mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-11 13:44:38 +00:00
e7d21e1ee3
# 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>
103 lines
3.9 KiB
Python
103 lines
3.9 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.
|
|
|
|
# Custom Llama Stack Exception classes should follow the following schema
|
|
# 1. All classes should inherit from an existing Built-In Exception class: https://docs.python.org/3/library/exceptions.html
|
|
# 2. All classes should have a custom error message with the goal of informing the Llama Stack user specifically
|
|
# 3. All classes should propogate the inherited __init__ function otherwise via 'super().__init__(message)'
|
|
|
|
|
|
class ResourceNotFoundError(ValueError):
|
|
"""generic exception for a missing Llama Stack resource"""
|
|
|
|
def __init__(self, resource_name: str, resource_type: str, client_list: str) -> None:
|
|
message = (
|
|
f"{resource_type} '{resource_name}' not found. Use '{client_list}' to list available {resource_type}s."
|
|
)
|
|
super().__init__(message)
|
|
|
|
|
|
class UnsupportedModelError(ValueError):
|
|
"""raised when model is not present in the list of supported models"""
|
|
|
|
def __init__(self, model_name: str, supported_models_list: list[str]):
|
|
message = f"'{model_name}' model is not supported. Supported models are: {', '.join(supported_models_list)}"
|
|
super().__init__(message)
|
|
|
|
|
|
class ModelNotFoundError(ResourceNotFoundError):
|
|
"""raised when Llama Stack cannot find a referenced model"""
|
|
|
|
def __init__(self, model_name: str) -> None:
|
|
super().__init__(model_name, "Model", "client.models.list()")
|
|
|
|
|
|
class VectorStoreNotFoundError(ResourceNotFoundError):
|
|
"""raised when Llama Stack cannot find a referenced vector store"""
|
|
|
|
def __init__(self, vector_store_name: str) -> None:
|
|
super().__init__(vector_store_name, "Vector Store", "client.vector_dbs.list()")
|
|
|
|
|
|
class DatasetNotFoundError(ResourceNotFoundError):
|
|
"""raised when Llama Stack cannot find a referenced dataset"""
|
|
|
|
def __init__(self, dataset_name: str) -> None:
|
|
super().__init__(dataset_name, "Dataset", "client.datasets.list()")
|
|
|
|
|
|
class ToolGroupNotFoundError(ResourceNotFoundError):
|
|
"""raised when Llama Stack cannot find a referenced tool group"""
|
|
|
|
def __init__(self, toolgroup_name: str) -> None:
|
|
super().__init__(toolgroup_name, "Tool Group", "client.toolgroups.list()")
|
|
|
|
|
|
class SessionNotFoundError(ValueError):
|
|
"""raised when Llama Stack cannot find a referenced session or access is denied"""
|
|
|
|
def __init__(self, session_name: str) -> None:
|
|
message = f"Session '{session_name}' not found or access denied."
|
|
super().__init__(message)
|
|
|
|
|
|
class ModelTypeError(TypeError):
|
|
"""raised when a model is present but not the correct type"""
|
|
|
|
def __init__(self, model_name: str, model_type: str, expected_model_type: str) -> None:
|
|
message = (
|
|
f"Model '{model_name}' is of type '{model_type}' rather than the expected type '{expected_model_type}'"
|
|
)
|
|
super().__init__(message)
|
|
|
|
|
|
class ConflictError(ValueError):
|
|
"""raised when an operation cannot be performed due to a conflict with the current state"""
|
|
|
|
def __init__(self, message: str) -> None:
|
|
super().__init__(message)
|
|
|
|
|
|
class TokenValidationError(ValueError):
|
|
"""raised when token validation fails during authentication"""
|
|
|
|
def __init__(self, message: str) -> None:
|
|
super().__init__(message)
|
|
|
|
|
|
class ConversationNotFoundError(ResourceNotFoundError):
|
|
"""raised when Llama Stack cannot find a referenced conversation"""
|
|
|
|
def __init__(self, conversation_id: str) -> None:
|
|
super().__init__(conversation_id, "Conversation", "client.conversations.list()")
|
|
|
|
|
|
class InvalidConversationIdError(ValueError):
|
|
"""raised when a conversation ID has an invalid format"""
|
|
|
|
def __init__(self, conversation_id: str) -> None:
|
|
message = f"Invalid conversation ID '{conversation_id}'. Expected an ID that begins with 'conv_'."
|
|
super().__init__(message)
|