Francisco Arceo
e7d21e1ee3
feat: Add support for Conversations in Responses API ( #3743 )
...
# What does this PR do?
This PR adds support for Conversations in Responses.
<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
## Test Plan
Unit tests
Integration tests
<Details>
<Summary>Manual testing with this script: (click to expand)</Summary>
```python
from openai import OpenAI
client = OpenAI()
client = OpenAI(base_url="http://localhost:8321/v1/ ", api_key="none")
def test_conversation_create():
print("Testing conversation create...")
conversation = client.conversations.create(
metadata={"topic": "demo"},
items=[
{"type": "message", "role": "user", "content": "Hello!"}
]
)
print(f"Created: {conversation}")
return conversation
def test_conversation_retrieve(conv_id):
print(f"Testing conversation retrieve for {conv_id}...")
retrieved = client.conversations.retrieve(conv_id)
print(f"Retrieved: {retrieved}")
return retrieved
def test_conversation_update(conv_id):
print(f"Testing conversation update for {conv_id}...")
updated = client.conversations.update(
conv_id,
metadata={"topic": "project-x"}
)
print(f"Updated: {updated}")
return updated
def test_conversation_delete(conv_id):
print(f"Testing conversation delete for {conv_id}...")
deleted = client.conversations.delete(conv_id)
print(f"Deleted: {deleted}")
return deleted
def test_conversation_items_create(conv_id):
print(f"Testing conversation items create for {conv_id}...")
items = client.conversations.items.create(
conv_id,
items=[
{
"type": "message",
"role": "user",
"content": [{"type": "input_text", "text": "Hello!"}]
},
{
"type": "message",
"role": "user",
"content": [{"type": "input_text", "text": "How are you?"}]
}
]
)
print(f"Items created: {items}")
return items
def test_conversation_items_list(conv_id):
print(f"Testing conversation items list for {conv_id}...")
items = client.conversations.items.list(conv_id, limit=10)
print(f"Items list: {items}")
return items
def test_conversation_item_retrieve(conv_id, item_id):
print(f"Testing conversation item retrieve for {conv_id}/{item_id}...")
item = client.conversations.items.retrieve(conversation_id=conv_id, item_id=item_id)
print(f"Item retrieved: {item}")
return item
def test_conversation_item_delete(conv_id, item_id):
print(f"Testing conversation item delete for {conv_id}/{item_id}...")
deleted = client.conversations.items.delete(conversation_id=conv_id, item_id=item_id)
print(f"Item deleted: {deleted}")
return deleted
def test_conversation_responses_create():
print("\nTesting conversation create for a responses example...")
conversation = client.conversations.create()
print(f"Created: {conversation}")
response = client.responses.create(
model="gpt-4.1",
input=[{"role": "user", "content": "What are the 5 Ds of dodgeball?"}],
conversation=conversation.id,
)
print(f"Created response: {response} for conversation {conversation.id}")
return response, conversation
def test_conversations_responses_create_followup(
conversation,
content="Repeat what you just said but add 'this is my second time saying this'",
):
print(f"Using: {conversation.id}")
response = client.responses.create(
model="gpt-4.1",
input=[{"role": "user", "content": content}],
conversation=conversation.id,
)
print(f"Created response: {response} for conversation {conversation.id}")
conv_items = client.conversations.items.list(conversation.id)
print(f"\nRetrieving list of items for conversation {conversation.id}:")
print(conv_items.model_dump_json(indent=2))
def test_response_with_fake_conv_id():
fake_conv_id = "conv_zzzzzzzzz5dc81908289d62779d2ac510a2b0b602ef00a44"
print(f"Using {fake_conv_id}")
try:
response = client.responses.create(
model="gpt-4.1",
input=[{"role": "user", "content": "say hello"}],
conversation=fake_conv_id,
)
print(f"Created response: {response} for conversation {fake_conv_id}")
except Exception as e:
print(f"failed to create response for conversation {fake_conv_id} with error {e}")
def main():
print("Testing OpenAI Conversations API...")
# Create conversation
conversation = test_conversation_create()
conv_id = conversation.id
# Retrieve conversation
test_conversation_retrieve(conv_id)
# Update conversation
test_conversation_update(conv_id)
# Create items
items = test_conversation_items_create(conv_id)
# List items
items_list = test_conversation_items_list(conv_id)
# Retrieve specific item
if items_list.data:
item_id = items_list.data[0].id
test_conversation_item_retrieve(conv_id, item_id)
# Delete item
test_conversation_item_delete(conv_id, item_id)
# Delete conversation
test_conversation_delete(conv_id)
response, conversation2 = test_conversation_responses_create()
print('\ntesting reseponse retrieval')
test_conversation_retrieve(conversation2.id)
print('\ntesting responses follow up')
test_conversations_responses_create_followup(conversation2)
print('\ntesting responses follow up x2!')
test_conversations_responses_create_followup(
conversation2,
content="Repeat what you just said but add 'this is my third time saying this'",
)
test_response_with_fake_conv_id()
print("All tests completed!")
if __name__ == "__main__":
main()
```
</Details>
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
2025-10-10 11:57:40 -07:00
Sébastien Han
f31bcc11bc
feat: add Azure OpenAI inference provider support ( #3396 )
...
# What does this PR do?
Llama-stack now supports a new OpenAI compatible endpoint with Azure
OpenAI. The starter distro has been updated to add the new remote
inference provider.
A few tests have been modified and improved.
## Test Plan
Deploy a model in the Aure portal then:
```
$ AZURE_API_KEY=... AZURE_API_BASE=... uv run llama stack build --image-type venv --providers inference=remote::azure --run
...
$ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model azure/gpt-4.1 tests/integration/inference/test_openai_completion.py
...
Results:
```
============================================= test session starts
============================================== platform darwin -- Python
3.12.8, pytest-8.4.1, pluggy-1.6.0 --
/Users/leseb/Documents/AI/llama-stack/.venv/bin/python3 cachedir:
.pytest_cache
metadata: {'Python': '3.12.8', 'Platform':
'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '8.4.1',
'pluggy': '1.6.0'}, 'Plugins': {'anyio': '4.9.0', 'html': '4.1.1',
'socket': '0.7.0', 'asyncio': '1.1.0', 'json-report': '1.5.0',
'timeout': '2.4.0', 'metadata': '3.1.1', 'cov': '6.2.1', 'nbval':
'0.11.0', 'hydra-core': '1.3.2'}} rootdir:
/Users/leseb/Documents/AI/llama-stack
configfile: pyproject.toml
plugins: anyio-4.9.0, html-4.1.1, socket-0.7.0, asyncio-1.1.0,
json-report-1.5.0, timeout-2.4.0, metadata-3.1.1, cov-6.2.1,
nbval-0.11.0, hydra-core-1.3.2 asyncio: mode=Mode.AUTO,
asyncio_default_fixture_loop_scope=None,
asyncio_default_test_loop_scope=function collected 27 items
tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=azure/gpt-5-mini-inference:completion:sanity]
SKIPPED [ 3%]
tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming_suffix[txt=azure/gpt-5-mini-inference:completion:suffix]
SKIPPED [ 7%]
tests/integration/inference/test_openai_completion.py::test_openai_completion_streaming[txt=azure/gpt-5-mini-inference:completion:sanity]
SKIPPED [ 11%]
tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=azure/gpt-5-mini-1]
SKIPPED [ 14%]
tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=azure/gpt-5-mini]
SKIPPED [ 18%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_01]
PASSED [ 22%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01]
PASSED [ 25%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01]
PASSED [ 29%]
tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=azure/gpt-5-mini-True]
PASSED [ 33%]
tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=azure/gpt-5-mini-True]
PASSED [ 37%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming_with_file[txt=azure/gpt-5-mini]
SKIPPEDed files.) [ 40%]
tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=azure/gpt-5-mini-0]
SKIPPED [ 44%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_02]
PASSED [ 48%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02]
PASSED [ 51%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02]
PASSED [ 55%]
tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=azure/gpt-5-mini-False]
PASSED [ 59%]
tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=azure/gpt-5-mini-False]
PASSED [ 62%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_01]
PASSED [ 66%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01]
PASSED [ 70%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01]
PASSED [ 74%]
tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=azure/gpt-5-mini-True]
PASSED [ 77%]
tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=azure/gpt-5-mini-True]
PASSED [ 81%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_02]
PASSED [ 85%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02]
PASSED [ 88%]
tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02]
PASSED [ 92%]
tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=azure/gpt-5-mini-False]
PASSED [ 96%]
tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=azure/gpt-5-mini-False]
PASSED [100%]
=========================================== short test summary info
============================================ SKIPPED [3]
tests/integration/inference/test_openai_completion.py:63: Model
azure/gpt-5-mini hosted by remote::azure doesn't support OpenAI
completions. SKIPPED [3]
tests/integration/inference/test_openai_completion.py:118: Model
azure/gpt-5-mini hosted by remote::azure doesn't support vllm extra_body
parameters. SKIPPED [1]
tests/integration/inference/test_openai_completion.py:124: Model
azure/gpt-5-mini hosted by remote::azure doesn't support chat completion
calls with base64 encoded files. ================================== 20
passed, 7 skipped, 2 warnings in 51.77s
==================================
```
Signed-off-by: Sébastien Han <seb@redhat.com>
2025-09-11 13:48:38 +02:00
