mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-16 14:57:20 +00:00
e9b4278a51
This PR updates the Conversation item related types and improves a couple critical parts of the implemenation: - it creates a streaming output item for the final assistant message output by the model. until now we only added content parts and included that message in the final response. - rewrites the conversation update code completely to account for items other than messages (tool calls, outputs, etc.) ## Test Plan Used the test script from https://github.com/llamastack/llama-stack-client-python/pull/281 for this ``` TEST_API_BASE_URL=http://localhost:8321/v1 \ pytest tests/integration/test_agent_turn_step_events.py::test_client_side_function_tool -xvs ```
68 lines
2.4 KiB
Python
68 lines
2.4 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 time
|
|
|
|
|
|
def new_vector_store(openai_client, name, embedding_model, embedding_dimension):
|
|
"""Create a new vector store, cleaning up any existing one with the same name."""
|
|
# Ensure we don't reuse an existing vector store
|
|
vector_stores = openai_client.vector_stores.list()
|
|
for vector_store in vector_stores:
|
|
if vector_store.name == name:
|
|
openai_client.vector_stores.delete(vector_store_id=vector_store.id)
|
|
|
|
# Create a new vector store
|
|
|
|
vector_store = openai_client.vector_stores.create(
|
|
name=name,
|
|
extra_body={"embedding_model": embedding_model, "embedding_dimension": embedding_dimension},
|
|
)
|
|
return vector_store
|
|
|
|
|
|
def upload_file(openai_client, name, file_path):
|
|
"""Upload a file, cleaning up any existing file with the same name."""
|
|
# Ensure we don't reuse an existing file
|
|
files = openai_client.files.list()
|
|
for file in files:
|
|
if file.filename == name:
|
|
openai_client.files.delete(file_id=file.id)
|
|
|
|
# Upload a text file with our document content
|
|
return openai_client.files.create(file=open(file_path, "rb"), purpose="assistants")
|
|
|
|
|
|
def wait_for_file_attachment(compat_client, vector_store_id, file_id):
|
|
"""Wait for a file to be attached to a vector store."""
|
|
file_attach_response = compat_client.vector_stores.files.retrieve(
|
|
vector_store_id=vector_store_id,
|
|
file_id=file_id,
|
|
)
|
|
|
|
while file_attach_response.status == "in_progress":
|
|
time.sleep(0.1)
|
|
file_attach_response = compat_client.vector_stores.files.retrieve(
|
|
vector_store_id=vector_store_id,
|
|
file_id=file_id,
|
|
)
|
|
|
|
assert file_attach_response.status == "completed", f"Expected file to be attached, got {file_attach_response}"
|
|
assert not file_attach_response.last_error
|
|
return file_attach_response
|
|
|
|
|
|
def setup_mcp_tools(tools, mcp_server_info):
|
|
"""Replace placeholder MCP server URLs with actual server info."""
|
|
# Create a deep copy to avoid modifying the original test case
|
|
import copy
|
|
|
|
tools_copy = copy.deepcopy(tools)
|
|
|
|
for tool in tools_copy:
|
|
if tool["type"] == "mcp" and tool["server_url"] == "<FILLED_BY_TEST_RUNNER>":
|
|
tool["server_url"] = mcp_server_info["server_url"]
|
|
return tools_copy
|