forked from phoenix-oss/llama-stack-mirror

Composable building blocks to build Llama Apps

Find a file

Sébastien Han 369cc513cb fix: improve stack build on venv (#980 ) # What does this PR do? Added a pre_run_checks function to ensure a smooth environment setup by verifying prerequisites. It checks for an existing virtual environment, ensures uv is installed, and deactivates any active environment if necessary. Run the full build inside a venv created by 'uv'. Improved string handling in printf statements and added shellcheck suppressions for expected word splitting in pip commands. These enhancements improve robustness, prevent conflicts, and ensure a seamless setup process. Signed-off-by: Sébastien Han <seb@redhat.com> - [ ] Addresses issue (#issue) ## Test Plan Run the following command on either Linux or MacOS: ``` llama stack build --template ollama --image-type venv --image-name foo + build_name=foo + env_name=llamastack-foo + pip_dependencies='datasets matplotlib autoevals transformers blobfile opentelemetry-sdk sentencepiece opentelemetry-exporter-otlp-proto-http ollama nltk redis pillow psycopg2-binary scikit-learn pandas faiss-cpu chromadb-client numpy chardet scipy aiohttp aiosqlite requests tqdm pypdf openai aiosqlite fastapi fire httpx uvicorn' + RED='\033[0;31m' + NC='\033[0m' + ENVNAME= +++ readlink -f /Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/build_venv.sh ++ dirname /Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/build_venv.sh + SCRIPT_DIR=/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution + source /Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/common.sh + pre_run_checks llamastack-foo + local env_name=llamastack-foo + is_command_available uv + command -v uv + '[' -d llamastack-foo ']' + run llamastack-foo 'datasets matplotlib autoevals transformers blobfile opentelemetry-sdk sentencepiece opentelemetry-exporter-otlp-proto-http ollama nltk redis pillow psycopg2-binary scikit-learn pandas faiss-cpu chromadb-client numpy chardet scipy aiohttp aiosqlite requests tqdm pypdf openai aiosqlite fastapi fire httpx uvicorn' 'sentence-transformers --no-deps#torch torchvision --index-url https://download.pytorch.org/whl/cpu' + local env_name=llamastack-foo + local 'pip_dependencies=datasets matplotlib autoevals transformers blobfile opentelemetry-sdk sentencepiece opentelemetry-exporter-otlp-proto-http ollama nltk redis pillow psycopg2-binary scikit-learn pandas faiss-cpu chromadb-client numpy chardet scipy aiohttp aiosqlite requests tqdm pypdf openai aiosqlite fastapi fire httpx uvicorn' + local 'special_pip_deps=sentence-transformers --no-deps#torch torchvision --index-url https://download.pytorch.org/whl/cpu' + echo 'Creating new virtual environment llamastack-foo' Creating new virtual environment llamastack-foo + uv venv llamastack-foo Using CPython 3.13.1 interpreter at: /opt/homebrew/opt/python@3.13/bin/python3.13 Creating virtual environment at: llamastack-foo Activate with: source llamastack-foo/bin/activate + source llamastack-foo/bin/activate ++ '[' -n x ']' ++ SCRIPT_PATH=llamastack-foo/bin/activate ++ '[' llamastack-foo/bin/activate = /Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/build_venv.sh ']' ++ deactivate nondestructive ++ unset -f pydoc ++ '[' -z '' ']' ++ '[' -z '' ']' ++ hash -r ++ '[' -z '' ']' ++ unset VIRTUAL_ENV ++ unset VIRTUAL_ENV_PROMPT ++ '[' '!' nondestructive = nondestructive ']' ++ VIRTUAL_ENV=/Users/leseb/Documents/AI/llama-stack/llamastack-foo ++ '[' darwin24 = cygwin ']' ++ '[' darwin24 = msys ']' ++ export VIRTUAL_ENV ++ _OLD_VIRTUAL_PATH='/Users/leseb/Documents/AI/llama-stack/.venv/bin:/opt/homebrew/opt/protobuf@21/bin:/opt/homebrew/opt/gnu-sed/libexec/gnubin:/opt/homebrew/bin:/opt/homebrew/sbin:/usr/local/bin:/System/Cryptexes/App/usr/bin:/usr/bin:/bin:/usr/sbin:/sbin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/local/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/appleinternal/bin:/usr/local/munki:/opt/podman/bin:/opt/homebrew/opt/protobuf@21/bin:/opt/homebrew/opt/gnu-sed/libexec/gnubin:/Users/leseb/.local/share/zinit/plugins/so-fancy---diff-so-fancy:/Users/leseb/.local/share/zinit/polaris/bin:/Users/leseb/.cargo/bin:/Users/leseb/Library/Application Support/Code/User/globalStorage/github.copilot-chat/debugCommand' ++ PATH='/Users/leseb/Documents/AI/llama-stack/llamastack-foo/bin:/Users/leseb/Documents/AI/llama-stack/.venv/bin:/opt/homebrew/opt/protobuf@21/bin:/opt/homebrew/opt/gnu-sed/libexec/gnubin:/opt/homebrew/bin:/opt/homebrew/sbin:/usr/local/bin:/System/Cryptexes/App/usr/bin:/usr/bin:/bin:/usr/sbin:/sbin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/local/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/appleinternal/bin:/usr/local/munki:/opt/podman/bin:/opt/homebrew/opt/protobuf@21/bin:/opt/homebrew/opt/gnu-sed/libexec/gnubin:/Users/leseb/.local/share/zinit/plugins/so-fancy---diff-so-fancy:/Users/leseb/.local/share/zinit/polaris/bin:/Users/leseb/.cargo/bin:/Users/leseb/Library/Application Support/Code/User/globalStorage/github.copilot-chat/debugCommand' ++ export PATH ++ '[' x '!=' x ']' +++ basename /Users/leseb/Documents/AI/llama-stack/llamastack-foo ++ VIRTUAL_ENV_PROMPT='(llamastack-foo) ' ++ export VIRTUAL_ENV_PROMPT ++ '[' -z '' ']' ++ '[' -z '' ']' ++ _OLD_VIRTUAL_PS1= ++ PS1='(llamastack-foo) ' ++ export PS1 ++ alias pydoc ++ true ++ hash -r + '[' -n '' ']' + '[' -n '' ']' + uv pip install --no-cache-dir llama-stack Using Python 3.13.1 environment at: llamastack-foo Resolved 50 packages in 1.25s Built fire==0.7.0 Prepared 50 packages in 1.22s Installed 50 packages in 126ms + annotated-types==0.7.0 + anyio==4.8.0 + blobfile==3.0.0 + certifi==2025.1.31 + charset-normalizer==3.4.1 + click==8.1.8 + distro==1.9.0 + filelock==3.17.0 + fire==0.7.0 + fsspec==2025.2.0 + h11==0.14.0 + httpcore==1.0.7 + httpx==0.28.1 + huggingface-hub==0.28.1 + idna==3.10 + jinja2==3.1.5 + llama-models==0.1.2 + llama-stack==0.1.2 + llama-stack-client==0.1.2 + lxml==5.3.1 + markdown-it-py==3.0.0 + markupsafe==3.0.2 + mdurl==0.1.2 + numpy==2.2.2 + packaging==24.2 + pandas==2.2.3 + pillow==11.1.0 + prompt-toolkit==3.0.50 + pyaml==25.1.0 + pycryptodomex==3.21.0 + pydantic==2.10.6 + pydantic-core==2.27.2 + pygments==2.19.1 + python-dateutil==2.9.0.post0 + python-dotenv==1.0.1 + pytz==2025.1 + pyyaml==6.0.2 + regex==2024.11.6 + requests==2.32.3 + rich==13.9.4 + setuptools==75.8.0 + six==1.17.0 + sniffio==1.3.1 + termcolor==2.5.0 + tiktoken==0.8.0 + tqdm==4.67.1 + typing-extensions==4.12.2 + tzdata==2025.1 + urllib3==2.3.0 + wcwidth==0.2.13 + '[' -n '' ']' + printf 'Installing pip dependencies\n' Installing pip dependencies + uv pip install datasets matplotlib autoevals transformers blobfile opentelemetry-sdk sentencepiece opentelemetry-exporter-otlp-proto-http ollama nltk redis pillow psycopg2-binary scikit-learn pandas faiss-cpu chromadb-client numpy chardet scipy aiohttp aiosqlite requests tqdm pypdf openai aiosqlite fastapi fire httpx uvicorn Using Python 3.13.1 environment at: llamastack-foo Resolved 105 packages in 37ms Uninstalled 2 packages in 65ms Installed 72 packages in 195ms + aiohappyeyeballs==2.4.6 + aiohttp==3.11.12 + aiosignal==1.3.2 + aiosqlite==0.21.0 + attrs==25.1.0 + autoevals==0.0.119 + backoff==2.2.1 + braintrust-core==0.0.58 + chardet==5.2.0 + chevron==0.14.0 + chromadb-client==0.6.3 + contourpy==1.3.1 + cycler==0.12.1 + datasets==3.2.0 + deprecated==1.2.18 + dill==0.3.8 + faiss-cpu==1.10.0 + fastapi==0.115.8 + fonttools==4.56.0 + frozenlist==1.5.0 - fsspec==2025.2.0 + fsspec==2024.9.0 + googleapis-common-protos==1.66.0 + grpcio==1.70.0 + importlib-metadata==8.5.0 + jiter==0.8.2 + joblib==1.4.2 + jsonschema==4.23.0 + jsonschema-specifications==2024.10.1 + kiwisolver==1.4.8 + levenshtein==0.26.1 + matplotlib==3.10.0 + monotonic==1.6 + multidict==6.1.0 + multiprocess==0.70.16 + nltk==3.9.1 - numpy==2.2.2 + numpy==1.26.4 + ollama==0.4.7 + openai==1.61.1 + opentelemetry-api==1.30.0 + opentelemetry-exporter-otlp-proto-common==1.30.0 + opentelemetry-exporter-otlp-proto-grpc==1.30.0 + opentelemetry-exporter-otlp-proto-http==1.30.0 + opentelemetry-proto==1.30.0 + opentelemetry-sdk==1.30.0 + opentelemetry-semantic-conventions==0.51b0 + orjson==3.10.15 + overrides==7.7.0 + posthog==3.12.0 + propcache==0.2.1 + protobuf==5.29.3 + psycopg2-binary==2.9.10 + pyarrow==19.0.0 + pyparsing==3.2.1 + pypdf==5.3.0 + rapidfuzz==3.12.1 + redis==5.2.1 + referencing==0.36.2 + rpds-py==0.22.3 + safetensors==0.5.2 + scikit-learn==1.6.1 + scipy==1.15.1 + sentencepiece==0.2.0 + starlette==0.45.3 + tenacity==9.0.0 + threadpoolctl==3.5.0 + tokenizers==0.21.0 + transformers==4.48.3 + uvicorn==0.34.0 + wrapt==1.17.2 + xxhash==3.5.0 + yarl==1.18.3 + zipp==3.21.0 + '[' -n 'sentence-transformers --no-deps#torch torchvision --index-url https://download.pytorch.org/whl/cpu' ']' + IFS='#' + read -ra parts + for part in '"${parts[@]}"' + echo 'sentence-transformers --no-deps' sentence-transformers --no-deps + uv pip install sentence-transformers --no-deps Using Python 3.13.1 environment at: llamastack-foo Resolved 1 package in 141ms Installed 1 package in 6ms + sentence-transformers==3.4.1 + for part in '"${parts[@]}"' + echo 'torch torchvision --index-url https://download.pytorch.org/whl/cpu' torch torchvision --index-url https://download.pytorch.org/whl/cpu + uv pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu Using Python 3.13.1 environment at: llamastack-foo Resolved 13 packages in 2.15s Installed 5 packages in 324ms + mpmath==1.3.0 + networkx==3.3 + sympy==1.13.1 + torch==2.6.0 + torchvision==0.21.0 Build Successful! ``` Run: ``` $ source llamastack-foo/bin/activate $ INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" OLLAMA_INFERENCE_MODEL="llama3.2:3b-instruct-fp16" python -m llama_stack.distribution.server.server --yaml-config ./llama_stack/templates/ollama/run.yaml --port 5001 Using config file: llama_stack/templates/ollama/run.yaml Run configuration: apis: - agents - datasetio - eval - inference - safety - scoring - telemetry - tool_runtime - vector_io container_image: null datasets: [] eval_tasks: [] image_name: ollama metadata_store: db_path: /Users/leseb/.llama/distributions/ollama/registry.db namespace: null type: sqlite models: - metadata: {} model_id: meta-llama/Llama-3.2-3B-Instruct model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType - llm provider_id: ollama provider_model_id: null - metadata: embedding_dimension: 384 model_id: all-MiniLM-L6-v2 model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType - embedding provider_id: sentence-transformers provider_model_id: null providers: agents: - config: persistence_store: db_path: /Users/leseb/.llama/distributions/ollama/agents_store.db namespace: null type: sqlite provider_id: meta-reference provider_type: inline::meta-reference datasetio: - config: {} provider_id: huggingface provider_type: remote::huggingface - config: {} provider_id: localfs provider_type: inline::localfs eval: - config: {} provider_id: meta-reference provider_type: inline::meta-reference inference: - config: url: http://localhost:11434 provider_id: ollama provider_type: remote::ollama - config: {} provider_id: sentence-transformers provider_type: inline::sentence-transformers safety: - config: {} provider_id: llama-guard provider_type: inline::llama-guard scoring: - config: {} provider_id: basic provider_type: inline::basic - config: {} provider_id: llm-as-judge provider_type: inline::llm-as-judge - config: openai_api_key: '******' provider_id: braintrust provider_type: inline::braintrust telemetry: - config: service_name: llama-stack sinks: console,sqlite sqlite_db_path: /Users/leseb/.llama/distributions/ollama/trace_store.db provider_id: meta-reference provider_type: inline::meta-reference tool_runtime: - config: api_key: '****' max_results: 3 provider_id: brave-search provider_type: remote::brave-search - config: api_key: '******' max_results: 3 provider_id: tavily-search provider_type: remote::tavily-search - config: {} provider_id: code-interpreter provider_type: inline::code-interpreter - config: {} provider_id: rag-runtime provider_type: inline::rag-runtime vector_io: - config: kvstore: db_path: /Users/leseb/.llama/distributions/ollama/faiss_store.db namespace: null type: sqlite provider_id: faiss provider_type: inline::faiss scoring_fns: [] server: port: 8321 tls_certfile: null tls_keyfile: null shields: [] tool_groups: - args: null mcp_endpoint: null provider_id: tavily-search toolgroup_id: builtin::websearch - args: null mcp_endpoint: null provider_id: rag-runtime toolgroup_id: builtin::rag - args: null mcp_endpoint: null provider_id: code-interpreter toolgroup_id: builtin::code_interpreter vector_dbs: [] version: '2' Warning: `bwrap` is not available. Code interpreter tool will not work correctly. modules.json: 100%\|███████████████████████████████████████████████████████████\| 349/349 [00:00<00:00, 485kB/s] config_sentence_transformers.json: 100%\|██████████████████████████████████████\| 116/116 [00:00<00:00, 498kB/s] README.md: 100%\|█████████████████████████████████████████████████████████\| 10.7k/10.7k [00:00<00:00, 20.5MB/s] sentence_bert_config.json: 100%\|████████████████████████████████████████████\| 53.0/53.0 [00:00<00:00, 583kB/s] config.json: 100%\|███████████████████████████████████████████████████████████\| 612/612 [00:00<00:00, 4.63MB/s] model.safetensors: 100%\|█████████████████████████████████████████████████\| 90.9M/90.9M [00:02<00:00, 36.6MB/s] tokenizer_config.json: 100%\|█████████████████████████████████████████████████\| 350/350 [00:00<00:00, 4.27MB/s] vocab.txt: 100%\|███████████████████████████████████████████████████████████\| 232k/232k [00:00<00:00, 1.90MB/s] tokenizer.json: 100%\|██████████████████████████████████████████████████████\| 466k/466k [00:00<00:00, 2.23MB/s] special_tokens_map.json: 100%\|███████████████████████████████████████████████\| 112/112 [00:00<00:00, 1.47MB/s] 1_Pooling/config.json: 100%\|██████████████████████████████████████████████████\| 190/190 [00:00<00:00, 841kB/s] Serving API tool_groups GET /v1/tools/{tool_name} GET /v1/toolgroups/{toolgroup_id} GET /v1/toolgroups GET /v1/tools POST /v1/toolgroups DELETE /v1/toolgroups/{toolgroup_id} Serving API tool_runtime POST /v1/tool-runtime/invoke GET /v1/tool-runtime/list-tools POST /v1/tool-runtime/rag-tool/insert POST /v1/tool-runtime/rag-tool/query Serving API vector_io POST /v1/vector-io/insert POST /v1/vector-io/query Serving API telemetry GET /v1/telemetry/traces/{trace_id}/spans/{span_id} GET /v1/telemetry/spans/{span_id}/tree GET /v1/telemetry/traces/{trace_id} POST /v1/telemetry/events GET /v1/telemetry/spans GET /v1/telemetry/traces POST /v1/telemetry/spans/export Serving API models GET /v1/models/{model_id} GET /v1/models POST /v1/models DELETE /v1/models/{model_id} Serving API eval POST /v1/eval/tasks/{task_id}/evaluations DELETE /v1/eval/tasks/{task_id}/jobs/{job_id} GET /v1/eval/tasks/{task_id}/jobs/{job_id}/result GET /v1/eval/tasks/{task_id}/jobs/{job_id} POST /v1/eval/tasks/{task_id}/jobs Serving API datasets GET /v1/datasets/{dataset_id} GET /v1/datasets POST /v1/datasets DELETE /v1/datasets/{dataset_id} Serving API scoring_functions GET /v1/scoring-functions/{scoring_fn_id} GET /v1/scoring-functions POST /v1/scoring-functions Serving API inspect GET /v1/health GET /v1/inspect/providers GET /v1/inspect/routes GET /v1/version Serving API scoring POST /v1/scoring/score POST /v1/scoring/score-batch Serving API shields GET /v1/shields/{identifier} GET /v1/shields POST /v1/shields Serving API vector_dbs GET /v1/vector-dbs/{vector_db_id} GET /v1/vector-dbs POST /v1/vector-dbs DELETE /v1/vector-dbs/{vector_db_id} Serving API eval_tasks GET /v1/eval-tasks/{eval_task_id} GET /v1/eval-tasks POST /v1/eval-tasks Serving API agents POST /v1/agents POST /v1/agents/{agent_id}/session POST /v1/agents/{agent_id}/session/{session_id}/turn DELETE /v1/agents/{agent_id} DELETE /v1/agents/{agent_id}/session/{session_id} GET /v1/agents/{agent_id}/session/{session_id} GET /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id} GET /v1/agents/{agent_id}/session/{session_id}/turn/{turn_id} Serving API inference POST /v1/inference/chat-completion POST /v1/inference/completion POST /v1/inference/embeddings Serving API datasetio POST /v1/datasetio/rows GET /v1/datasetio/rows Serving API safety POST /v1/safety/run-shield Listening on ['::', '0.0.0.0']:5001 INFO: Started server process [39145] INFO: Waiting for application startup. INFO: ASGI 'lifespan' protocol appears unsupported. INFO: Application startup complete. INFO: Uvicorn running on http://['::', '0.0.0.0']:5001 (Press CTRL+C to quit) ``` ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests. Signed-off-by: Sébastien Han <seb@redhat.com>		2025-02-14 09:22:03 -08:00
.github	docs: remove changelog mention from PR template (#1049 )	2025-02-11 13:24:53 -05:00
distributions	fix: Gaps in doc codegen (#1035 )	2025-02-10 13:24:15 -08:00
docs	fix: enable_session_persistence in AgentConfig should be optional (#1012 )	2025-02-14 09:19:53 -08:00
llama_stack	fix: improve stack build on venv (#980 )	2025-02-14 09:22:03 -08:00
rfcs	docs: Fix url to the llama-stack-spec yaml/html files (#1081 )	2025-02-13 12:39:26 -08:00
tests/client-sdk	chore: move all Llama Stack types from llama-models to llama-stack (#1098 )	2025-02-14 09:10:59 -08:00
.gitignore	github: ignore non-hidden python virtual environments (#939 )	2025-02-03 11:53:05 -08:00
.gitmodules	`impls` -> `inline`, `adapters` -> `remote` (#381 )	2024-11-06 14:54:05 -08:00
.pre-commit-config.yaml	chore: move all Llama Stack types from llama-models to llama-stack (#1098 )	2025-02-14 09:10:59 -08:00
.readthedocs.yaml	first version of readthedocs (#278 )	2024-10-22 10:15:58 +05:30
CODE_OF_CONDUCT.md	Initial commit	2024-07-23 08:32:33 -07:00
CONTRIBUTING.md	docs: Mention convential commits format in CONTRIBUTING.md (#1075 )	2025-02-13 10:57:30 -05:00
LICENSE	Update LICENSE (#47 )	2024-08-29 07:39:50 -07:00
MANIFEST.in	Move to use pyproject.toml so it is uv compatible	2025-01-31 21:28:08 -08:00
pyproject.toml	chore: move all Llama Stack types from llama-models to llama-stack (#1098 )	2025-02-14 09:10:59 -08:00
README.md	docs: Updating wording and nits in the README.md (#992 )	2025-02-11 09:53:26 -05:00
requirements.txt	chore: move all Llama Stack types from llama-models to llama-stack (#1098 )	2025-02-14 09:10:59 -08:00
SECURITY.md	Create SECURITY.md	2024-10-08 13:30:40 -04:00
uv.lock	chore: move all Llama Stack types from llama-models to llama-stack (#1098 )	2025-02-14 09:10:59 -08:00

README.md

Llama Stack

Quick Start | Documentation | Colab Notebook

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.

API Provider Builder	Environments	Agents	Inference	Memory	Safety	Telemetry
Meta Reference	Single Node	✅	✅	✅	✅	✅
SambaNova	Hosted		✅
Cerebras	Hosted		✅
Fireworks	Hosted	✅	✅	✅
AWS Bedrock	Hosted		✅		✅
Together	Hosted	✅	✅		✅
Groq	Hosted		✅
Ollama	Single Node		✅
TGI	Hosted and Single Node		✅
NVIDIA NIM	Hosted and Single Node		✅
Chroma	Single Node			✅
PG Vector	Single Node			✅
PyTorch ExecuTorch	On-device iOS	✅	✅
vLLM	Hosted and Single Node		✅

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
Meta Reference	llamastack/distribution-meta-reference-gpu	Guide
Meta Reference Quantized	llamastack/distribution-meta-reference-quantized-gpu	Guide
SambaNova	llamastack/distribution-sambanova	Guide
Cerebras	llamastack/distribution-cerebras	Guide
Ollama	llamastack/distribution-ollama	Guide
TGI	llamastack/distribution-tgi	Guide
Together	llamastack/distribution-together	Guide
Fireworks	llamastack/distribution-fireworks	Guide
vLLM	llamastack/distribution-remote-vllm	Guide

Installation

You have two ways to install this repository:

Install as a package: You can install the repository directly from PyPI by running the following command:
```
pip install llama-stack
```

Install from source: If you prefer to install from the source code, make sure you have conda installed. Then, run the following commands:

 mkdir -p ~/local
 cd ~/local
 git clone git@github.com:meta-llama/llama-stack.git

 conda create -n stack python=3.10
 conda activate stack

 cd llama-stack
 pip install -e .

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.