
"overlap_size_in_tokens": 64,
|
|
},
|
|
provider_id=memory_provider_id,
|
|
)
|
|
|
|
# list to check memory bank is successfully registered
|
|
available_memory_banks = [
|
|
memory_bank.identifier for memory_bank in llama_stack_client.memory_banks.list()
|
|
]
|
|
assert memory_bank_id in available_memory_banks
|
|
|
|
# add documents to memory bank
|
|
urls = [
|
|
"memory_optimizations.rst",
|
|
"chat.rst",
|
|
"llama3.rst",
|
|
"datasets.rst",
|
|
]
|
|
documents = [
|
|
Document(
|
|
document_id=f"num-{i}",
|
|
content=f"https://raw.githubusercontent.com/pytorch/torchtune/main/docs/source/tutorials/{url}",
|
|
mime_type="text/plain",
|
|
metadata={},
|
|
)
|
|
for i, url in enumerate(urls)
|
|
]
|
|
|
|
llama_stack_client.memory.insert(
|
|
bank_id=memory_bank_id,
|
|
documents=documents,
|
|
)
|
|
|
|
# query documents
|
|
response = llama_stack_client.memory.query(
|
|
bank_id=memory_bank_id,
|
|
query=[
|
|
"How do I use lora",
|
|
],
|
|
)
|
|
|
|
assert len(response.chunks) > 0
|
|
assert len(response.chunks) == len(response.scores)
|
|
|
|
contents = [chunk.content for chunk in response.chunks]
|
|
assert "lora" in contents[0].lower()
|