diff --git a/distributions/dependencies.json b/distributions/dependencies.json index c3d643695..7b5d8b002 100644 --- a/distributions/dependencies.json +++ b/distributions/dependencies.json @@ -1,9 +1,43 @@ { - "bedrock": [ + "hf-serverless": [ + "aiohttp", + "aiosqlite", + "autoevals", + "blobfile", + "chardet", + "chromadb-client", + "datasets", + "faiss-cpu", + "fastapi", + "fire", + "httpx", + "huggingface_hub", + "matplotlib", + "mcp", + "nltk", + "numpy", + "openai", + "opentelemetry-exporter-otlp-proto-http", + "opentelemetry-sdk", + "pandas", + "pillow", + "psycopg2-binary", + "pypdf", + "redis", + "requests", + "scikit-learn", + "scipy", + "sentencepiece", + "tqdm", + "transformers", + "uvicorn", + "sentence-transformers --no-deps", + "torch --index-url https://download.pytorch.org/whl/cpu" + ], + "together": [ "aiosqlite", "autoevals", "blobfile", - "boto3", "chardet", "chromadb-client", "datasets", @@ -12,6 +46,75 @@ "fire", "httpx", "matplotlib", + "mcp", + "nltk", + "numpy", + "openai", + "opentelemetry-exporter-otlp-proto-http", + "opentelemetry-sdk", + "pandas", + "pillow", + "psycopg2-binary", + "pypdf", + "redis", + "requests", + "scikit-learn", + "scipy", + "sentencepiece", + "together", + "tqdm", + "transformers", + "uvicorn", + "sentence-transformers --no-deps", + "torch --index-url https://download.pytorch.org/whl/cpu" + ], + "vllm-gpu": [ + "aiosqlite", + "autoevals", + "blobfile", + "chardet", + "chromadb-client", + "datasets", + "faiss-cpu", + "fastapi", + "fire", + "httpx", + "matplotlib", + "mcp", + "nltk", + "numpy", + "openai", + "opentelemetry-exporter-otlp-proto-http", + "opentelemetry-sdk", + "pandas", + "pillow", + "psycopg2-binary", + "pypdf", + "redis", + "requests", + "scikit-learn", + "scipy", + "sentencepiece", + "tqdm", + "transformers", + "uvicorn", + "vllm", + "sentence-transformers --no-deps", + "torch --index-url https://download.pytorch.org/whl/cpu" + ], + "remote-vllm": [ + "aiosqlite", + "autoevals", + "blobfile", + "chardet", + "chromadb-client", + "datasets", + "faiss-cpu", + "fastapi", + "fire", + "httpx", + "matplotlib", + "mcp", "nltk", "numpy", "openai", @@ -45,6 +148,7 @@ "fireworks-ai", "httpx", "matplotlib", + "mcp", "nltk", "numpy", "openai", @@ -65,7 +169,7 @@ "sentence-transformers --no-deps", "torch --index-url https://download.pytorch.org/whl/cpu" ], - "hf-endpoint": [ + "tgi": [ "aiohttp", "aiosqlite", "autoevals", @@ -79,6 +183,7 @@ "httpx", "huggingface_hub", "matplotlib", + "mcp", "nltk", "numpy", "openai", @@ -99,11 +204,11 @@ "sentence-transformers --no-deps", "torch --index-url https://download.pytorch.org/whl/cpu" ], - "hf-serverless": [ - "aiohttp", + "bedrock": [ "aiosqlite", "autoevals", "blobfile", + "boto3", "chardet", "chromadb-client", "datasets", @@ -111,8 +216,8 @@ "fastapi", "fire", "httpx", - "huggingface_hub", "matplotlib", + "mcp", "nltk", "numpy", "openai", @@ -148,6 +253,7 @@ "httpx", "lm-format-enforcer", "matplotlib", + "mcp", "nltk", "numpy", "openai", @@ -172,6 +278,38 @@ "sentence-transformers --no-deps", "torch --index-url https://download.pytorch.org/whl/cpu" ], + "nvidia": [ + "aiosqlite", + "autoevals", + "blobfile", + "chardet", + "datasets", + "faiss-cpu", + "fastapi", + "fire", + "httpx", + "matplotlib", + "mcp", + "nltk", + "numpy", + "openai", + "opentelemetry-exporter-otlp-proto-http", + "opentelemetry-sdk", + "pandas", + "pillow", + "psycopg2-binary", + "pypdf", + "redis", + "requests", + "scikit-learn", + "scipy", + "sentencepiece", + "tqdm", + "transformers", + "uvicorn", + "sentence-transformers --no-deps", + "torch --index-url https://download.pytorch.org/whl/cpu" + ], "meta-reference-quantized-gpu": [ "accelerate", "aiosqlite", @@ -188,6 +326,7 @@ "httpx", "lm-format-enforcer", "matplotlib", + "mcp", "nltk", "numpy", "openai", @@ -213,6 +352,39 @@ "sentence-transformers --no-deps", "torch --index-url https://download.pytorch.org/whl/cpu" ], + "cerebras": [ + "aiosqlite", + "autoevals", + "blobfile", + "cerebras_cloud_sdk", + "chardet", + "chromadb-client", + "datasets", + "faiss-cpu", + "fastapi", + "fire", + "httpx", + "matplotlib", + "nltk", + "numpy", + "openai", + "opentelemetry-exporter-otlp-proto-http", + "opentelemetry-sdk", + "pandas", + "pillow", + "psycopg2-binary", + "pypdf", + "redis", + "requests", + "scikit-learn", + "scipy", + "sentencepiece", + "tqdm", + "transformers", + "uvicorn", + "sentence-transformers --no-deps", + "torch --index-url https://download.pytorch.org/whl/cpu" + ], "ollama": [ "aiohttp", "aiosqlite", @@ -247,7 +419,7 @@ "sentence-transformers --no-deps", "torch --index-url https://download.pytorch.org/whl/cpu" ], - "tgi": [ + "hf-endpoint": [ "aiohttp", "aiosqlite", "autoevals", @@ -261,168 +433,7 @@ "httpx", "huggingface_hub", "matplotlib", - "nltk", - "numpy", - "openai", - "opentelemetry-exporter-otlp-proto-http", - "opentelemetry-sdk", - "pandas", - "pillow", - "psycopg2-binary", - "pypdf", - "redis", - "requests", - "scikit-learn", - "scipy", - "sentencepiece", - "tqdm", - "transformers", - "uvicorn", - "sentence-transformers --no-deps", - "torch --index-url https://download.pytorch.org/whl/cpu" - ], - "together": [ - "aiosqlite", - "autoevals", - "blobfile", - "chardet", - "chromadb-client", - "datasets", - "faiss-cpu", - "fastapi", - "fire", - "httpx", - "matplotlib", - "nltk", - "numpy", - "openai", - "opentelemetry-exporter-otlp-proto-http", - "opentelemetry-sdk", - "pandas", - "pillow", - "psycopg2-binary", - "pypdf", - "redis", - "requests", - "scikit-learn", - "scipy", - "sentencepiece", - "together", - "tqdm", - "transformers", - "uvicorn", - "sentence-transformers --no-deps", - "torch --index-url https://download.pytorch.org/whl/cpu" - ], - "remote-vllm": [ - "aiosqlite", - "autoevals", - "blobfile", - "chardet", - "chromadb-client", - "datasets", - "faiss-cpu", - "fastapi", - "fire", - "httpx", - "matplotlib", - "nltk", - "numpy", - "openai", - "opentelemetry-exporter-otlp-proto-http", - "opentelemetry-sdk", - "pandas", - "pillow", - "psycopg2-binary", - "pypdf", - "redis", - "requests", - "scikit-learn", - "scipy", - "sentencepiece", - "tqdm", - "transformers", - "uvicorn", - "sentence-transformers --no-deps", - "torch --index-url https://download.pytorch.org/whl/cpu" - ], - "cerebras": [ - "aiosqlite", - "autoevals", - "blobfile", - "cerebras_cloud_sdk", - "chardet", - "chromadb-client", - "datasets", - "faiss-cpu", - "fastapi", - "fire", - "httpx", - "matplotlib", - "nltk", - "numpy", - "openai", - "opentelemetry-exporter-otlp-proto-http", - "opentelemetry-sdk", - "pandas", - "pillow", - "psycopg2-binary", - "pypdf", - "redis", - "requests", - "scikit-learn", - "scipy", - "sentencepiece", - "tqdm", - "transformers", - "uvicorn", - "sentence-transformers --no-deps", - "torch --index-url https://download.pytorch.org/whl/cpu" - ], - "vllm-gpu": [ - "aiosqlite", - "autoevals", - "blobfile", - "chardet", - "chromadb-client", - "datasets", - "faiss-cpu", - "fastapi", - "fire", - "httpx", - "matplotlib", - "nltk", - "numpy", - "openai", - "opentelemetry-exporter-otlp-proto-http", - "opentelemetry-sdk", - "pandas", - "pillow", - "psycopg2-binary", - "pypdf", - "redis", - "requests", - "scikit-learn", - "scipy", - "sentencepiece", - "tqdm", - "transformers", - "uvicorn", - "vllm", - "sentence-transformers --no-deps", - "torch --index-url https://download.pytorch.org/whl/cpu" - ], - "nvidia": [ - "aiosqlite", - "autoevals", - "blobfile", - "chardet", - "datasets", - "faiss-cpu", - "fastapi", - "fire", - "httpx", - "matplotlib", + "mcp", "nltk", "numpy", "openai", diff --git a/docs/source/distributions/remote_hosted_distro/nvidia.md b/docs/source/distributions/remote_hosted_distro/nvidia.md index 7e3446863..4028ed384 100644 --- a/docs/source/distributions/remote_hosted_distro/nvidia.md +++ b/docs/source/distributions/remote_hosted_distro/nvidia.md @@ -12,7 +12,7 @@ The `llamastack/distribution-nvidia` distribution consists of the following prov | safety | `inline::llama-guard` | | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | -| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` | +| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` | ### Environment Variables diff --git a/docs/source/distributions/self_hosted_distro/bedrock.md b/docs/source/distributions/self_hosted_distro/bedrock.md index 71adfad09..dd4e51264 100644 --- a/docs/source/distributions/self_hosted_distro/bedrock.md +++ b/docs/source/distributions/self_hosted_distro/bedrock.md @@ -19,7 +19,7 @@ The `llamastack/distribution-bedrock` distribution consists of the following pro | safety | `remote::bedrock` | | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | -| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` | +| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` | diff --git a/docs/source/distributions/self_hosted_distro/fireworks.md b/docs/source/distributions/self_hosted_distro/fireworks.md index 335309729..7ed174984 100644 --- a/docs/source/distributions/self_hosted_distro/fireworks.md +++ b/docs/source/distributions/self_hosted_distro/fireworks.md @@ -22,7 +22,7 @@ The `llamastack/distribution-fireworks` distribution consists of the following p | safety | `inline::llama-guard` | | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | -| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` | +| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` | ### Environment Variables diff --git a/docs/source/distributions/self_hosted_distro/meta-reference-gpu.md b/docs/source/distributions/self_hosted_distro/meta-reference-gpu.md index a89719dea..269354e98 100644 --- a/docs/source/distributions/self_hosted_distro/meta-reference-gpu.md +++ b/docs/source/distributions/self_hosted_distro/meta-reference-gpu.md @@ -22,7 +22,7 @@ The `llamastack/distribution-meta-reference-gpu` distribution consists of the fo | safety | `inline::llama-guard` | | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | -| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` | +| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` | Note that you need access to nvidia GPUs to run this distribution. This distribution is not compatible with CPU-only machines or machines with AMD GPUs. diff --git a/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md b/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md index 26ed5d05b..937dbbdbd 100644 --- a/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md +++ b/docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md @@ -22,7 +22,7 @@ The `llamastack/distribution-meta-reference-quantized-gpu` distribution consists | safety | `inline::llama-guard` | | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | -| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` | +| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` | The only difference vs. the `meta-reference-gpu` distribution is that it has support for more efficient inference -- with fp8, int4 quantization, etc. diff --git a/docs/source/distributions/self_hosted_distro/remote-vllm.md b/docs/source/distributions/self_hosted_distro/remote-vllm.md index 5b29c402f..2bb5329b9 100644 --- a/docs/source/distributions/self_hosted_distro/remote-vllm.md +++ b/docs/source/distributions/self_hosted_distro/remote-vllm.md @@ -21,7 +21,7 @@ The `llamastack/distribution-remote-vllm` distribution consists of the following | safety | `inline::llama-guard` | | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | -| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` | +| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` | You can use this distribution if you have GPUs and want to run an independent vLLM server container for running inference. diff --git a/docs/source/distributions/self_hosted_distro/tgi.md b/docs/source/distributions/self_hosted_distro/tgi.md index f4f705b12..0fd6a693c 100644 --- a/docs/source/distributions/self_hosted_distro/tgi.md +++ b/docs/source/distributions/self_hosted_distro/tgi.md @@ -23,7 +23,7 @@ The `llamastack/distribution-tgi` distribution consists of the following provide | safety | `inline::llama-guard` | | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | -| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` | +| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` | You can use this distribution if you have GPUs and want to run an independent TGI server container for running inference. diff --git a/docs/source/distributions/self_hosted_distro/together.md b/docs/source/distributions/self_hosted_distro/together.md index 3b476c9bf..e990e273f 100644 --- a/docs/source/distributions/self_hosted_distro/together.md +++ b/docs/source/distributions/self_hosted_distro/together.md @@ -22,7 +22,7 @@ The `llamastack/distribution-together` distribution consists of the following pr | safety | `inline::llama-guard` | | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | -| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime` | +| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::memory-runtime`, `remote::model-context-protocol` | ### Environment Variables diff --git a/llama_stack/templates/bedrock/bedrock.py b/llama_stack/templates/bedrock/bedrock.py index da792e461..668134be8 100644 --- a/llama_stack/templates/bedrock/bedrock.py +++ b/llama_stack/templates/bedrock/bedrock.py @@ -30,6 +30,7 @@ def get_distribution_template() -> DistributionTemplate: "remote::tavily-search", "inline::code-interpreter", "inline::memory-runtime", + "remote::model-context-protocol", ], } name = "bedrock" diff --git a/llama_stack/templates/bedrock/build.yaml b/llama_stack/templates/bedrock/build.yaml index 794e54306..95b8684e3 100644 --- a/llama_stack/templates/bedrock/build.yaml +++ b/llama_stack/templates/bedrock/build.yaml @@ -28,4 +28,5 @@ distribution_spec: - remote::tavily-search - inline::code-interpreter - inline::memory-runtime + - remote::model-context-protocol image_type: conda diff --git a/llama_stack/templates/bedrock/run.yaml b/llama_stack/templates/bedrock/run.yaml index 3a6922ae7..118723bbc 100644 --- a/llama_stack/templates/bedrock/run.yaml +++ b/llama_stack/templates/bedrock/run.yaml @@ -81,6 +81,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/registry.db diff --git a/llama_stack/templates/fireworks/build.yaml b/llama_stack/templates/fireworks/build.yaml index 504c913bd..d8e1e27ee 100644 --- a/llama_stack/templates/fireworks/build.yaml +++ b/llama_stack/templates/fireworks/build.yaml @@ -28,4 +28,5 @@ distribution_spec: - remote::tavily-search - inline::code-interpreter - inline::memory-runtime + - remote::model-context-protocol image_type: conda diff --git a/llama_stack/templates/fireworks/fireworks.py b/llama_stack/templates/fireworks/fireworks.py index c94074a70..14fd392c4 100644 --- a/llama_stack/templates/fireworks/fireworks.py +++ b/llama_stack/templates/fireworks/fireworks.py @@ -39,6 +39,7 @@ def get_distribution_template() -> DistributionTemplate: "remote::tavily-search", "inline::code-interpreter", "inline::memory-runtime", + "remote::model-context-protocol", ], } diff --git a/llama_stack/templates/fireworks/run-with-safety.yaml b/llama_stack/templates/fireworks/run-with-safety.yaml index 8fefbd98a..dd21120ed 100644 --- a/llama_stack/templates/fireworks/run-with-safety.yaml +++ b/llama_stack/templates/fireworks/run-with-safety.yaml @@ -92,6 +92,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/registry.db diff --git a/llama_stack/templates/fireworks/run.yaml b/llama_stack/templates/fireworks/run.yaml index 53128f456..993417b50 100644 --- a/llama_stack/templates/fireworks/run.yaml +++ b/llama_stack/templates/fireworks/run.yaml @@ -86,6 +86,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/registry.db diff --git a/llama_stack/templates/hf-endpoint/build.yaml b/llama_stack/templates/hf-endpoint/build.yaml index 43486030e..f4fdc4a3d 100644 --- a/llama_stack/templates/hf-endpoint/build.yaml +++ b/llama_stack/templates/hf-endpoint/build.yaml @@ -28,4 +28,5 @@ distribution_spec: - remote::tavily-search - inline::code-interpreter - inline::memory-runtime + - remote::model-context-protocol image_type: conda diff --git a/llama_stack/templates/hf-endpoint/hf_endpoint.py b/llama_stack/templates/hf-endpoint/hf_endpoint.py index 04e2a53b5..1a5c23a42 100644 --- a/llama_stack/templates/hf-endpoint/hf_endpoint.py +++ b/llama_stack/templates/hf-endpoint/hf_endpoint.py @@ -34,6 +34,7 @@ def get_distribution_template() -> DistributionTemplate: "remote::tavily-search", "inline::code-interpreter", "inline::memory-runtime", + "remote::model-context-protocol", ], } name = "hf-endpoint" diff --git a/llama_stack/templates/hf-endpoint/run-with-safety.yaml b/llama_stack/templates/hf-endpoint/run-with-safety.yaml index 6a52ca861..537e4024f 100644 --- a/llama_stack/templates/hf-endpoint/run-with-safety.yaml +++ b/llama_stack/templates/hf-endpoint/run-with-safety.yaml @@ -91,6 +91,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/registry.db diff --git a/llama_stack/templates/hf-endpoint/run.yaml b/llama_stack/templates/hf-endpoint/run.yaml index c019c587a..b31f28434 100644 --- a/llama_stack/templates/hf-endpoint/run.yaml +++ b/llama_stack/templates/hf-endpoint/run.yaml @@ -86,6 +86,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/registry.db diff --git a/llama_stack/templates/hf-serverless/build.yaml b/llama_stack/templates/hf-serverless/build.yaml index e1328bd58..d075a7449 100644 --- a/llama_stack/templates/hf-serverless/build.yaml +++ b/llama_stack/templates/hf-serverless/build.yaml @@ -28,4 +28,5 @@ distribution_spec: - remote::tavily-search - inline::code-interpreter - inline::memory-runtime + - remote::model-context-protocol image_type: conda diff --git a/llama_stack/templates/hf-serverless/hf_serverless.py b/llama_stack/templates/hf-serverless/hf_serverless.py index af8d77629..0292f13e2 100644 --- a/llama_stack/templates/hf-serverless/hf_serverless.py +++ b/llama_stack/templates/hf-serverless/hf_serverless.py @@ -34,6 +34,7 @@ def get_distribution_template() -> DistributionTemplate: "remote::tavily-search", "inline::code-interpreter", "inline::memory-runtime", + "remote::model-context-protocol", ], } diff --git a/llama_stack/templates/hf-serverless/run-with-safety.yaml b/llama_stack/templates/hf-serverless/run-with-safety.yaml index 0a64de358..484b2d0bd 100644 --- a/llama_stack/templates/hf-serverless/run-with-safety.yaml +++ b/llama_stack/templates/hf-serverless/run-with-safety.yaml @@ -91,6 +91,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/registry.db diff --git a/llama_stack/templates/hf-serverless/run.yaml b/llama_stack/templates/hf-serverless/run.yaml index f04213533..a75baf1f9 100644 --- a/llama_stack/templates/hf-serverless/run.yaml +++ b/llama_stack/templates/hf-serverless/run.yaml @@ -86,6 +86,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/registry.db diff --git a/llama_stack/templates/meta-reference-gpu/build.yaml b/llama_stack/templates/meta-reference-gpu/build.yaml index 9ad7b26bf..a75d3604b 100644 --- a/llama_stack/templates/meta-reference-gpu/build.yaml +++ b/llama_stack/templates/meta-reference-gpu/build.yaml @@ -28,4 +28,5 @@ distribution_spec: - remote::tavily-search - inline::code-interpreter - inline::memory-runtime + - remote::model-context-protocol image_type: conda diff --git a/llama_stack/templates/meta-reference-gpu/meta_reference.py b/llama_stack/templates/meta-reference-gpu/meta_reference.py index 7364ee422..584d38256 100644 --- a/llama_stack/templates/meta-reference-gpu/meta_reference.py +++ b/llama_stack/templates/meta-reference-gpu/meta_reference.py @@ -38,6 +38,7 @@ def get_distribution_template() -> DistributionTemplate: "remote::tavily-search", "inline::code-interpreter", "inline::memory-runtime", + "remote::model-context-protocol", ], } name = "meta-reference-gpu" diff --git a/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml b/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml index 591afa2be..9dbdb6fa5 100644 --- a/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml +++ b/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml @@ -93,6 +93,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/registry.db diff --git a/llama_stack/templates/meta-reference-gpu/run.yaml b/llama_stack/templates/meta-reference-gpu/run.yaml index ecde69fdf..6465215f0 100644 --- a/llama_stack/templates/meta-reference-gpu/run.yaml +++ b/llama_stack/templates/meta-reference-gpu/run.yaml @@ -87,6 +87,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/registry.db diff --git a/llama_stack/templates/meta-reference-quantized-gpu/build.yaml b/llama_stack/templates/meta-reference-quantized-gpu/build.yaml index e6b64ea1e..4c3e2f492 100644 --- a/llama_stack/templates/meta-reference-quantized-gpu/build.yaml +++ b/llama_stack/templates/meta-reference-quantized-gpu/build.yaml @@ -28,4 +28,5 @@ distribution_spec: - remote::tavily-search - inline::code-interpreter - inline::memory-runtime + - remote::model-context-protocol image_type: conda diff --git a/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py b/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py index 5c40134af..56293f42c 100644 --- a/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py +++ b/llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py @@ -33,6 +33,7 @@ def get_distribution_template() -> DistributionTemplate: "remote::tavily-search", "inline::code-interpreter", "inline::memory-runtime", + "remote::model-context-protocol", ], } default_tool_groups = [ diff --git a/llama_stack/templates/meta-reference-quantized-gpu/run.yaml b/llama_stack/templates/meta-reference-quantized-gpu/run.yaml index ff0affafb..059034741 100644 --- a/llama_stack/templates/meta-reference-quantized-gpu/run.yaml +++ b/llama_stack/templates/meta-reference-quantized-gpu/run.yaml @@ -89,6 +89,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/registry.db diff --git a/llama_stack/templates/nvidia/build.yaml b/llama_stack/templates/nvidia/build.yaml index 56124552b..7bd2a3865 100644 --- a/llama_stack/templates/nvidia/build.yaml +++ b/llama_stack/templates/nvidia/build.yaml @@ -26,4 +26,5 @@ distribution_spec: - remote::tavily-search - inline::code-interpreter - inline::memory-runtime + - remote::model-context-protocol image_type: conda diff --git a/llama_stack/templates/nvidia/nvidia.py b/llama_stack/templates/nvidia/nvidia.py index d5518ecc9..e72fe359f 100644 --- a/llama_stack/templates/nvidia/nvidia.py +++ b/llama_stack/templates/nvidia/nvidia.py @@ -29,6 +29,7 @@ def get_distribution_template() -> DistributionTemplate: "remote::tavily-search", "inline::code-interpreter", "inline::memory-runtime", + "remote::model-context-protocol", ], } diff --git a/llama_stack/templates/nvidia/run.yaml b/llama_stack/templates/nvidia/run.yaml index 578f70c9d..07c901371 100644 --- a/llama_stack/templates/nvidia/run.yaml +++ b/llama_stack/templates/nvidia/run.yaml @@ -83,6 +83,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db diff --git a/llama_stack/templates/remote-vllm/build.yaml b/llama_stack/templates/remote-vllm/build.yaml index 7398ab96d..6f301914c 100644 --- a/llama_stack/templates/remote-vllm/build.yaml +++ b/llama_stack/templates/remote-vllm/build.yaml @@ -28,4 +28,5 @@ distribution_spec: - remote::tavily-search - inline::code-interpreter - inline::memory-runtime + - remote::model-context-protocol image_type: conda diff --git a/llama_stack/templates/remote-vllm/run-with-safety.yaml b/llama_stack/templates/remote-vllm/run-with-safety.yaml index 9c030e8b2..5e5bd6af6 100644 --- a/llama_stack/templates/remote-vllm/run-with-safety.yaml +++ b/llama_stack/templates/remote-vllm/run-with-safety.yaml @@ -93,6 +93,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db diff --git a/llama_stack/templates/remote-vllm/run.yaml b/llama_stack/templates/remote-vllm/run.yaml index 053b254bd..4eac4dad7 100644 --- a/llama_stack/templates/remote-vllm/run.yaml +++ b/llama_stack/templates/remote-vllm/run.yaml @@ -87,6 +87,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db diff --git a/llama_stack/templates/remote-vllm/vllm.py b/llama_stack/templates/remote-vllm/vllm.py index 229d7f172..296e2b4f5 100644 --- a/llama_stack/templates/remote-vllm/vllm.py +++ b/llama_stack/templates/remote-vllm/vllm.py @@ -36,6 +36,7 @@ def get_distribution_template() -> DistributionTemplate: "remote::tavily-search", "inline::code-interpreter", "inline::memory-runtime", + "remote::model-context-protocol", ], } name = "remote-vllm" diff --git a/llama_stack/templates/tgi/build.yaml b/llama_stack/templates/tgi/build.yaml index 3bcacffb0..4391ddd5d 100644 --- a/llama_stack/templates/tgi/build.yaml +++ b/llama_stack/templates/tgi/build.yaml @@ -28,4 +28,5 @@ distribution_spec: - remote::tavily-search - inline::code-interpreter - inline::memory-runtime + - remote::model-context-protocol image_type: conda diff --git a/llama_stack/templates/tgi/run-with-safety.yaml b/llama_stack/templates/tgi/run-with-safety.yaml index 070daedc1..9bd06d650 100644 --- a/llama_stack/templates/tgi/run-with-safety.yaml +++ b/llama_stack/templates/tgi/run-with-safety.yaml @@ -86,6 +86,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/registry.db diff --git a/llama_stack/templates/tgi/run.yaml b/llama_stack/templates/tgi/run.yaml index e9696c584..2fc1b52d9 100644 --- a/llama_stack/templates/tgi/run.yaml +++ b/llama_stack/templates/tgi/run.yaml @@ -85,6 +85,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/registry.db diff --git a/llama_stack/templates/tgi/tgi.py b/llama_stack/templates/tgi/tgi.py index 02187f986..8ad9725e3 100644 --- a/llama_stack/templates/tgi/tgi.py +++ b/llama_stack/templates/tgi/tgi.py @@ -36,6 +36,7 @@ def get_distribution_template() -> DistributionTemplate: "remote::tavily-search", "inline::code-interpreter", "inline::memory-runtime", + "remote::model-context-protocol", ], } name = "tgi" diff --git a/llama_stack/templates/together/build.yaml b/llama_stack/templates/together/build.yaml index ad970f405..ea7387a24 100644 --- a/llama_stack/templates/together/build.yaml +++ b/llama_stack/templates/together/build.yaml @@ -28,4 +28,5 @@ distribution_spec: - remote::tavily-search - inline::code-interpreter - inline::memory-runtime + - remote::model-context-protocol image_type: conda diff --git a/llama_stack/templates/together/run-with-safety.yaml b/llama_stack/templates/together/run-with-safety.yaml index 4e162aab3..c1461d75d 100644 --- a/llama_stack/templates/together/run-with-safety.yaml +++ b/llama_stack/templates/together/run-with-safety.yaml @@ -92,6 +92,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/registry.db diff --git a/llama_stack/templates/together/run.yaml b/llama_stack/templates/together/run.yaml index 3c4844447..da25fd144 100644 --- a/llama_stack/templates/together/run.yaml +++ b/llama_stack/templates/together/run.yaml @@ -86,6 +86,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/registry.db diff --git a/llama_stack/templates/together/together.py b/llama_stack/templates/together/together.py index 28c01095a..1e2def3bd 100644 --- a/llama_stack/templates/together/together.py +++ b/llama_stack/templates/together/together.py @@ -39,6 +39,7 @@ def get_distribution_template() -> DistributionTemplate: "remote::tavily-search", "inline::code-interpreter", "inline::memory-runtime", + "remote::model-context-protocol", ], } name = "together" diff --git a/llama_stack/templates/vllm-gpu/build.yaml b/llama_stack/templates/vllm-gpu/build.yaml index e068fa97e..e8a1693d0 100644 --- a/llama_stack/templates/vllm-gpu/build.yaml +++ b/llama_stack/templates/vllm-gpu/build.yaml @@ -28,4 +28,5 @@ distribution_spec: - remote::tavily-search - inline::code-interpreter - inline::memory-runtime + - remote::model-context-protocol image_type: conda diff --git a/llama_stack/templates/vllm-gpu/run.yaml b/llama_stack/templates/vllm-gpu/run.yaml index 1cb44b052..cc0ff047f 100644 --- a/llama_stack/templates/vllm-gpu/run.yaml +++ b/llama_stack/templates/vllm-gpu/run.yaml @@ -89,6 +89,9 @@ providers: - provider_id: memory-runtime provider_type: inline::memory-runtime config: {} + - provider_id: model-context-protocol + provider_type: remote::model-context-protocol + config: {} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/registry.db diff --git a/llama_stack/templates/vllm-gpu/vllm.py b/llama_stack/templates/vllm-gpu/vllm.py index 1f3cf4b35..71b24482d 100644 --- a/llama_stack/templates/vllm-gpu/vllm.py +++ b/llama_stack/templates/vllm-gpu/vllm.py @@ -33,6 +33,7 @@ def get_distribution_template() -> DistributionTemplate: "remote::tavily-search", "inline::code-interpreter", "inline::memory-runtime", + "remote::model-context-protocol", ], }