mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 18:00:36 +00:00
Update the "InterleavedTextMedia" type (#635)
## 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
```
This commit is contained in:
parent
10eb31badf
commit
8de8eb03c8
66 changed files with 1344 additions and 1801 deletions
|
|
@ -5,7 +5,6 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
from contextlib import asynccontextmanager
|
||||
from typing import Dict, List, Optional, Protocol, Tuple
|
||||
|
||||
|
|
@ -54,10 +53,7 @@ def _parse_registry_values(values: List[str]) -> List[RoutableObjectWithProvider
|
|||
"""Utility function to parse registry values into RoutableObjectWithProvider objects."""
|
||||
all_objects = []
|
||||
for value in values:
|
||||
obj = pydantic.parse_obj_as(
|
||||
RoutableObjectWithProvider,
|
||||
json.loads(value),
|
||||
)
|
||||
obj = pydantic.TypeAdapter(RoutableObjectWithProvider).validate_json(value)
|
||||
all_objects.append(obj)
|
||||
return all_objects
|
||||
|
||||
|
|
@ -89,14 +85,7 @@ class DiskDistributionRegistry(DistributionRegistry):
|
|||
if not json_str:
|
||||
return None
|
||||
|
||||
objects_data = json.loads(json_str)
|
||||
# Return only the first object if any exist
|
||||
if objects_data:
|
||||
return pydantic.parse_obj_as(
|
||||
RoutableObjectWithProvider,
|
||||
json.loads(objects_data),
|
||||
)
|
||||
return None
|
||||
return pydantic.TypeAdapter(RoutableObjectWithProvider).validate_json(json_str)
|
||||
|
||||
async def update(self, obj: RoutableObjectWithProvider) -> None:
|
||||
await self.kvstore.set(
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue