forked from phoenix-oss/llama-stack-mirror
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
```
45 lines
1.2 KiB
Python
45 lines
1.2 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 base64
|
|
import io
|
|
from urllib.parse import unquote
|
|
|
|
import pandas
|
|
|
|
from llama_stack.apis.common.content_types import URL
|
|
|
|
from llama_stack.providers.utils.memory.vector_store import parse_data_url
|
|
|
|
|
|
def get_dataframe_from_url(url: URL):
|
|
df = None
|
|
if url.uri.endswith(".csv"):
|
|
df = pandas.read_csv(url.uri)
|
|
elif url.uri.endswith(".xlsx"):
|
|
df = pandas.read_excel(url.uri)
|
|
elif url.uri.startswith("data:"):
|
|
parts = parse_data_url(url.uri)
|
|
data = parts["data"]
|
|
if parts["is_base64"]:
|
|
data = base64.b64decode(data)
|
|
else:
|
|
data = unquote(data)
|
|
encoding = parts["encoding"] or "utf-8"
|
|
data = data.encode(encoding)
|
|
|
|
mime_type = parts["mimetype"]
|
|
mime_category = mime_type.split("/")[0]
|
|
data_bytes = io.BytesIO(data)
|
|
|
|
if mime_category == "text":
|
|
df = pandas.read_csv(data_bytes)
|
|
else:
|
|
df = pandas.read_excel(data_bytes)
|
|
else:
|
|
raise ValueError(f"Unsupported file type: {url}")
|
|
|
|
return df
|