mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-11 05:38:38 +00:00

Composable building blocks to build Llama Apps https://llama-stack.readthedocs.io

Find a file

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
.github	fix(ci): remove responses from CI for now (#3773 )	2025-10-10 11:52:17 -07:00
benchmarking/k8s-benchmark	chore(perf): run guidellm benchmarks (#3421 )	2025-09-24 10:18:33 -07:00
docs	feat: Add support for Conversations in Responses API (#3743 )	2025-10-10 11:57:40 -07:00
llama_stack	feat: Add support for Conversations in Responses API (#3743 )	2025-10-10 11:57:40 -07:00
scripts	feat: use SecretStr for inference provider auth credentials (#3724 )	2025-10-10 07:32:50 -07:00
tests	feat: Add support for Conversations in Responses API (#3743 )	2025-10-10 11:57:40 -07:00
.coveragerc	test: Measure and track code coverage (#2636 )	2025-07-18 18:08:36 +02:00
.gitignore	docs: docusaurus setup (#3541 )	2025-09-24 14:11:30 -07:00
.pre-commit-config.yaml	fix: distro-codegen pre-commit hook file pattern (#3337 )	2025-09-04 17:56:32 +02:00
CHANGELOG.md	docs: Update changelog (#3343 )	2025-09-08 10:01:41 +02:00
CODE_OF_CONDUCT.md	Initial commit	2024-07-23 08:32:33 -07:00
CONTRIBUTING.md	docs: fix more broken links (#3649 )	2025-10-02 10:43:49 +02:00
coverage.svg	test: Measure and track code coverage (#2636 )	2025-07-18 18:08:36 +02:00
LICENSE	Update LICENSE (#47 )	2024-08-29 07:39:50 -07:00
MANIFEST.in	chore: MANIFEST maintenance (#3454 )	2025-09-27 11:28:11 -07:00
pyproject.toml	chore!: remove model mgmt from CLI for Hugging Face CLI (#3700 )	2025-10-09 16:50:33 -07:00
README.md	chore!: remove model mgmt from CLI for Hugging Face CLI (#3700 )	2025-10-09 16:50:33 -07:00
SECURITY.md	Create SECURITY.md	2024-10-08 13:30:40 -04:00
uv.lock	chore!: remove model mgmt from CLI for Hugging Face CLI (#3700 )	2025-10-09 16:50:33 -07:00

README.md

Llama Stack

Quick Start | Documentation | Colab Notebook | Discord

✨🎉 Llama 4 Support 🎉✨

We released Version 0.2.0 with support for the Llama 4 herd of models released by Meta.

👋 Click here to see how to run Llama 4 models on Llama Stack

Note you need 8xH100 GPU-host to run these models

pip install -U llama_stack

MODEL="Llama-4-Scout-17B-16E-Instruct"
# get meta url from llama.com
huggingface-cli download meta-llama/$MODEL --local-dir ~/.llama/$MODEL

# start a llama stack server
INFERENCE_MODEL=meta-llama/$MODEL llama stack build --run --template meta-reference-gpu

# install client to interact with the server
pip install llama-stack-client

CLI

# Run a chat completion
MODEL="Llama-4-Scout-17B-16E-Instruct"

llama-stack-client --endpoint http://localhost:8321 \
inference chat-completion \
--model-id meta-llama/$MODEL \
--message "write a haiku for meta's llama 4 models"

OpenAIChatCompletion(
    ...
    choices=[
        OpenAIChatCompletionChoice(
            finish_reason='stop',
            index=0,
            message=OpenAIChatCompletionChoiceMessageOpenAIAssistantMessageParam(
                role='assistant',
                content='...**Silent minds awaken,**  \n**Whispers of billions of words,**  \n**Reasoning breaks the night.**  \n\n—  \n*This haiku blends the essence of LLaMA 4\'s capabilities with nature-inspired metaphor, evoking its vast training data and transformative potential.*',
                ...
            ),
            ...
        )
    ],
    ...
)

Python SDK

from llama_stack_client import LlamaStackClient

client = LlamaStackClient(base_url=f"http://localhost:8321")

model_id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
prompt = "Write a haiku about coding"

print(f"User> {prompt}")
response = client.chat.completions.create(
    model=model_id,
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt},
    ],
)
print(f"Assistant> {response.choices[0].message.content}")

As more providers start supporting Llama 4, you can use them in Llama Stack as well. We are adding to the list. Stay tuned!

🚀 One-Line Installer 🚀

To try Llama Stack locally, run:

curl -LsSf https://github.com/meta-llama/llama-stack/raw/main/scripts/install.sh | bash

Overview

Llama Stack standardizes the core building blocks that simplify AI application development. It codifies best practices across the Llama ecosystem. More specifically, it provides

Unified API layer for Inference, RAG, Agents, Tools, Safety, Evals, and Telemetry.
Plugin architecture to support the rich ecosystem of different API implementations in various environments, including local development, on-premises, cloud, and mobile.
Prepackaged verified distributions which offer a one-stop solution for developers to get started quickly and reliably in any environment.
Multiple developer interfaces like CLI and SDKs for Python, Typescript, iOS, and Android.
Standalone applications as examples for how to build production-grade AI applications with Llama Stack.

Llama Stack Benefits

Flexible Options: Developers can choose their preferred infrastructure without changing APIs and enjoy flexible deployment choices.
Consistent Experience: With its unified APIs, Llama Stack makes it easier to build, test, and deploy AI applications with consistent application behavior.
Robust Ecosystem: Llama Stack is already integrated with distribution partners (cloud providers, hardware vendors, and AI-focused companies) that offer tailored infrastructure, software, and services for deploying Llama models.

By reducing friction and complexity, Llama Stack empowers developers to focus on what they do best: building transformative generative AI applications.

API Providers

Here is a list of the various API providers and available distributions that can help developers get started easily with Llama Stack. Please checkout for full list

API Provider Builder	Environments	Agents	Inference	VectorIO	Safety	Telemetry	Post Training	Eval	DatasetIO
Meta Reference	Single Node	✅	✅	✅	✅	✅	✅	✅	✅
SambaNova	Hosted		✅		✅
Cerebras	Hosted		✅
Fireworks	Hosted	✅	✅	✅
AWS Bedrock	Hosted		✅		✅
Together	Hosted	✅	✅		✅
Groq	Hosted		✅
Ollama	Single Node		✅
TGI	Hosted/Single Node		✅
NVIDIA NIM	Hosted/Single Node		✅		✅
ChromaDB	Hosted/Single Node			✅
Milvus	Hosted/Single Node			✅
Qdrant	Hosted/Single Node			✅
Weaviate	Hosted/Single Node			✅
SQLite-vec	Single Node			✅
PG Vector	Single Node			✅
PyTorch ExecuTorch	On-device iOS	✅	✅
vLLM	Single Node		✅
OpenAI	Hosted		✅
Anthropic	Hosted		✅
Gemini	Hosted		✅
WatsonX	Hosted		✅
HuggingFace	Single Node						✅		✅
TorchTune	Single Node						✅
NVIDIA NEMO	Hosted		✅	✅			✅	✅	✅
NVIDIA	Hosted						✅	✅	✅

Note

: Additional providers are available through external packages. See External Providers documentation.

Distributions

A Llama Stack Distribution (or "distro") is a pre-configured bundle of provider implementations for each API component. Distributions make it easy to get started with a specific deployment scenario - you can begin with a local development setup (eg. ollama) and seamlessly transition to production (eg. Fireworks) without changing your application code. Here are some of the distributions we support:

Distribution	Llama Stack Docker	Start This Distribution
Starter Distribution	llamastack/distribution-starter	Guide
Meta Reference	llamastack/distribution-meta-reference-gpu	Guide
PostgreSQL	llamastack/distribution-postgres-demo

Documentation

Please checkout our Documentation page for more details.

CLI references
- llama (server-side) CLI Reference: Guide for using the llama CLI to work with Llama models (download, study prompts), and building/starting a Llama Stack distribution.
- llama (client-side) CLI Reference: Guide for using the llama-stack-client CLI, which allows you to query information about the distribution.
Getting Started
- Quick guide to start a Llama Stack server.
- Jupyter notebook to walk-through how to use simple text and vision inference llama_stack_client APIs
- The complete Llama Stack lesson Colab notebook of the new Llama 3.2 course on Deeplearning.ai.
- A Zero-to-Hero Guide that guide you through all the key components of llama stack with code samples.
Contributing
- Adding a new API Provider to walk-through how to add a new API provider.

Llama Stack Client SDKs

Language	Client SDK	Package
Python	llama-stack-client-python
Swift	llama-stack-client-swift
Typescript	llama-stack-client-typescript
Kotlin	llama-stack-client-kotlin

Check out our client SDKs for connecting to a Llama Stack server in your preferred language, you can choose from python, typescript, swift, and kotlin programming languages to quickly build your applications.

You can find more example scripts with client SDKs to talk with the Llama Stack server in our llama-stack-apps repo.

🌟 GitHub Star History

Star History

✨ Contributors

Thanks to all of our amazing contributors!