provider codegen fixes

docs/docs/providers/agents/index.mdx

@@ -1,7 +1,13 @@
 ---
-description: Available providers for the agents API
+description: "Agents API for creating and interacting with agentic systems.
-sidebar_label: Overview
+
-sidebar_position: 1
+    Main functionalities provided by this API:
+    - Create agents with specific instructions and ability to use tools.
+    - Interactions with agents are grouped into sessions (\"threads\"), and each interaction is called a \"turn\".
+    - Agents can be provided with various tools (see the ToolGroups and ToolRuntime APIs for more details).
+    - Agents can be provided with various shields (see the Safety API for more details).
+    - Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details."
+sidebar_label: Agents
 title: Agents
 ---
 
@@ -22,4 +28,4 @@ This section contains documentation for all available providers for the **agents
 
 ## Providers
 
-- **[Meta Reference](./inline_meta-reference)** - Inline provider
+- [Meta-Reference](./inline_meta-reference)

docs/docs/providers/agents/inline_meta-reference.mdx

@@ -1,8 +1,6 @@
 ---
-description: Meta's reference implementation of an agent system that can use tools,
+description: "Meta's reference implementation of an agent system that can use tools, access vector databases, and perform complex reasoning tasks."
-  access vector databases, and perform complex reasoning tasks
+sidebar_label: Meta-Reference
-sidebar_label: Meta Reference
-sidebar_position: 2
 title: inline::meta-reference
 ---
 

docs/docs/providers/batches/index.mdx

@@ -1,7 +1,15 @@
 ---
-description: Available providers for the batches API
+description: "The Batches API enables efficient processing of multiple requests in a single operation,
-sidebar_label: Overview
+    particularly useful for processing large datasets, batch evaluation workflows, and
-sidebar_position: 1
+    cost-effective inference at scale.
+
+    The API is designed to allow use of openai client libraries for seamless integration.
+
+    This API provides the following extensions:
+     - idempotent batch creation
+
+    Note: This API is currently under active development and may undergo changes."
+sidebar_label: Batches
 title: Batches
 ---
 
@@ -24,4 +32,4 @@ This section contains documentation for all available providers for the **batche
 
 ## Providers
 
-- **[Reference](./inline_reference)** - Inline provider
+- [Reference](./inline_reference)

docs/docs/providers/batches/inline_reference.mdx

@@ -1,7 +1,6 @@
 ---
-description: Reference implementation of batches API with KVStore persistence
+description: "Reference implementation of batches API with KVStore persistence."
 sidebar_label: Reference
-sidebar_position: 2
 title: inline::reference
 ---
 

docs/docs/providers/datasetio/index.mdx

@@ -1,7 +1,5 @@
 ---
-description: Available providers for the datasetio API
+sidebar_label: Datasetio
-sidebar_label: Overview
-sidebar_position: 1
 title: Datasetio
 ---
 
@@ -13,6 +11,6 @@ This section contains documentation for all available providers for the **datase
 
 ## Providers
 
-- **[Localfs](./inline_localfs)** - Inline provider
+- [Localfs](./inline_localfs)
-- **[Huggingface](./remote_huggingface)** - Remote provider
+- [Remote - Huggingface](./remote_huggingface)
-- **[Nvidia](./remote_nvidia)** - Remote provider
+- [Remote - Nvidia](./remote_nvidia)

docs/docs/providers/datasetio/inline_localfs.mdx

@@ -1,8 +1,6 @@
 ---
-description: Local filesystem-based dataset I/O provider for reading and writing datasets
+description: "Local filesystem-based dataset I/O provider for reading and writing datasets to local storage."
-  to local storage
 sidebar_label: Localfs
-sidebar_position: 2
 title: inline::localfs
 ---
 

docs/docs/providers/datasetio/remote_huggingface.mdx

@@ -1,8 +1,6 @@
 ---
-description: HuggingFace datasets provider for accessing and managing datasets from
+description: "HuggingFace datasets provider for accessing and managing datasets from the HuggingFace Hub."
-  the HuggingFace Hub
+sidebar_label: Remote - Huggingface
-sidebar_label: Huggingface
-sidebar_position: 3
 title: remote::huggingface
 ---
 

docs/docs/providers/datasetio/remote_nvidia.mdx

@@ -1,8 +1,6 @@
 ---
-description: NVIDIA's dataset I/O provider for accessing datasets from NVIDIA's data
+description: "NVIDIA's dataset I/O provider for accessing datasets from NVIDIA's data platform."
-  platform
+sidebar_label: Remote - Nvidia
-sidebar_label: Nvidia
-sidebar_position: 4
 title: remote::nvidia
 ---
 

docs/docs/providers/eval/index.mdx

@@ -1,7 +1,6 @@
 ---
-description: Available providers for the eval API
+description: "Llama Stack Evaluation API for running evaluations on model and agent candidates."
-sidebar_label: Overview
+sidebar_label: Eval
-sidebar_position: 1
 title: Eval
 ---
 
@@ -15,5 +14,5 @@ This section contains documentation for all available providers for the **eval**
 
 ## Providers
 
-- **[Meta Reference](./inline_meta-reference)** - Inline provider
+- [Meta-Reference](./inline_meta-reference)
-- **[Nvidia](./remote_nvidia)** - Remote provider
+- [Remote - Nvidia](./remote_nvidia)

docs/docs/providers/eval/inline_meta-reference.mdx

@@ -1,8 +1,6 @@
 ---
-description: Meta's reference implementation of evaluation tasks with support for
+description: "Meta's reference implementation of evaluation tasks with support for multiple languages and evaluation metrics."
-  multiple languages and evaluation metrics
+sidebar_label: Meta-Reference
-sidebar_label: Meta Reference
-sidebar_position: 2
 title: inline::meta-reference
 ---
 

docs/docs/providers/eval/remote_nvidia.mdx

@@ -1,8 +1,6 @@
 ---
-description: NVIDIA's evaluation provider for running evaluation tasks on NVIDIA's
+description: "NVIDIA's evaluation provider for running evaluation tasks on NVIDIA's platform."
-  platform
+sidebar_label: Remote - Nvidia
-sidebar_label: Nvidia
-sidebar_position: 3
 title: remote::nvidia
 ---
 

docs/docs/providers/files/index.mdx

@@ -1,7 +1,5 @@
 ---
-description: Available providers for the files API
+sidebar_label: Files
-sidebar_label: Overview
-sidebar_position: 1
 title: Files
 ---
 
@@ -13,5 +11,5 @@ This section contains documentation for all available providers for the **files*
 
 ## Providers
 
-- **[Localfs](./inline_localfs)** - Inline provider
+- [Localfs](./inline_localfs)
-- **[S3](./remote_s3)** - Remote provider
+- [Remote - S3](./remote_s3)

docs/docs/providers/files/inline_localfs.mdx

@@ -1,8 +1,6 @@
 ---
-description: Local filesystem-based file storage provider for managing files and documents
+description: "Local filesystem-based file storage provider for managing files and documents locally."
-  locally
 sidebar_label: Localfs
-sidebar_position: 2
 title: inline::localfs
 ---
 

docs/docs/providers/files/remote_s3.mdx

@@ -1,8 +1,6 @@
 ---
-description: AWS S3-based file storage provider for scalable cloud file management
+description: "AWS S3-based file storage provider for scalable cloud file management with metadata persistence."
-  with metadata persistence
+sidebar_label: Remote - S3
-sidebar_label: S3
-sidebar_position: 3
 title: remote::s3
 ---
 

docs/docs/providers/inference/index.mdx

@@ -1,7 +1,10 @@
 ---
-description: Available providers for the inference API
+description: "Llama Stack Inference API for generating completions, chat completions, and embeddings.
-sidebar_label: Overview
+
-sidebar_position: 1
+    This API provides the raw interface to the underlying models. Two kinds of models are supported:
+    - LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.
+    - Embedding models: these models generate embeddings to be used for semantic search."
+sidebar_label: Inference
 title: Inference
 ---
 
@@ -19,28 +22,27 @@ This section contains documentation for all available providers for the **infere
 
 ## Providers
 
-- **[Meta Reference](./inline_meta-reference)** - Inline provider
+- [Meta-Reference](./inline_meta-reference)
-- **[Sentence Transformers](./inline_sentence-transformers)** - Inline provider
+- [Sentence-Transformers](./inline_sentence-transformers)
-- **[Anthropic](./remote_anthropic)** - Remote provider
+- [Remote - Anthropic](./remote_anthropic)
-- **[Azure](./remote_azure)** - Remote provider
+- [Remote - Azure](./remote_azure)
-- **[Bedrock](./remote_bedrock)** - Remote provider
+- [Remote - Bedrock](./remote_bedrock)
-- **[Cerebras](./remote_cerebras)** - Remote provider
+- [Remote - Cerebras](./remote_cerebras)
-- **[Databricks](./remote_databricks)** - Remote provider
+- [Remote - Databricks](./remote_databricks)
-- **[Fireworks](./remote_fireworks)** - Remote provider
+- [Remote - Fireworks](./remote_fireworks)
-- **[Gemini](./remote_gemini)** - Remote provider
+- [Remote - Gemini](./remote_gemini)
-- **[Groq](./remote_groq)** - Remote provider
+- [Remote - Groq](./remote_groq)
-- **[Hugging Face Endpoint](./remote_hf_endpoint)** - Remote provider
+- [Remote - Hf - Endpoint](./remote_hf_endpoint)
-- **[Hugging Face Serverless](./remote_hf_serverless)** - Remote provider
+- [Remote - Hf - Serverless](./remote_hf_serverless)
-- **[Llama OpenAI Compatible](./remote_llama-openai-compat)** - Remote provider
+- [Remote - Llama-Openai-Compat](./remote_llama-openai-compat)
-- **[Nvidia](./remote_nvidia)** - Remote provider
+- [Remote - Nvidia](./remote_nvidia)
-- **[Ollama](./remote_ollama)** - Remote provider
+- [Remote - Ollama](./remote_ollama)
-- **[Openai](./remote_openai)** - Remote provider
+- [Remote - Openai](./remote_openai)
-- **[Passthrough](./remote_passthrough)** - Remote provider
+- [Remote - Passthrough](./remote_passthrough)
-- **[Runpod](./remote_runpod)** - Remote provider
+- [Remote - Runpod](./remote_runpod)
-- **[Sambanova](./remote_sambanova)** - Remote provider
+- [Remote - Sambanova](./remote_sambanova)
-- **[SambaNova OpenAI Compatible](./remote_sambanova-openai-compat)** - Remote provider
+- [Remote - Tgi](./remote_tgi)
-- **[Tgi](./remote_tgi)** - Remote provider
+- [Remote - Together](./remote_together)
-- **[Together](./remote_together)** - Remote provider
+- [Remote - Vertexai](./remote_vertexai)
-- **[Vertexai](./remote_vertexai)** - Remote provider
+- [Remote - Vllm](./remote_vllm)
-- **[Vllm](./remote_vllm)** - Remote provider
+- [Remote - Watsonx](./remote_watsonx)
-- **[Watsonx](./remote_watsonx)** - Remote provider

docs/docs/providers/inference/inline_meta-reference.mdx

@@ -1,8 +1,6 @@
 ---
-description: Meta's reference implementation of inference with support for various
+description: "Meta's reference implementation of inference with support for various model formats and optimization techniques."
-  model formats and optimization techniques
+sidebar_label: Meta-Reference
-sidebar_label: Meta Reference
-sidebar_position: 2
 title: inline::meta-reference
 ---
 

docs/docs/providers/inference/inline_sentence-transformers.mdx

@@ -1,8 +1,6 @@
 ---
-description: Sentence Transformers inference provider for text embeddings and similarity
+description: "Sentence Transformers inference provider for text embeddings and similarity search."
-  search
+sidebar_label: Sentence-Transformers
-sidebar_label: Sentence Transformers
-sidebar_position: 3
 title: inline::sentence-transformers
 ---
 
@@ -12,10 +10,6 @@ title: inline::sentence-transformers
 
 Sentence Transformers inference provider for text embeddings and similarity search.
 
-## Configuration
-
-No configuration options available.
-
 ## Sample Configuration
 
 ```yaml

docs/docs/providers/inference/remote_anthropic.mdx

@@ -1,8 +1,6 @@
 ---
-description: Anthropic inference provider for accessing Claude models and Anthropic's
+description: "Anthropic inference provider for accessing Claude models and Anthropic's AI services."
-  AI services
+sidebar_label: Remote - Anthropic
-sidebar_label: Anthropic
-sidebar_position: 4
 title: remote::anthropic
 ---
 

docs/docs/providers/inference/remote_azure.mdx

@@ -1,8 +1,9 @@
 ---
-description: Azure OpenAI inference provider for accessing GPT models and other Azure
+description: |
-  services
+  Azure OpenAI inference provider for accessing GPT models and other Azure services.
-sidebar_label: Azure
+  Provider documentation
-sidebar_position: 5
+  https://learn.microsoft.com/en-us/azure/ai-foundry/openai/overview
+sidebar_label: Remote - Azure
 title: remote::azure
 ---
 
@@ -10,10 +11,12 @@ title: remote::azure
 
 ## Description
 
+
 Azure OpenAI inference provider for accessing GPT models and other Azure services.
 Provider documentation
 https://learn.microsoft.com/en-us/azure/ai-foundry/openai/overview
 
+
 ## Configuration
 
 | Field | Type | Required | Default | Description |

docs/docs/providers/inference/remote_bedrock.mdx

@@ -1,8 +1,6 @@
 ---
-description: AWS Bedrock inference provider for accessing various AI models through
+description: "AWS Bedrock inference provider for accessing various AI models through AWS's managed service."
-  AWS's managed service
+sidebar_label: Remote - Bedrock
-sidebar_label: Bedrock
-sidebar_position: 6
 title: remote::bedrock
 ---
 

docs/docs/providers/inference/remote_cerebras.mdx

@@ -1,7 +1,6 @@
 ---
-description: Cerebras inference provider for running models on Cerebras Cloud platform
+description: "Cerebras inference provider for running models on Cerebras Cloud platform."
-sidebar_label: Cerebras
+sidebar_label: Remote - Cerebras
-sidebar_position: 7
 title: remote::cerebras
 ---
 

docs/docs/providers/inference/remote_databricks.mdx

@@ -1,8 +1,6 @@
 ---
-description: Databricks inference provider for running models on Databricks' unified
+description: "Databricks inference provider for running models on Databricks' unified analytics platform."
-  analytics platform
+sidebar_label: Remote - Databricks
-sidebar_label: Databricks
-sidebar_position: 8
 title: remote::databricks
 ---
 

docs/docs/providers/inference/remote_fireworks.mdx

@@ -1,8 +1,6 @@
 ---
-description: Fireworks AI inference provider for Llama models and other AI models
+description: "Fireworks AI inference provider for Llama models and other AI models on the Fireworks platform."
-  on the Fireworks platform
+sidebar_label: Remote - Fireworks
-sidebar_label: Fireworks
-sidebar_position: 9
 title: remote::fireworks
 ---
 

docs/docs/providers/inference/remote_gemini.mdx

@@ -1,8 +1,6 @@
 ---
-description: Google Gemini inference provider for accessing Gemini models and Google's
+description: "Google Gemini inference provider for accessing Gemini models and Google's AI services."
-  AI services
+sidebar_label: Remote - Gemini
-sidebar_label: Gemini
-sidebar_position: 10
 title: remote::gemini
 ---
 

docs/docs/providers/inference/remote_groq.mdx

@@ -1,7 +1,6 @@
 ---
-description: Groq inference provider for ultra-fast inference using Groq's LPU technology
+description: "Groq inference provider for ultra-fast inference using Groq's LPU technology."
-sidebar_label: Groq
+sidebar_label: Remote - Groq
-sidebar_position: 11
 title: remote::groq
 ---
 

docs/docs/providers/inference/remote_hf_endpoint.mdx

@@ -1,7 +1,6 @@
 ---
-description: HuggingFace Inference Endpoints provider for dedicated model serving
+description: "HuggingFace Inference Endpoints provider for dedicated model serving."
-sidebar_label: Hugging Face Endpoint
+sidebar_label: Remote - Hf - Endpoint
-sidebar_position: 12
 title: remote::hf::endpoint
 ---
 
@@ -15,8 +14,8 @@ HuggingFace Inference Endpoints provider for dedicated model serving.
 
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
-| `endpoint_name` | `<class 'str'>` | No |  | The name of the Hugging Face Inference Endpoint in the format of `{namespace}/{endpoint_name}` (e.g. 'my-cool-org/meta-llama-3-1-8b-instruct-rce'). Namespace is optional and will default to the user account if not provided. |
+| `endpoint_name` | `<class 'str'>` | No |  | The name of the Hugging Face Inference Endpoint in the format of '{namespace}/{endpoint_name}' (e.g. 'my-cool-org/meta-llama-3-1-8b-instruct-rce'). Namespace is optional and will default to the user account if not provided. |
-| `api_token` | `pydantic.types.SecretStr or None` | No |  | Your Hugging Face user access token (will default to locally saved token if not provided) |
+| `api_token` | `pydantic.types.SecretStr \| None` | No |  | Your Hugging Face user access token (will default to locally saved token if not provided) |
 
 ## Sample Configuration
 

docs/docs/providers/inference/remote_hf_serverless.mdx

@@ -1,7 +1,6 @@
 ---
-description: HuggingFace Inference API serverless provider for on-demand model inference
+description: "HuggingFace Inference API serverless provider for on-demand model inference."
-sidebar_label: Hugging Face Serverless
+sidebar_label: Remote - Hf - Serverless
-sidebar_position: 13
 title: remote::hf::serverless
 ---
 

docs/docs/providers/inference/remote_llama-openai-compat.mdx

@@ -1,8 +1,6 @@
 ---
-description: Llama OpenAI-compatible provider for using Llama models with OpenAI API
+description: "Llama OpenAI-compatible provider for using Llama models with OpenAI API format."
-  format
+sidebar_label: Remote - Llama-Openai-Compat
-sidebar_label: Llama OpenAI Compatible
-sidebar_position: 14
 title: remote::llama-openai-compat
 ---
 

docs/docs/providers/inference/remote_nvidia.mdx

@@ -1,7 +1,6 @@
 ---
-description: NVIDIA inference provider for accessing NVIDIA NIM models and AI services
+description: "NVIDIA inference provider for accessing NVIDIA NIM models and AI services."
-sidebar_label: Nvidia
+sidebar_label: Remote - Nvidia
-sidebar_position: 15
 title: remote::nvidia
 ---
 

docs/docs/providers/inference/remote_ollama.mdx

@@ -1,8 +1,6 @@
 ---
-description: Ollama inference provider for running local models through the Ollama
+description: "Ollama inference provider for running local models through the Ollama runtime."
-  runtime
+sidebar_label: Remote - Ollama
-sidebar_label: Ollama
-sidebar_position: 16
 title: remote::ollama
 ---
 

docs/docs/providers/inference/remote_openai.mdx

@@ -1,7 +1,6 @@
 ---
-description: OpenAI inference provider for accessing GPT models and other OpenAI services
+description: "OpenAI inference provider for accessing GPT models and other OpenAI services."
-sidebar_label: Openai
+sidebar_label: Remote - Openai
-sidebar_position: 17
 title: remote::openai
 ---
 

docs/docs/providers/inference/remote_passthrough.mdx

@@ -1,8 +1,6 @@
 ---
-description: Passthrough inference provider for connecting to any external inference
+description: "Passthrough inference provider for connecting to any external inference service not directly supported."
-  service not directly supported
+sidebar_label: Remote - Passthrough
-sidebar_label: Passthrough
-sidebar_position: 18
 title: remote::passthrough
 ---
 

docs/docs/providers/inference/remote_runpod.mdx

@@ -1,7 +1,6 @@
 ---
-description: RunPod inference provider for running models on RunPod's cloud GPU platform
+description: "RunPod inference provider for running models on RunPod's cloud GPU platform."
-sidebar_label: Runpod
+sidebar_label: Remote - Runpod
-sidebar_position: 19
 title: remote::runpod
 ---
 

docs/docs/providers/inference/remote_sambanova.mdx

@@ -1,8 +1,6 @@
 ---
-description: SambaNova inference provider for running models on SambaNova's dataflow
+description: "SambaNova inference provider for running models on SambaNova's dataflow architecture."
-  architecture
+sidebar_label: Remote - Sambanova
-sidebar_label: Sambanova
-sidebar_position: 20
 title: remote::sambanova
 ---
 

docs/docs/providers/inference/remote_tgi.mdx

@@ -1,7 +1,6 @@
 ---
-description: Text Generation Inference (TGI) provider for HuggingFace model serving
+description: "Text Generation Inference (TGI) provider for HuggingFace model serving."
-sidebar_label: Tgi
+sidebar_label: Remote - Tgi
-sidebar_position: 22
 title: remote::tgi
 ---
 

docs/docs/providers/inference/remote_together.mdx

@@ -1,8 +1,6 @@
 ---
-description: Together AI inference provider for open-source models and collaborative
+description: "Together AI inference provider for open-source models and collaborative AI development."
-  AI development
+sidebar_label: Remote - Together
-sidebar_label: Together
-sidebar_position: 23
 title: remote::together
 ---
 

docs/docs/providers/inference/remote_vertexai.mdx

@@ -1,18 +1,26 @@
 ---
-description: "Google Vertex AI inference provider enables you to use Google's Gemini\
+description: |
-  \ models through Google Cloud's Vertex AI platform, providing several advantages:\n\
+  Google Vertex AI inference provider enables you to use Google's Gemini models through Google Cloud's Vertex AI platform, providing several advantages:
-  \n\u2022 Enterprise-grade security: Uses Google Cloud's security controls and IAM\n\
+
-  \u2022 Better integration: Seamless integration with other Google Cloud services\n\
+  • Enterprise-grade security: Uses Google Cloud's security controls and IAM
-  \u2022 Advanced features: Access to additional Vertex AI features like model tuning\
+  • Better integration: Seamless integration with other Google Cloud services
-  \ and monitoring\n\u2022 Authentication: Uses Google Cloud Application Default Credentials\
+  • Advanced features: Access to additional Vertex AI features like model tuning and monitoring
-  \ (ADC) instead of API keys\n\nConfiguration:\n- Set VERTEX_AI_PROJECT environment\
+  • Authentication: Uses Google Cloud Application Default Credentials (ADC) instead of API keys
-  \ variable (required)\n- Set VERTEX_AI_LOCATION environment variable (optional,\
+
-  \ defaults to us-central1)\n- Use Google Cloud Application Default Credentials or\
+  Configuration:
-  \ service account key\n\nAuthentication Setup:\nOption 1 (Recommended): gcloud auth\
+  - Set VERTEX_AI_PROJECT environment variable (required)
-  \ application-default login\nOption 2: Set GOOGLE_APPLICATION_CREDENTIALS to service\
+  - Set VERTEX_AI_LOCATION environment variable (optional, defaults to us-central1)
-  \ account key path\n\nAvailable Models:\n- vertex_ai/gemini-2"
+  - Use Google Cloud Application Default Credentials or service account key
-sidebar_label: Vertexai
+
-sidebar_position: 24
+  Authentication Setup:
+  Option 1 (Recommended): gcloud auth application-default login
+  Option 2: Set GOOGLE_APPLICATION_CREDENTIALS to service account key path
+
+  Available Models:
+  - vertex_ai/gemini-2.0-flash
+  - vertex_ai/gemini-2.5-flash
+  - vertex_ai/gemini-2.5-pro
+sidebar_label: Remote - Vertexai
 title: remote::vertexai
 ---
 

docs/docs/providers/inference/remote_vllm.mdx

@@ -1,7 +1,6 @@
 ---
-description: Remote vLLM inference provider for connecting to vLLM servers
+description: "Remote vLLM inference provider for connecting to vLLM servers."
-sidebar_label: Vllm
+sidebar_label: Remote - Vllm
-sidebar_position: 25
 title: remote::vllm
 ---
 

docs/docs/providers/inference/remote_watsonx.mdx

@@ -1,8 +1,6 @@
 ---
-description: IBM WatsonX inference provider for accessing AI models on IBM's WatsonX
+description: "IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform."
-  platform
+sidebar_label: Remote - Watsonx
-sidebar_label: Watsonx
-sidebar_position: 26
 title: remote::watsonx
 ---
 
@@ -17,8 +15,8 @@ IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `<class 'str'>` | No | https://us-south.ml.cloud.ibm.com | A base url for accessing the watsonx.ai |
-| `api_key` | `pydantic.types.SecretStr \| None` | No |  | The watsonx API key, only needed of using the hosted service |
+| `api_key` | `pydantic.types.SecretStr \| None` | No |  | The watsonx API key |
-| `project_id` | `str \| None` | No |  | The Project ID key, only needed of using the hosted service |
+| `project_id` | `str \| None` | No |  | The Project ID key |
 | `timeout` | `<class 'int'>` | No | 60 | Timeout for the HTTP requests |
 
 ## Sample Configuration

docs/docs/providers/post_training/index.mdx

@@ -1,7 +1,5 @@
 ---
-description: Available providers for the post_training API
+sidebar_label: Post Training
-sidebar_label: Overview
-sidebar_position: 1
 title: Post_Training
 ---
 
@@ -13,10 +11,7 @@ This section contains documentation for all available providers for the **post_t
 
 ## Providers
 
-- **[Huggingface](./inline_huggingface)** - Inline provider
+- [Huggingface-Gpu](./inline_huggingface-gpu)
-- **[Huggingface Cpu](./inline_huggingface-cpu)** - Inline provider
+- [Torchtune-Cpu](./inline_torchtune-cpu)
-- **[Huggingface Gpu](./inline_huggingface-gpu)** - Inline provider
+- [Torchtune-Gpu](./inline_torchtune-gpu)
-- **[Torchtune](./inline_torchtune)** - Inline provider
+- [Remote - Nvidia](./remote_nvidia)
-- **[Torchtune Cpu](./inline_torchtune-cpu)** - Inline provider
-- **[Torchtune Gpu](./inline_torchtune-gpu)** - Inline provider
-- **[Nvidia](./remote_nvidia)** - Remote provider

docs/docs/providers/post_training/inline_huggingface-gpu.mdx

@@ -1,8 +1,6 @@
 ---
-description: HuggingFace-based post-training provider for fine-tuning models using
+description: "HuggingFace-based post-training provider for fine-tuning models using the HuggingFace ecosystem."
-  the HuggingFace ecosystem
+sidebar_label: Huggingface-Gpu
-sidebar_label: Huggingface Gpu
-sidebar_position: 4
 title: inline::huggingface-gpu
 ---
 
@@ -17,10 +15,13 @@ HuggingFace-based post-training provider for fine-tuning models using the Huggin
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `device` | `<class 'str'>` | No | cuda |  |
-| `distributed_backend` | `Literal['fsdp', 'deepspeed']` | No |  |  |
+| `distributed_backend` | `Literal['fsdp', 'deepspeed'` | No |  |  |
-| `checkpoint_format` | `Literal['full_state', 'huggingface']` | No | huggingface |  |
+| `checkpoint_format` | `Literal['full_state', 'huggingface'` | No | huggingface |  |
-| `chat_template` | `<class 'str'>` | No | `<\|user\|>{input}<\|assistant\|>{output}` |  |
+| `chat_template` | `<class 'str'>` | No | <|user|>
-| `model_specific_config` | `<class 'dict'>` | No | `{'trust_remote_code': True, 'attn_implementation': 'sdpa'}` |  |
+{input}
+<|assistant|>
+{output} |  |
+| `model_specific_config` | `<class 'dict'>` | No | {'trust_remote_code': True, 'attn_implementation': 'sdpa'} |  |
 | `max_seq_length` | `<class 'int'>` | No | 2048 |  |
 | `gradient_checkpointing` | `<class 'bool'>` | No | False |  |
 | `save_total_limit` | `<class 'int'>` | No | 3 |  |

docs/docs/providers/post_training/inline_torchtune-cpu.mdx

@@ -1,8 +1,6 @@
 ---
-description: TorchTune-based post-training provider for fine-tuning and optimizing
+description: "TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework."
-  models using Meta's TorchTune framework
+sidebar_label: Torchtune-Cpu
-sidebar_label: Torchtune Cpu
-sidebar_position: 6
 title: inline::torchtune-cpu
 ---
 

docs/docs/providers/post_training/inline_torchtune-gpu.mdx

@@ -1,8 +1,6 @@
 ---
-description: TorchTune-based post-training provider for fine-tuning and optimizing
+description: "TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework."
-  models using Meta's TorchTune framework
+sidebar_label: Torchtune-Gpu
-sidebar_label: Torchtune Gpu
-sidebar_position: 7
 title: inline::torchtune-gpu
 ---
 

docs/docs/providers/post_training/remote_nvidia.mdx

@@ -1,7 +1,6 @@
 ---
-description: NVIDIA's post-training provider for fine-tuning models on NVIDIA's platform
+description: "NVIDIA's post-training provider for fine-tuning models on NVIDIA's platform."
-sidebar_label: Nvidia
+sidebar_label: Remote - Nvidia
-sidebar_position: 8
 title: remote::nvidia
 ---
 

docs/docs/providers/safety/index.mdx

@@ -1,7 +1,5 @@
 ---
-description: Available providers for the safety API
+sidebar_label: Safety
-sidebar_label: Overview
-sidebar_position: 1
 title: Safety
 ---
 
@@ -13,9 +11,9 @@ This section contains documentation for all available providers for the **safety
 
 ## Providers
 
-- **[Code Scanner](./inline_code-scanner)** - Inline provider
+- [Code-Scanner](./inline_code-scanner)
-- **[Llama Guard](./inline_llama-guard)** - Inline provider
+- [Llama-Guard](./inline_llama-guard)
-- **[Prompt Guard](./inline_prompt-guard)** - Inline provider
+- [Prompt-Guard](./inline_prompt-guard)
-- **[Bedrock](./remote_bedrock)** - Remote provider
+- [Remote - Bedrock](./remote_bedrock)
-- **[Nvidia](./remote_nvidia)** - Remote provider
+- [Remote - Nvidia](./remote_nvidia)
-- **[Sambanova](./remote_sambanova)** - Remote provider
+- [Remote - Sambanova](./remote_sambanova)

docs/docs/providers/safety/inline_code-scanner.mdx

@@ -1,8 +1,6 @@
 ---
-description: Code Scanner safety provider for detecting security vulnerabilities and
+description: "Code Scanner safety provider for detecting security vulnerabilities and unsafe code patterns."
-  unsafe code patterns
+sidebar_label: Code-Scanner
-sidebar_label: Code Scanner
-sidebar_position: 2
 title: inline::code-scanner
 ---
 
@@ -12,10 +10,6 @@ title: inline::code-scanner
 
 Code Scanner safety provider for detecting security vulnerabilities and unsafe code patterns.
 
-## Configuration
-
-No configuration options available.
-
 ## Sample Configuration
 
 ```yaml

docs/docs/providers/safety/inline_llama-guard.mdx

@@ -1,8 +1,6 @@
 ---
-description: Llama Guard safety provider for content moderation and safety filtering
+description: "Llama Guard safety provider for content moderation and safety filtering using Meta's Llama Guard model."
-  using Meta's Llama Guard model
+sidebar_label: Llama-Guard
-sidebar_label: Llama Guard
-sidebar_position: 3
 title: inline::llama-guard
 ---
 

docs/docs/providers/safety/inline_prompt-guard.mdx

@@ -1,8 +1,6 @@
 ---
-description: Prompt Guard safety provider for detecting and filtering unsafe prompts
+description: "Prompt Guard safety provider for detecting and filtering unsafe prompts and content."
-  and content
+sidebar_label: Prompt-Guard
-sidebar_label: Prompt Guard
-sidebar_position: 4
 title: inline::prompt-guard
 ---
 

docs/docs/providers/safety/remote_bedrock.mdx

@@ -1,8 +1,6 @@
 ---
-description: AWS Bedrock safety provider for content moderation using AWS's safety
+description: "AWS Bedrock safety provider for content moderation using AWS's safety services."
-  services
+sidebar_label: Remote - Bedrock
-sidebar_label: Bedrock
-sidebar_position: 5
 title: remote::bedrock
 ---
 

docs/docs/providers/safety/remote_nvidia.mdx

@@ -1,7 +1,6 @@
 ---
-description: NVIDIA's safety provider for content moderation and safety filtering
+description: "NVIDIA's safety provider for content moderation and safety filtering."
-sidebar_label: Nvidia
+sidebar_label: Remote - Nvidia
-sidebar_position: 6
 title: remote::nvidia
 ---
 

docs/docs/providers/safety/remote_sambanova.mdx

@@ -1,7 +1,6 @@
 ---
-description: SambaNova's safety provider for content moderation and safety filtering
+description: "SambaNova's safety provider for content moderation and safety filtering."
-sidebar_label: Sambanova
+sidebar_label: Remote - Sambanova
-sidebar_position: 7
 title: remote::sambanova
 ---
 

docs/docs/providers/scoring/index.mdx

@@ -1,7 +1,5 @@
 ---
-description: Available providers for the scoring API
+sidebar_label: Scoring
-sidebar_label: Overview
-sidebar_position: 1
 title: Scoring
 ---
 
@@ -13,6 +11,6 @@ This section contains documentation for all available providers for the **scorin
 
 ## Providers
 
-- **[Basic](./inline_basic)** - Inline provider
+- [Basic](./inline_basic)
-- **[Braintrust](./inline_braintrust)** - Inline provider
+- [Braintrust](./inline_braintrust)
-- **[Llm As Judge](./inline_llm-as-judge)** - Inline provider
+- [Llm-As-Judge](./inline_llm-as-judge)

docs/docs/providers/scoring/inline_basic.mdx

@@ -1,7 +1,6 @@
 ---
-description: Basic scoring provider for simple evaluation metrics and scoring functions
+description: "Basic scoring provider for simple evaluation metrics and scoring functions."
 sidebar_label: Basic
-sidebar_position: 2
 title: inline::basic
 ---
 
@@ -11,10 +10,6 @@ title: inline::basic
 
 Basic scoring provider for simple evaluation metrics and scoring functions.
 
-## Configuration
-
-No configuration options available.
-
 ## Sample Configuration
 
 ```yaml

docs/docs/providers/scoring/inline_braintrust.mdx

@@ -1,8 +1,6 @@
 ---
-description: Braintrust scoring provider for evaluation and scoring using the Braintrust
+description: "Braintrust scoring provider for evaluation and scoring using the Braintrust platform."
-  platform
 sidebar_label: Braintrust
-sidebar_position: 3
 title: inline::braintrust
 ---
 

docs/docs/providers/scoring/inline_llm-as-judge.mdx

@@ -1,8 +1,6 @@
 ---
-description: LLM-as-judge scoring provider that uses language models to evaluate and
+description: "LLM-as-judge scoring provider that uses language models to evaluate and score responses."
-  score responses
+sidebar_label: Llm-As-Judge
-sidebar_label: Llm As Judge
-sidebar_position: 4
 title: inline::llm-as-judge
 ---
 
@@ -12,10 +10,6 @@ title: inline::llm-as-judge
 
 LLM-as-judge scoring provider that uses language models to evaluate and score responses.
 
-## Configuration
-
-No configuration options available.
-
 ## Sample Configuration
 
 ```yaml

docs/docs/providers/telemetry/index.mdx

@@ -1,7 +1,5 @@
 ---
-description: Available providers for the telemetry API
+sidebar_label: Telemetry
-sidebar_label: Overview
-sidebar_position: 1
 title: Telemetry
 ---
 
@@ -13,4 +11,4 @@ This section contains documentation for all available providers for the **teleme
 
 ## Providers
 
-- **[Meta Reference](./inline_meta-reference)** - Inline provider
+- [Meta-Reference](./inline_meta-reference)

docs/docs/providers/telemetry/inline_meta-reference.mdx

@@ -1,8 +1,6 @@
 ---
-description: Meta's reference implementation of telemetry and observability using
+description: "Meta's reference implementation of telemetry and observability using OpenTelemetry."
-  OpenTelemetry
+sidebar_label: Meta-Reference
-sidebar_label: Meta Reference
-sidebar_position: 2
 title: inline::meta-reference
 ---
 
@@ -16,9 +14,9 @@ Meta's reference implementation of telemetry and observability using OpenTelemet
 
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
-| `otel_exporter_otlp_endpoint` | `str or None` | No |  | The OpenTelemetry collector endpoint URL (base URL for traces, metrics, and logs). If not set, the SDK will use OTEL_EXPORTER_OTLP_ENDPOINT environment variable. |
+| `otel_exporter_otlp_endpoint` | `str \| None` | No |  | The OpenTelemetry collector endpoint URL (base URL for traces, metrics, and logs). If not set, the SDK will use OTEL_EXPORTER_OTLP_ENDPOINT environment variable. |
 | `service_name` | `<class 'str'>` | No | ​ | The service name to use for telemetry |
-| `sinks` | `list[TelemetrySink]` | No | `[CONSOLE, SQLITE]` | List of telemetry sinks to enable (possible values: otel_trace, otel_metric, sqlite, console) |
+| `sinks` | `list[inline.telemetry.meta_reference.config.TelemetrySink` | No | [<TelemetrySink.CONSOLE: 'console'>, <TelemetrySink.SQLITE: 'sqlite'>] | List of telemetry sinks to enable (possible values: otel_trace, otel_metric, sqlite, console) |
 | `sqlite_db_path` | `<class 'str'>` | No | ~/.llama/runtime/trace_store.db | The path to the SQLite database to use for storing traces |
 
 ## Sample Configuration

docs/docs/providers/tool_runtime/index.mdx

@@ -1,7 +1,5 @@
 ---
-description: Available providers for the tool_runtime API
+sidebar_label: Tool Runtime
-sidebar_label: Overview
-sidebar_position: 1
 title: Tool_Runtime
 ---
 
@@ -13,9 +11,9 @@ This section contains documentation for all available providers for the **tool_r
 
 ## Providers
 
-- **[Rag Runtime](./inline_rag-runtime)** - Inline provider
+- [Rag-Runtime](./inline_rag-runtime)
-- **[Bing Search](./remote_bing-search)** - Remote provider
+- [Remote - Bing-Search](./remote_bing-search)
-- **[Brave Search](./remote_brave-search)** - Remote provider
+- [Remote - Brave-Search](./remote_brave-search)
-- **[Model Context Protocol](./remote_model-context-protocol)** - Remote provider
+- [Remote - Model-Context-Protocol](./remote_model-context-protocol)
-- **[Tavily Search](./remote_tavily-search)** - Remote provider
+- [Remote - Tavily-Search](./remote_tavily-search)
-- **[Wolfram Alpha](./remote_wolfram-alpha)** - Remote provider
+- [Remote - Wolfram-Alpha](./remote_wolfram-alpha)

docs/docs/providers/tool_runtime/inline_rag-runtime.mdx

@@ -1,8 +1,6 @@
 ---
-description: RAG (Retrieval-Augmented Generation) tool runtime for document ingestion,
+description: "RAG (Retrieval-Augmented Generation) tool runtime for document ingestion, chunking, and semantic search."
-  chunking, and semantic search
+sidebar_label: Rag-Runtime
-sidebar_label: Rag Runtime
-sidebar_position: 2
 title: inline::rag-runtime
 ---
 
@@ -12,10 +10,6 @@ title: inline::rag-runtime
 
 RAG (Retrieval-Augmented Generation) tool runtime for document ingestion, chunking, and semantic search.
 
-## Configuration
-
-No configuration options available.
-
 ## Sample Configuration
 
 ```yaml

docs/docs/providers/tool_runtime/remote_bing-search.mdx

@@ -1,8 +1,6 @@
 ---
-description: Bing Search tool for web search capabilities using Microsoft's search
+description: "Bing Search tool for web search capabilities using Microsoft's search engine."
-  engine
+sidebar_label: Remote - Bing-Search
-sidebar_label: Bing Search
-sidebar_position: 3
 title: remote::bing-search
 ---
 

docs/docs/providers/tool_runtime/remote_brave-search.mdx

@@ -1,7 +1,6 @@
 ---
-description: Brave Search tool for web search capabilities with privacy-focused results
+description: "Brave Search tool for web search capabilities with privacy-focused results."
-sidebar_label: Brave Search
+sidebar_label: Remote - Brave-Search
-sidebar_position: 4
 title: remote::brave-search
 ---
 

docs/docs/providers/tool_runtime/remote_model-context-protocol.mdx

@@ -1,8 +1,6 @@
 ---
-description: Model Context Protocol (MCP) tool for standardized tool calling and context
+description: "Model Context Protocol (MCP) tool for standardized tool calling and context management."
-  management
+sidebar_label: Remote - Model-Context-Protocol
-sidebar_label: Model Context Protocol
-sidebar_position: 5
 title: remote::model-context-protocol
 ---
 
@@ -12,10 +10,6 @@ title: remote::model-context-protocol
 
 Model Context Protocol (MCP) tool for standardized tool calling and context management.
 
-## Configuration
-
-No configuration options available.
-
 ## Sample Configuration
 
 ```yaml

docs/docs/providers/tool_runtime/remote_tavily-search.mdx

@@ -1,7 +1,6 @@
 ---
-description: Tavily Search tool for AI-optimized web search with structured results
+description: "Tavily Search tool for AI-optimized web search with structured results."
-sidebar_label: Tavily Search
+sidebar_label: Remote - Tavily-Search
-sidebar_position: 6
 title: remote::tavily-search
 ---
 

docs/docs/providers/tool_runtime/remote_wolfram-alpha.mdx

@@ -1,7 +1,6 @@
 ---
-description: Wolfram Alpha tool for computational knowledge and mathematical calculations
+description: "Wolfram Alpha tool for computational knowledge and mathematical calculations."
-sidebar_label: Wolfram Alpha
+sidebar_label: Remote - Wolfram-Alpha
-sidebar_position: 7
 title: remote::wolfram-alpha
 ---
 

docs/docs/providers/vector_io/index.mdx

@@ -1,7 +1,5 @@
 ---
-description: Available providers for the vector_io API
+sidebar_label: Vector Io
-sidebar_label: Overview
-sidebar_position: 1
 title: Vector_Io
 ---
 
@@ -13,15 +11,15 @@ This section contains documentation for all available providers for the **vector
 
 ## Providers
 
-- **[Chromadb](./inline_chromadb)** - Inline provider
+- [Chromadb](./inline_chromadb)
-- **[Faiss](./inline_faiss)** - Inline provider
+- [Faiss](./inline_faiss)
-- **[Meta Reference](./inline_meta-reference)** - Inline provider
+- [Meta-Reference](./inline_meta-reference)
-- **[Milvus](./inline_milvus)** - Inline provider
+- [Milvus](./inline_milvus)
-- **[Qdrant](./inline_qdrant)** - Inline provider
+- [Qdrant](./inline_qdrant)
-- **[SQLite-Vec](./inline_sqlite-vec)** - Inline provider
+- [Sqlite-Vec](./inline_sqlite-vec)
-- **[SQLite-Vec](./inline_sqlite_vec)** - Inline provider
+- [Sqlite Vec](./inline_sqlite_vec)
-- **[Chromadb](./remote_chromadb)** - Remote provider
+- [Remote - Chromadb](./remote_chromadb)
-- **[Milvus](./remote_milvus)** - Remote provider
+- [Remote - Milvus](./remote_milvus)
-- **[Pgvector](./remote_pgvector)** - Remote provider
+- [Remote - Pgvector](./remote_pgvector)
-- **[Qdrant](./remote_qdrant)** - Remote provider
+- [Remote - Qdrant](./remote_qdrant)
-- **[Weaviate](./remote_weaviate)** - Remote provider
+- [Remote - Weaviate](./remote_weaviate)

docs/docs/providers/vector_io/inline_chromadb.mdx

@@ -1,7 +1,37 @@
 ---
-description: '[Chroma](https://www'
+description: |
+  [Chroma](https://www.trychroma.com/) is an inline and remote vector
+  database provider for Llama Stack. It allows you to store and query vectors directly within a Chroma database.
+  That means you're not limited to storing vectors in memory or in a separate service.
+
+  ## Features
+  Chroma supports:
+  - Store embeddings and their metadata
+  - Vector search
+  - Full-text search
+  - Document storage
+  - Metadata filtering
+  - Multi-modal retrieval
+
+  ## Usage
+
+  To use Chrome in your Llama Stack project, follow these steps:
+
+  1. Install the necessary dependencies.
+  2. Configure your Llama Stack project to use chroma.
+  3. Start storing and querying vectors.
+
+  ## Installation
+
+  You can install chroma using pip:
+
+  ```bash
+  pip install chromadb
+  ```
+
+  ## Documentation
+  See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introduction) for more details about Chroma in general.
 sidebar_label: Chromadb
-sidebar_position: 2
 title: inline::chromadb
 ---
 
@@ -9,10 +39,41 @@ title: inline::chromadb
 
 ## Description
 
+
 [Chroma](https://www.trychroma.com/) is an inline and remote vector
 database provider for Llama Stack. It allows you to store and query vectors directly within a Chroma database.
 That means you're not limited to storing vectors in memory or in a separate service.
 
+## Features
+Chroma supports:
+- Store embeddings and their metadata
+- Vector search
+- Full-text search
+- Document storage
+- Metadata filtering
+- Multi-modal retrieval
+
+## Usage
+
+To use Chrome in your Llama Stack project, follow these steps:
+
+1. Install the necessary dependencies.
+2. Configure your Llama Stack project to use chroma.
+3. Start storing and querying vectors.
+
+## Installation
+
+You can install chroma using pip:
+
+```bash
+pip install chromadb
+```
+
+## Documentation
+See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introduction) for more details about Chroma in general.
+
+
+
 ## Configuration
 
 | Field | Type | Required | Default | Description |

docs/docs/providers/vector_io/inline_faiss.mdx

@@ -1,7 +1,46 @@
 ---
-description: '[Faiss](https://github'
+description: |
+  [Faiss](https://github.com/facebookresearch/faiss) is an inline vector database provider for Llama Stack. It
+  allows you to store and query vectors directly in memory.
+  That means you'll get fast and efficient vector retrieval.
+
+  ## Features
+
+  - Lightweight and easy to use
+  - Fully integrated with Llama Stack
+  - GPU support
+  - **Vector search** - FAISS supports pure vector similarity search using embeddings
+
+  ## Search Modes
+
+  **Supported:**
+  - **Vector Search** (`mode="vector"`): Performs vector similarity search using embeddings
+
+  **Not Supported:**
+  - **Keyword Search** (`mode="keyword"`): Not supported by FAISS
+  - **Hybrid Search** (`mode="hybrid"`): Not supported by FAISS
+
+  > **Note**: FAISS is designed as a pure vector similarity search library. See the [FAISS GitHub repository](https://github.com/facebookresearch/faiss) for more details about FAISS's core functionality.
+
+  ## Usage
+
+  To use Faiss in your Llama Stack project, follow these steps:
+
+  1. Install the necessary dependencies.
+  2. Configure your Llama Stack project to use Faiss.
+  3. Start storing and querying vectors.
+
+  ## Installation
+
+  You can install Faiss using pip:
+
+  ```bash
+  pip install faiss-cpu
+  ```
+  ## Documentation
+  See [Faiss' documentation](https://faiss.ai/) or the [Faiss Wiki](https://github.com/facebookresearch/faiss/wiki) for
+  more details about Faiss in general.
 sidebar_label: Faiss
-sidebar_position: 3
 title: inline::faiss
 ---
 
@@ -9,10 +48,49 @@ title: inline::faiss
 
 ## Description
 
+
 [Faiss](https://github.com/facebookresearch/faiss) is an inline vector database provider for Llama Stack. It
 allows you to store and query vectors directly in memory.
 That means you'll get fast and efficient vector retrieval.
 
+## Features
+
+- Lightweight and easy to use
+- Fully integrated with Llama Stack
+- GPU support
+- **Vector search** - FAISS supports pure vector similarity search using embeddings
+
+## Search Modes
+
+**Supported:**
+- **Vector Search** (`mode="vector"`): Performs vector similarity search using embeddings
+
+**Not Supported:**
+- **Keyword Search** (`mode="keyword"`): Not supported by FAISS
+- **Hybrid Search** (`mode="hybrid"`): Not supported by FAISS
+
+> **Note**: FAISS is designed as a pure vector similarity search library. See the [FAISS GitHub repository](https://github.com/facebookresearch/faiss) for more details about FAISS's core functionality.
+
+## Usage
+
+To use Faiss in your Llama Stack project, follow these steps:
+
+1. Install the necessary dependencies.
+2. Configure your Llama Stack project to use Faiss.
+3. Start storing and querying vectors.
+
+## Installation
+
+You can install Faiss using pip:
+
+```bash
+pip install faiss-cpu
+```
+## Documentation
+See [Faiss' documentation](https://faiss.ai/) or the [Faiss Wiki](https://github.com/facebookresearch/faiss/wiki) for
+more details about Faiss in general.
+
+
 ## Configuration
 
 | Field | Type | Required | Default | Description |

docs/docs/providers/vector_io/inline_meta-reference.mdx

@@ -1,7 +1,6 @@
 ---
-description: Meta's reference implementation of a vector database
+description: "Meta's reference implementation of a vector database."
-sidebar_label: Meta Reference
+sidebar_label: Meta-Reference
-sidebar_position: 4
 title: inline::meta-reference
 ---
 
@@ -24,3 +23,9 @@ kvstore:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/faiss_store.db
 ```
+## Deprecation Notice
+
+:::warning
+Please use the `inline::faiss` provider instead.
+:::
+

docs/docs/providers/vector_io/inline_milvus.mdx

@@ -1,7 +1,6 @@
 ---
-description: Please refer to the remote provider documentation
+description: "Please refer to the remote provider documentation."
 sidebar_label: Milvus
-sidebar_position: 5
 title: inline::milvus
 ---
 
@@ -9,8 +8,10 @@ title: inline::milvus
 
 ## Description
 
+
 Please refer to the remote provider documentation.
 
+
 ## Configuration
 
 | Field | Type | Required | Default | Description |

docs/docs/providers/vector_io/inline_qdrant.mdx

@@ -1,7 +1,47 @@
 ---
-description: '[Qdrant](https://qdrant'
+description: |
+  [Qdrant](https://qdrant.tech/documentation/) is an inline and remote vector database provider for Llama Stack. It
+  allows you to store and query vectors directly in memory.
+  That means you'll get fast and efficient vector retrieval.
+
+  > By default, Qdrant stores vectors in RAM, delivering incredibly fast access for datasets that fit comfortably in
+  > memory. But when your dataset exceeds RAM capacity, Qdrant offers Memmap as an alternative.
+  >
+  > \[[An Introduction to Vector Databases](https://qdrant.tech/articles/what-is-a-vector-database/)\]
+
+
+
+  ## Features
+
+  - Lightweight and easy to use
+  - Fully integrated with Llama Stack
+  - Apache 2.0 license terms
+  - Store embeddings and their metadata
+  - Supports search by
+    [Keyword](https://qdrant.tech/articles/qdrant-introduces-full-text-filters-and-indexes/)
+    and [Hybrid](https://qdrant.tech/articles/hybrid-search/#building-a-hybrid-search-system-in-qdrant) search
+  - [Multilingual and Multimodal retrieval](https://qdrant.tech/documentation/multimodal-search/)
+  - [Medatata filtering](https://qdrant.tech/articles/vector-search-filtering/)
+  - [GPU support](https://qdrant.tech/documentation/guides/running-with-gpu/)
+
+  ## Usage
+
+  To use Qdrant in your Llama Stack project, follow these steps:
+
+  1. Install the necessary dependencies.
+  2. Configure your Llama Stack project to use Qdrant.
+  3. Start storing and querying vectors.
+
+  ## Installation
+
+  You can install Qdrant using docker:
+
+  ```bash
+  docker pull qdrant/qdrant
+  ```
+  ## Documentation
+  See the [Qdrant documentation](https://qdrant.tech/documentation/) for more details about Qdrant in general.
 sidebar_label: Qdrant
-sidebar_position: 6
 title: inline::qdrant
 ---
 
@@ -9,6 +49,7 @@ title: inline::qdrant
 
 ## Description
 
+
 [Qdrant](https://qdrant.tech/documentation/) is an inline and remote vector database provider for Llama Stack. It
 allows you to store and query vectors directly in memory.
 That means you'll get fast and efficient vector retrieval.
@@ -18,6 +59,40 @@ That means you'll get fast and efficient vector retrieval.
 >
 > \[[An Introduction to Vector Databases](https://qdrant.tech/articles/what-is-a-vector-database/)\]
 
+
+
+## Features
+
+- Lightweight and easy to use
+- Fully integrated with Llama Stack
+- Apache 2.0 license terms
+- Store embeddings and their metadata
+- Supports search by
+  [Keyword](https://qdrant.tech/articles/qdrant-introduces-full-text-filters-and-indexes/)
+  and [Hybrid](https://qdrant.tech/articles/hybrid-search/#building-a-hybrid-search-system-in-qdrant) search
+- [Multilingual and Multimodal retrieval](https://qdrant.tech/documentation/multimodal-search/)
+- [Medatata filtering](https://qdrant.tech/articles/vector-search-filtering/)
+- [GPU support](https://qdrant.tech/documentation/guides/running-with-gpu/)
+
+## Usage
+
+To use Qdrant in your Llama Stack project, follow these steps:
+
+1. Install the necessary dependencies.
+2. Configure your Llama Stack project to use Qdrant.
+3. Start storing and querying vectors.
+
+## Installation
+
+You can install Qdrant using docker:
+
+```bash
+docker pull qdrant/qdrant
+```
+## Documentation
+See the [Qdrant documentation](https://qdrant.tech/documentation/) for more details about Qdrant in general.
+
+
 ## Configuration
 
 | Field | Type | Required | Default | Description |

docs/docs/providers/vector_io/inline_sqlite-vec.mdx

@@ -1,7 +1,202 @@
 ---
-description: '[SQLite-Vec](https://github'
+description: |
-sidebar_label: SQLite-Vec
+  [SQLite-Vec](https://github.com/asg017/sqlite-vec) is an inline vector database provider for Llama Stack. It
-sidebar_position: 7
+  allows you to store and query vectors directly within an SQLite database.
+  That means you're not limited to storing vectors in memory or in a separate service.
+
+  ## Features
+
+  - Lightweight and easy to use
+  - Fully integrated with Llama Stacks
+  - Uses disk-based storage for persistence, allowing for larger vector storage
+
+  ### Comparison to Faiss
+
+  The choice between Faiss and sqlite-vec should be made based on the needs of your application,
+  as they have different strengths.
+
+  #### Choosing the Right Provider
+
+  Scenario | Recommended Tool | Reason
+  -- |-----------------| --
+  Online Analytical Processing (OLAP) | Faiss           | Fast, in-memory searches
+  Online Transaction Processing (OLTP) | sqlite-vec      | Frequent writes and reads
+  Frequent writes | sqlite-vec      | Efficient disk-based storage and incremental indexing
+  Large datasets | sqlite-vec      | Disk-based storage for larger vector storage
+  Datasets that can fit in memory, frequent reads | Faiss | Optimized for speed, indexing, and GPU acceleration
+
+  #### Empirical Example
+
+  Consider the histogram below in which 10,000 randomly generated strings were inserted
+  in batches of 100 into both Faiss and sqlite-vec using `client.tool_runtime.rag_tool.insert()`.
+
+  ```{image} ../../../../_static/providers/vector_io/write_time_comparison_sqlite-vec-faiss.png
+  :alt: Comparison of SQLite-Vec and Faiss write times
+  :width: 400px
+  ```
+
+  You will notice that the average write time for `sqlite-vec` was 788ms, compared to
+  47,640ms for Faiss. While the number is jarring, if you look at the distribution, you can see that it is rather
+  uniformly spread across the [1500, 100000] interval.
+
+  Looking at each individual write in the order that the documents are inserted you'll see the increase in
+  write speed as Faiss reindexes the vectors after each write.
+  ```{image} ../../../../_static/providers/vector_io/write_time_sequence_sqlite-vec-faiss.png
+  :alt: Comparison of SQLite-Vec and Faiss write times
+  :width: 400px
+  ```
+
+  In comparison, the read times for Faiss was on average 10% faster than sqlite-vec.
+  The modes of the two distributions highlight the differences much further where Faiss
+  will likely yield faster read performance.
+
+  ```{image} ../../../../_static/providers/vector_io/read_time_comparison_sqlite-vec-faiss.png
+  :alt: Comparison of SQLite-Vec and Faiss read times
+  :width: 400px
+  ```
+
+  ## Usage
+
+  To use sqlite-vec in your Llama Stack project, follow these steps:
+
+  1. Install the necessary dependencies.
+  2. Configure your Llama Stack project to use SQLite-Vec.
+  3. Start storing and querying vectors.
+
+  The SQLite-vec provider supports three search modes:
+
+  1. **Vector Search** (`mode="vector"`): Performs pure vector similarity search using the embeddings.
+  2. **Keyword Search** (`mode="keyword"`): Performs full-text search using SQLite's FTS5.
+  3. **Hybrid Search** (`mode="hybrid"`): Combines both vector and keyword search for better results. First performs keyword search to get candidate matches, then applies vector similarity search on those candidates.
+
+  Example with hybrid search:
+  ```python
+  response = await vector_io.query_chunks(
+      vector_db_id="my_db",
+      query="your query here",
+      params={"mode": "hybrid", "max_chunks": 3, "score_threshold": 0.7},
+  )
+
+  # Using RRF ranker
+  response = await vector_io.query_chunks(
+      vector_db_id="my_db",
+      query="your query here",
+      params={
+          "mode": "hybrid",
+          "max_chunks": 3,
+          "score_threshold": 0.7,
+          "ranker": {"type": "rrf", "impact_factor": 60.0},
+      },
+  )
+
+  # Using weighted ranker
+  response = await vector_io.query_chunks(
+      vector_db_id="my_db",
+      query="your query here",
+      params={
+          "mode": "hybrid",
+          "max_chunks": 3,
+          "score_threshold": 0.7,
+          "ranker": {"type": "weighted", "alpha": 0.7},  # 70% vector, 30% keyword
+      },
+  )
+  ```
+
+  Example with explicit vector search:
+  ```python
+  response = await vector_io.query_chunks(
+      vector_db_id="my_db",
+      query="your query here",
+      params={"mode": "vector", "max_chunks": 3, "score_threshold": 0.7},
+  )
+  ```
+
+  Example with keyword search:
+  ```python
+  response = await vector_io.query_chunks(
+      vector_db_id="my_db",
+      query="your query here",
+      params={"mode": "keyword", "max_chunks": 3, "score_threshold": 0.7},
+  )
+  ```
+
+  ## Supported Search Modes
+
+  The SQLite vector store supports three search modes:
+
+  1. **Vector Search** (`mode="vector"`): Uses vector similarity to find relevant chunks
+  2. **Keyword Search** (`mode="keyword"`): Uses keyword matching to find relevant chunks
+  3. **Hybrid Search** (`mode="hybrid"`): Combines both vector and keyword scores using a ranker
+
+  ### Hybrid Search
+
+  Hybrid search combines the strengths of both vector and keyword search by:
+  - Computing vector similarity scores
+  - Computing keyword match scores
+  - Using a ranker to combine these scores
+
+  Two ranker types are supported:
+
+  1. **RRF (Reciprocal Rank Fusion)**:
+     - Combines ranks from both vector and keyword results
+     - Uses an impact factor (default: 60.0) to control the weight of higher-ranked results
+     - Good for balancing between vector and keyword results
+     - The default impact factor of 60.0 comes from the original RRF paper by Cormack et al. (2009) [^1], which found this value to provide optimal performance across various retrieval tasks
+
+  2. **Weighted**:
+     - Linearly combines normalized vector and keyword scores
+     - Uses an alpha parameter (0-1) to control the blend:
+       - alpha=0: Only use keyword scores
+       - alpha=1: Only use vector scores
+       - alpha=0.5: Equal weight to both (default)
+
+  Example using RAGQueryConfig with different search modes:
+
+  ```python
+  from llama_stack.apis.tools import RAGQueryConfig, RRFRanker, WeightedRanker
+
+  # Vector search
+  config = RAGQueryConfig(mode="vector", max_chunks=5)
+
+  # Keyword search
+  config = RAGQueryConfig(mode="keyword", max_chunks=5)
+
+  # Hybrid search with custom RRF ranker
+  config = RAGQueryConfig(
+      mode="hybrid",
+      max_chunks=5,
+      ranker=RRFRanker(impact_factor=50.0),  # Custom impact factor
+  )
+
+  # Hybrid search with weighted ranker
+  config = RAGQueryConfig(
+      mode="hybrid",
+      max_chunks=5,
+      ranker=WeightedRanker(alpha=0.7),  # 70% vector, 30% keyword
+  )
+
+  # Hybrid search with default RRF ranker
+  config = RAGQueryConfig(
+      mode="hybrid", max_chunks=5
+  )  # Will use RRF with impact_factor=60.0
+  ```
+
+  Note: The ranker configuration is only used in hybrid mode. For vector or keyword modes, the ranker parameter is ignored.
+
+  ## Installation
+
+  You can install SQLite-Vec using pip:
+
+  ```bash
+  pip install sqlite-vec
+  ```
+
+  ## Documentation
+
+  See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) for more details about sqlite-vec in general.
+
+  [^1]: Cormack, G. V., Clarke, C. L., & Buettcher, S. (2009). [Reciprocal rank fusion outperforms condorcet and individual rank learning methods](https://dl.acm.org/doi/10.1145/1571941.1572114). In Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval (pp. 758-759).
+sidebar_label: Sqlite-Vec
 title: inline::sqlite-vec
 ---
 
@@ -9,10 +204,205 @@ title: inline::sqlite-vec
 
 ## Description
 
+
 [SQLite-Vec](https://github.com/asg017/sqlite-vec) is an inline vector database provider for Llama Stack. It
 allows you to store and query vectors directly within an SQLite database.
 That means you're not limited to storing vectors in memory or in a separate service.
 
+## Features
+
+- Lightweight and easy to use
+- Fully integrated with Llama Stacks
+- Uses disk-based storage for persistence, allowing for larger vector storage
+
+### Comparison to Faiss
+
+The choice between Faiss and sqlite-vec should be made based on the needs of your application,
+as they have different strengths.
+
+#### Choosing the Right Provider
+
+Scenario | Recommended Tool | Reason
+-- |-----------------| --
+Online Analytical Processing (OLAP) | Faiss           | Fast, in-memory searches
+Online Transaction Processing (OLTP) | sqlite-vec      | Frequent writes and reads
+Frequent writes | sqlite-vec      | Efficient disk-based storage and incremental indexing
+Large datasets | sqlite-vec      | Disk-based storage for larger vector storage
+Datasets that can fit in memory, frequent reads | Faiss | Optimized for speed, indexing, and GPU acceleration
+
+#### Empirical Example
+
+Consider the histogram below in which 10,000 randomly generated strings were inserted
+in batches of 100 into both Faiss and sqlite-vec using `client.tool_runtime.rag_tool.insert()`.
+
+```{image} ../../../../_static/providers/vector_io/write_time_comparison_sqlite-vec-faiss.png
+:alt: Comparison of SQLite-Vec and Faiss write times
+:width: 400px
+```
+
+You will notice that the average write time for `sqlite-vec` was 788ms, compared to
+47,640ms for Faiss. While the number is jarring, if you look at the distribution, you can see that it is rather
+uniformly spread across the [1500, 100000] interval.
+
+Looking at each individual write in the order that the documents are inserted you'll see the increase in
+write speed as Faiss reindexes the vectors after each write.
+```{image} ../../../../_static/providers/vector_io/write_time_sequence_sqlite-vec-faiss.png
+:alt: Comparison of SQLite-Vec and Faiss write times
+:width: 400px
+```
+
+In comparison, the read times for Faiss was on average 10% faster than sqlite-vec.
+The modes of the two distributions highlight the differences much further where Faiss
+will likely yield faster read performance.
+
+```{image} ../../../../_static/providers/vector_io/read_time_comparison_sqlite-vec-faiss.png
+:alt: Comparison of SQLite-Vec and Faiss read times
+:width: 400px
+```
+
+## Usage
+
+To use sqlite-vec in your Llama Stack project, follow these steps:
+
+1. Install the necessary dependencies.
+2. Configure your Llama Stack project to use SQLite-Vec.
+3. Start storing and querying vectors.
+
+The SQLite-vec provider supports three search modes:
+
+1. **Vector Search** (`mode="vector"`): Performs pure vector similarity search using the embeddings.
+2. **Keyword Search** (`mode="keyword"`): Performs full-text search using SQLite's FTS5.
+3. **Hybrid Search** (`mode="hybrid"`): Combines both vector and keyword search for better results. First performs keyword search to get candidate matches, then applies vector similarity search on those candidates.
+
+Example with hybrid search:
+```python
+response = await vector_io.query_chunks(
+    vector_db_id="my_db",
+    query="your query here",
+    params={"mode": "hybrid", "max_chunks": 3, "score_threshold": 0.7},
+)
+
+# Using RRF ranker
+response = await vector_io.query_chunks(
+    vector_db_id="my_db",
+    query="your query here",
+    params={
+        "mode": "hybrid",
+        "max_chunks": 3,
+        "score_threshold": 0.7,
+        "ranker": {"type": "rrf", "impact_factor": 60.0},
+    },
+)
+
+# Using weighted ranker
+response = await vector_io.query_chunks(
+    vector_db_id="my_db",
+    query="your query here",
+    params={
+        "mode": "hybrid",
+        "max_chunks": 3,
+        "score_threshold": 0.7,
+        "ranker": {"type": "weighted", "alpha": 0.7},  # 70% vector, 30% keyword
+    },
+)
+```
+
+Example with explicit vector search:
+```python
+response = await vector_io.query_chunks(
+    vector_db_id="my_db",
+    query="your query here",
+    params={"mode": "vector", "max_chunks": 3, "score_threshold": 0.7},
+)
+```
+
+Example with keyword search:
+```python
+response = await vector_io.query_chunks(
+    vector_db_id="my_db",
+    query="your query here",
+    params={"mode": "keyword", "max_chunks": 3, "score_threshold": 0.7},
+)
+```
+
+## Supported Search Modes
+
+The SQLite vector store supports three search modes:
+
+1. **Vector Search** (`mode="vector"`): Uses vector similarity to find relevant chunks
+2. **Keyword Search** (`mode="keyword"`): Uses keyword matching to find relevant chunks
+3. **Hybrid Search** (`mode="hybrid"`): Combines both vector and keyword scores using a ranker
+
+### Hybrid Search
+
+Hybrid search combines the strengths of both vector and keyword search by:
+- Computing vector similarity scores
+- Computing keyword match scores
+- Using a ranker to combine these scores
+
+Two ranker types are supported:
+
+1. **RRF (Reciprocal Rank Fusion)**:
+   - Combines ranks from both vector and keyword results
+   - Uses an impact factor (default: 60.0) to control the weight of higher-ranked results
+   - Good for balancing between vector and keyword results
+   - The default impact factor of 60.0 comes from the original RRF paper by Cormack et al. (2009) [^1], which found this value to provide optimal performance across various retrieval tasks
+
+2. **Weighted**:
+   - Linearly combines normalized vector and keyword scores
+   - Uses an alpha parameter (0-1) to control the blend:
+     - alpha=0: Only use keyword scores
+     - alpha=1: Only use vector scores
+     - alpha=0.5: Equal weight to both (default)
+
+Example using RAGQueryConfig with different search modes:
+
+```python
+from llama_stack.apis.tools import RAGQueryConfig, RRFRanker, WeightedRanker
+
+# Vector search
+config = RAGQueryConfig(mode="vector", max_chunks=5)
+
+# Keyword search
+config = RAGQueryConfig(mode="keyword", max_chunks=5)
+
+# Hybrid search with custom RRF ranker
+config = RAGQueryConfig(
+    mode="hybrid",
+    max_chunks=5,
+    ranker=RRFRanker(impact_factor=50.0),  # Custom impact factor
+)
+
+# Hybrid search with weighted ranker
+config = RAGQueryConfig(
+    mode="hybrid",
+    max_chunks=5,
+    ranker=WeightedRanker(alpha=0.7),  # 70% vector, 30% keyword
+)
+
+# Hybrid search with default RRF ranker
+config = RAGQueryConfig(
+    mode="hybrid", max_chunks=5
+)  # Will use RRF with impact_factor=60.0
+```
+
+Note: The ranker configuration is only used in hybrid mode. For vector or keyword modes, the ranker parameter is ignored.
+
+## Installation
+
+You can install SQLite-Vec using pip:
+
+```bash
+pip install sqlite-vec
+```
+
+## Documentation
+
+See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) for more details about sqlite-vec in general.
+
+[^1]: Cormack, G. V., Clarke, C. L., & Buettcher, S. (2009). [Reciprocal rank fusion outperforms condorcet and individual rank learning methods](https://dl.acm.org/doi/10.1145/1571941.1572114). In Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval (pp. 758-759).
+
+
 ## Configuration
 
 | Field | Type | Required | Default | Description |

docs/docs/providers/vector_io/inline_sqlite_vec.mdx

@@ -0,0 +1,35 @@
+---
+description: "Please refer to the sqlite-vec provider documentation."
+sidebar_label: Sqlite Vec
+title: inline::sqlite_vec
+---
+
+# inline::sqlite_vec
+
+## Description
+
+
+Please refer to the sqlite-vec provider documentation.
+
+
+## Configuration
+
+| Field | Type | Required | Default | Description |
+|-------|------|----------|---------|-------------|
+| `db_path` | `<class 'str'>` | No |  | Path to the SQLite database file |
+| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
+
+## Sample Configuration
+
+```yaml
+db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/sqlite_vec.db
+kvstore:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/sqlite_vec_registry.db
+```
+## Deprecation Notice
+
+:::warning
+Please use the `inline::sqlite-vec` provider (notice the hyphen instead of underscore) instead.
+:::
+

docs/docs/providers/vector_io/remote_chromadb.mdx

@@ -1,7 +1,37 @@
 ---
-description: '[Chroma](https://www'
+description: |
-sidebar_label: Chromadb
+  [Chroma](https://www.trychroma.com/) is an inline and remote vector
-sidebar_position: 9
+  database provider for Llama Stack. It allows you to store and query vectors directly within a Chroma database.
+  That means you're not limited to storing vectors in memory or in a separate service.
+
+  ## Features
+  Chroma supports:
+  - Store embeddings and their metadata
+  - Vector search
+  - Full-text search
+  - Document storage
+  - Metadata filtering
+  - Multi-modal retrieval
+
+  ## Usage
+
+  To use Chrome in your Llama Stack project, follow these steps:
+
+  1. Install the necessary dependencies.
+  2. Configure your Llama Stack project to use chroma.
+  3. Start storing and querying vectors.
+
+  ## Installation
+
+  You can install chroma using pip:
+
+  ```bash
+  pip install chromadb
+  ```
+
+  ## Documentation
+  See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introduction) for more details about Chroma in general.
+sidebar_label: Remote - Chromadb
 title: remote::chromadb
 ---
 
@@ -9,10 +39,40 @@ title: remote::chromadb
 
 ## Description
 
+
 [Chroma](https://www.trychroma.com/) is an inline and remote vector
 database provider for Llama Stack. It allows you to store and query vectors directly within a Chroma database.
 That means you're not limited to storing vectors in memory or in a separate service.
 
+## Features
+Chroma supports:
+- Store embeddings and their metadata
+- Vector search
+- Full-text search
+- Document storage
+- Metadata filtering
+- Multi-modal retrieval
+
+## Usage
+
+To use Chrome in your Llama Stack project, follow these steps:
+
+1. Install the necessary dependencies.
+2. Configure your Llama Stack project to use chroma.
+3. Start storing and querying vectors.
+
+## Installation
+
+You can install chroma using pip:
+
+```bash
+pip install chromadb
+```
+
+## Documentation
+See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introduction) for more details about Chroma in general.
+
+
 ## Configuration
 
 | Field | Type | Required | Default | Description |

docs/docs/providers/vector_io/remote_milvus.mdx

@@ -1,7 +1,201 @@
 ---
-description: '[Milvus](https://milvus'
+description: |
-sidebar_label: Milvus
+  [Milvus](https://milvus.io/) is an inline and remote vector database provider for Llama Stack. It
-sidebar_position: 10
+  allows you to store and query vectors directly within a Milvus database.
+  That means you're not limited to storing vectors in memory or in a separate service.
+
+  ## Features
+
+  - Easy to use
+  - Fully integrated with Llama Stack
+  - Supports all search modes: vector, keyword, and hybrid search (both inline and remote configurations)
+
+  ## Usage
+
+  To use Milvus in your Llama Stack project, follow these steps:
+
+  1. Install the necessary dependencies.
+  2. Configure your Llama Stack project to use Milvus.
+  3. Start storing and querying vectors.
+
+  ## Installation
+
+  If you want to use inline Milvus, you can install:
+
+  ```bash
+  pip install pymilvus[milvus-lite]
+  ```
+
+  If you want to use remote Milvus, you can install:
+
+  ```bash
+  pip install pymilvus
+  ```
+
+  ## Configuration
+
+  In Llama Stack, Milvus can be configured in two ways:
+  - **Inline (Local) Configuration** - Uses Milvus-Lite for local storage
+  - **Remote Configuration** - Connects to a remote Milvus server
+
+  ### Inline (Local) Configuration
+
+  The simplest method is local configuration, which requires setting `db_path`, a path for locally storing Milvus-Lite files:
+
+  ```yaml
+  vector_io:
+    - provider_id: milvus
+      provider_type: inline::milvus
+      config:
+        db_path: ~/.llama/distributions/together/milvus_store.db
+  ```
+
+  ### Remote Configuration
+
+  Remote configuration is suitable for larger data storage requirements:
+
+  #### Standard Remote Connection
+
+  ```yaml
+  vector_io:
+    - provider_id: milvus
+      provider_type: remote::milvus
+      config:
+        uri: "http://<host>:<port>"
+        token: "<user>:<password>"
+  ```
+
+  #### TLS-Enabled Remote Connection (One-way TLS)
+
+  For connections to Milvus instances with one-way TLS enabled:
+
+  ```yaml
+  vector_io:
+    - provider_id: milvus
+      provider_type: remote::milvus
+      config:
+        uri: "https://<host>:<port>"
+        token: "<user>:<password>"
+        secure: True
+        server_pem_path: "/path/to/server.pem"
+  ```
+
+  #### Mutual TLS (mTLS) Remote Connection
+
+  For connections to Milvus instances with mutual TLS (mTLS) enabled:
+
+  ```yaml
+  vector_io:
+    - provider_id: milvus
+      provider_type: remote::milvus
+      config:
+        uri: "https://<host>:<port>"
+        token: "<user>:<password>"
+        secure: True
+        ca_pem_path: "/path/to/ca.pem"
+        client_pem_path: "/path/to/client.pem"
+        client_key_path: "/path/to/client.key"
+  ```
+
+  #### Key Parameters for TLS Configuration
+
+  - **`secure`**: Enables TLS encryption when set to `true`. Defaults to `false`.
+  - **`server_pem_path`**: Path to the **server certificate** for verifying the server's identity (used in one-way TLS).
+  - **`ca_pem_path`**: Path to the **Certificate Authority (CA) certificate** for validating the server certificate (required in mTLS).
+  - **`client_pem_path`**: Path to the **client certificate** file (required for mTLS).
+  - **`client_key_path`**: Path to the **client private key** file (required for mTLS).
+
+  ## Search Modes
+
+  Milvus supports three different search modes for both inline and remote configurations:
+
+  ### Vector Search
+  Vector search uses semantic similarity to find the most relevant chunks based on embedding vectors. This is the default search mode and works well for finding conceptually similar content.
+
+  ```python
+  # Vector search example
+  search_response = client.vector_stores.search(
+      vector_store_id=vector_store.id,
+      query="What is machine learning?",
+      search_mode="vector",
+      max_num_results=5,
+  )
+  ```
+
+  ### Keyword Search
+  Keyword search uses traditional text-based matching to find chunks containing specific terms or phrases. This is useful when you need exact term matches.
+
+  ```python
+  # Keyword search example
+  search_response = client.vector_stores.search(
+      vector_store_id=vector_store.id,
+      query="Python programming language",
+      search_mode="keyword",
+      max_num_results=5,
+  )
+  ```
+
+  ### Hybrid Search
+  Hybrid search combines both vector and keyword search methods to provide more comprehensive results. It leverages the strengths of both semantic similarity and exact term matching.
+
+  #### Basic Hybrid Search
+  ```python
+  # Basic hybrid search example (uses RRF ranker with default impact_factor=60.0)
+  search_response = client.vector_stores.search(
+      vector_store_id=vector_store.id,
+      query="neural networks in Python",
+      search_mode="hybrid",
+      max_num_results=5,
+  )
+  ```
+
+  **Note**: The default `impact_factor` value of 60.0 was empirically determined to be optimal in the original RRF research paper: ["Reciprocal Rank Fusion outperforms Condorcet and individual Rank Learning Methods"](https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf) (Cormack et al., 2009).
+
+  #### Hybrid Search with RRF (Reciprocal Rank Fusion) Ranker
+  RRF combines rankings from vector and keyword search by using reciprocal ranks. The impact factor controls how much weight is given to higher-ranked results.
+
+  ```python
+  # Hybrid search with custom RRF parameters
+  search_response = client.vector_stores.search(
+      vector_store_id=vector_store.id,
+      query="neural networks in Python",
+      search_mode="hybrid",
+      max_num_results=5,
+      ranking_options={
+          "ranker": {
+              "type": "rrf",
+              "impact_factor": 100.0,  # Higher values give more weight to top-ranked results
+          }
+      },
+  )
+  ```
+
+  #### Hybrid Search with Weighted Ranker
+  Weighted ranker linearly combines normalized scores from vector and keyword search. The alpha parameter controls the balance between the two search methods.
+
+  ```python
+  # Hybrid search with weighted ranker
+  search_response = client.vector_stores.search(
+      vector_store_id=vector_store.id,
+      query="neural networks in Python",
+      search_mode="hybrid",
+      max_num_results=5,
+      ranking_options={
+          "ranker": {
+              "type": "weighted",
+              "alpha": 0.7,  # 70% vector search, 30% keyword search
+          }
+      },
+  )
+  ```
+
+  For detailed documentation on RRF and Weighted rankers, please refer to the [Milvus Reranking Guide](https://milvus.io/docs/reranking.md).
+
+  ## Documentation
+  See the [Milvus documentation](https://milvus.io/docs/install-overview.md) for more details about Milvus in general.
+
+  For more details on TLS configuration, refer to the [TLS setup guide](https://milvus.io/docs/tls.md).
+sidebar_label: Remote - Milvus
 title: remote::milvus
 ---
 
@@ -9,10 +203,39 @@ title: remote::milvus
 
 ## Description
 
+
 [Milvus](https://milvus.io/) is an inline and remote vector database provider for Llama Stack. It
 allows you to store and query vectors directly within a Milvus database.
 That means you're not limited to storing vectors in memory or in a separate service.
 
+## Features
+
+- Easy to use
+- Fully integrated with Llama Stack
+- Supports all search modes: vector, keyword, and hybrid search (both inline and remote configurations)
+
+## Usage
+
+To use Milvus in your Llama Stack project, follow these steps:
+
+1. Install the necessary dependencies.
+2. Configure your Llama Stack project to use Milvus.
+3. Start storing and querying vectors.
+
+## Installation
+
+If you want to use inline Milvus, you can install:
+
+```bash
+pip install pymilvus[milvus-lite]
+```
+
+If you want to use remote Milvus, you can install:
+
+```bash
+pip install pymilvus
+```
+
 ## Configuration
 
 In Llama Stack, Milvus can be configured in two ways:
@@ -86,6 +309,112 @@ vector_io:
 - **`client_pem_path`**: Path to the **client certificate** file (required for mTLS).
 - **`client_key_path`**: Path to the **client private key** file (required for mTLS).
 
+## Search Modes
+
+Milvus supports three different search modes for both inline and remote configurations:
+
+### Vector Search
+Vector search uses semantic similarity to find the most relevant chunks based on embedding vectors. This is the default search mode and works well for finding conceptually similar content.
+
+```python
+# Vector search example
+search_response = client.vector_stores.search(
+    vector_store_id=vector_store.id,
+    query="What is machine learning?",
+    search_mode="vector",
+    max_num_results=5,
+)
+```
+
+### Keyword Search
+Keyword search uses traditional text-based matching to find chunks containing specific terms or phrases. This is useful when you need exact term matches.
+
+```python
+# Keyword search example
+search_response = client.vector_stores.search(
+    vector_store_id=vector_store.id,
+    query="Python programming language",
+    search_mode="keyword",
+    max_num_results=5,
+)
+```
+
+### Hybrid Search
+Hybrid search combines both vector and keyword search methods to provide more comprehensive results. It leverages the strengths of both semantic similarity and exact term matching.
+
+#### Basic Hybrid Search
+```python
+# Basic hybrid search example (uses RRF ranker with default impact_factor=60.0)
+search_response = client.vector_stores.search(
+    vector_store_id=vector_store.id,
+    query="neural networks in Python",
+    search_mode="hybrid",
+    max_num_results=5,
+)
+```
+
+**Note**: The default `impact_factor` value of 60.0 was empirically determined to be optimal in the original RRF research paper: ["Reciprocal Rank Fusion outperforms Condorcet and individual Rank Learning Methods"](https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf) (Cormack et al., 2009).
+
+#### Hybrid Search with RRF (Reciprocal Rank Fusion) Ranker
+RRF combines rankings from vector and keyword search by using reciprocal ranks. The impact factor controls how much weight is given to higher-ranked results.
+
+```python
+# Hybrid search with custom RRF parameters
+search_response = client.vector_stores.search(
+    vector_store_id=vector_store.id,
+    query="neural networks in Python",
+    search_mode="hybrid",
+    max_num_results=5,
+    ranking_options={
+        "ranker": {
+            "type": "rrf",
+            "impact_factor": 100.0,  # Higher values give more weight to top-ranked results
+        }
+    },
+)
+```
+
+#### Hybrid Search with Weighted Ranker
+Weighted ranker linearly combines normalized scores from vector and keyword search. The alpha parameter controls the balance between the two search methods.
+
+```python
+# Hybrid search with weighted ranker
+search_response = client.vector_stores.search(
+    vector_store_id=vector_store.id,
+    query="neural networks in Python",
+    search_mode="hybrid",
+    max_num_results=5,
+    ranking_options={
+        "ranker": {
+            "type": "weighted",
+            "alpha": 0.7,  # 70% vector search, 30% keyword search
+        }
+    },
+)
+```
+
+For detailed documentation on RRF and Weighted rankers, please refer to the [Milvus Reranking Guide](https://milvus.io/docs/reranking.md).
+
+## Documentation
+See the [Milvus documentation](https://milvus.io/docs/install-overview.md) for more details about Milvus in general.
+
+For more details on TLS configuration, refer to the [TLS setup guide](https://milvus.io/docs/tls.md).
+
+
+## Configuration
+
+| Field | Type | Required | Default | Description |
+|-------|------|----------|---------|-------------|
+| `uri` | `<class 'str'>` | No |  | The URI of the Milvus server |
+| `token` | `str \| None` | No |  | The token of the Milvus server |
+| `consistency_level` | `<class 'str'>` | No | Strong | The consistency level of the Milvus server |
+| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
+| `config` | `dict` | No | {} | This configuration allows additional fields to be passed through to the underlying Milvus client. See the [Milvus](https://milvus.io/docs/install-overview.md) documentation for more details about Milvus in general. |
+
+:::note
+This configuration class accepts additional fields beyond those listed above. You can pass any additional configuration options that will be forwarded to the underlying provider.
+:::
+
 ## Sample Configuration
 
 ```yaml

docs/docs/providers/vector_io/remote_pgvector.mdx

@@ -1,7 +1,105 @@
 ---
-description: '[PGVector](https://github'
+description: |
-sidebar_label: Pgvector
+  [PGVector](https://github.com/pgvector/pgvector) is a remote vector database provider for Llama Stack. It
-sidebar_position: 11
+  allows you to store and query vectors directly in memory.
+  That means you'll get fast and efficient vector retrieval.
+
+  ## Features
+
+  - Easy to use
+  - Fully integrated with Llama Stack
+
+  There are three implementations of search for PGVectoIndex available:
+
+  1. Vector Search:
+  - How it works:
+    - Uses PostgreSQL's vector extension (pgvector) to perform similarity search
+    - Compares query embeddings against stored embeddings using Cosine distance or other distance metrics
+    - Eg. SQL query: SELECT document, embedding <=> %s::vector AS distance FROM table ORDER BY distance
+
+  -Characteristics:
+    - Semantic understanding - finds documents similar in meaning even if they don't share keywords
+    - Works with high-dimensional vector embeddings (typically 768, 1024, or higher dimensions)
+    - Best for: Finding conceptually related content, handling synonyms, cross-language search
+
+  2. Keyword Search
+  - How it works:
+    - Uses PostgreSQL's full-text search capabilities with tsvector and ts_rank
+    - Converts text to searchable tokens using to_tsvector('english', text). Default language is English.
+    - Eg. SQL query: SELECT document, ts_rank(tokenized_content, plainto_tsquery('english', %s)) AS score
+
+  - Characteristics:
+    - Lexical matching - finds exact keyword matches and variations
+    - Uses GIN (Generalized Inverted Index) for fast text search performance
+    - Scoring: Uses PostgreSQL's ts_rank function for relevance scoring
+    - Best for: Exact term matching, proper names, technical terms, Boolean-style queries
+
+  3. Hybrid Search
+  - How it works:
+    - Combines both vector and keyword search results
+    - Runs both searches independently, then merges results using configurable reranking
+
+  - Two reranking strategies available:
+      - Reciprocal Rank Fusion (RRF) - (default: 60.0)
+      - Weighted Average - (default: 0.5)
+
+  - Characteristics:
+    - Best of both worlds: semantic understanding + exact matching
+    - Documents appearing in both searches get boosted scores
+    - Configurable balance between semantic and lexical matching
+    - Best for: General-purpose search where you want both precision and recall
+
+  4. Database Schema
+  The PGVector implementation stores data optimized for all three search types:
+  CREATE TABLE vector_store_xxx (
+      id TEXT PRIMARY KEY,
+      document JSONB,                    -- Original document
+      embedding vector(dimension),        -- For vector search
+      content_text TEXT,                 -- Raw text content
+      tokenized_content TSVECTOR          -- For keyword search
+  );
+
+  -- Indexes for performance
+  CREATE INDEX content_gin_idx ON table USING GIN(tokenized_content);  -- Keyword search
+  -- Vector index created automatically by pgvector
+
+  ## Usage
+
+  To use PGVector in your Llama Stack project, follow these steps:
+
+  1. Install the necessary dependencies.
+  2. Configure your Llama Stack project to use pgvector. (e.g. remote::pgvector).
+  3. Start storing and querying vectors.
+
+  ## This is an example how you can set up your environment for using PGVector
+
+  1. Export env vars:
+  ```bash
+  export ENABLE_PGVECTOR=true
+  export PGVECTOR_HOST=localhost
+  export PGVECTOR_PORT=5432
+  export PGVECTOR_DB=llamastack
+  export PGVECTOR_USER=llamastack
+  export PGVECTOR_PASSWORD=llamastack
+  ```
+
+  2. Create DB:
+  ```bash
+  psql -h localhost -U postgres -c "CREATE ROLE llamastack LOGIN PASSWORD 'llamastack';"
+  psql -h localhost -U postgres -c "CREATE DATABASE llamastack OWNER llamastack;"
+  psql -h localhost -U llamastack -d llamastack -c "CREATE EXTENSION IF NOT EXISTS vector;"
+  ```
+
+  ## Installation
+
+  You can install PGVector using docker:
+
+  ```bash
+  docker pull pgvector/pgvector:pg17
+  ```
+  ## Documentation
+  See [PGVector's documentation](https://github.com/pgvector/pgvector) for more details about PGVector in general.
+sidebar_label: Remote - Pgvector
 title: remote::pgvector
 ---
 
@@ -9,10 +107,108 @@ title: remote::pgvector
 
 ## Description
 
+
 [PGVector](https://github.com/pgvector/pgvector) is a remote vector database provider for Llama Stack. It
 allows you to store and query vectors directly in memory.
 That means you'll get fast and efficient vector retrieval.
 
+## Features
+
+- Easy to use
+- Fully integrated with Llama Stack
+
+There are three implementations of search for PGVectoIndex available:
+
+1. Vector Search:
+- How it works:
+  - Uses PostgreSQL's vector extension (pgvector) to perform similarity search
+  - Compares query embeddings against stored embeddings using Cosine distance or other distance metrics
+  - Eg. SQL query: SELECT document, embedding <=> %s::vector AS distance FROM table ORDER BY distance
+
+-Characteristics:
+  - Semantic understanding - finds documents similar in meaning even if they don't share keywords
+  - Works with high-dimensional vector embeddings (typically 768, 1024, or higher dimensions)
+  - Best for: Finding conceptually related content, handling synonyms, cross-language search
+
+2. Keyword Search
+- How it works:
+  - Uses PostgreSQL's full-text search capabilities with tsvector and ts_rank
+  - Converts text to searchable tokens using to_tsvector('english', text). Default language is English.
+  - Eg. SQL query: SELECT document, ts_rank(tokenized_content, plainto_tsquery('english', %s)) AS score
+
+- Characteristics:
+  - Lexical matching - finds exact keyword matches and variations
+  - Uses GIN (Generalized Inverted Index) for fast text search performance
+  - Scoring: Uses PostgreSQL's ts_rank function for relevance scoring
+  - Best for: Exact term matching, proper names, technical terms, Boolean-style queries
+
+3. Hybrid Search
+- How it works:
+  - Combines both vector and keyword search results
+  - Runs both searches independently, then merges results using configurable reranking
+
+- Two reranking strategies available:
+    - Reciprocal Rank Fusion (RRF) - (default: 60.0)
+    - Weighted Average - (default: 0.5)
+
+- Characteristics:
+  - Best of both worlds: semantic understanding + exact matching
+  - Documents appearing in both searches get boosted scores
+  - Configurable balance between semantic and lexical matching
+  - Best for: General-purpose search where you want both precision and recall
+
+4. Database Schema
+The PGVector implementation stores data optimized for all three search types:
+CREATE TABLE vector_store_xxx (
+    id TEXT PRIMARY KEY,
+    document JSONB,                    -- Original document
+    embedding vector(dimension),        -- For vector search
+    content_text TEXT,                 -- Raw text content
+    tokenized_content TSVECTOR          -- For keyword search
+);
+
+-- Indexes for performance
+CREATE INDEX content_gin_idx ON table USING GIN(tokenized_content);  -- Keyword search
+-- Vector index created automatically by pgvector
+
+## Usage
+
+To use PGVector in your Llama Stack project, follow these steps:
+
+1. Install the necessary dependencies.
+2. Configure your Llama Stack project to use pgvector. (e.g. remote::pgvector).
+3. Start storing and querying vectors.
+
+## This is an example how you can set up your environment for using PGVector
+
+1. Export env vars:
+```bash
+export ENABLE_PGVECTOR=true
+export PGVECTOR_HOST=localhost
+export PGVECTOR_PORT=5432
+export PGVECTOR_DB=llamastack
+export PGVECTOR_USER=llamastack
+export PGVECTOR_PASSWORD=llamastack
+```
+
+2. Create DB:
+```bash
+psql -h localhost -U postgres -c "CREATE ROLE llamastack LOGIN PASSWORD 'llamastack';"
+psql -h localhost -U postgres -c "CREATE DATABASE llamastack OWNER llamastack;"
+psql -h localhost -U llamastack -d llamastack -c "CREATE EXTENSION IF NOT EXISTS vector;"
+```
+
+## Installation
+
+You can install PGVector using docker:
+
+```bash
+docker pull pgvector/pgvector:pg17
+```
+## Documentation
+See [PGVector's documentation](https://github.com/pgvector/pgvector) for more details about PGVector in general.
+
+
 ## Configuration
 
 | Field | Type | Required | Default | Description |

docs/docs/providers/vector_io/remote_qdrant.mdx

@@ -1,7 +1,6 @@
 ---
-description: Please refer to the inline provider documentation
+description: "Please refer to the inline provider documentation."
-sidebar_label: Qdrant
+sidebar_label: Remote - Qdrant
-sidebar_position: 12
 title: remote::qdrant
 ---
 
@@ -9,8 +8,10 @@ title: remote::qdrant
 
 ## Description
 
+
 Please refer to the inline provider documentation.
 
+
 ## Configuration
 
 | Field | Type | Required | Default | Description |

docs/docs/providers/vector_io/remote_weaviate.mdx

@@ -1,7 +1,35 @@
 ---
-description: '[Weaviate](https://weaviate'
+description: |
-sidebar_label: Weaviate
+  [Weaviate](https://weaviate.io/) is a vector database provider for Llama Stack.
-sidebar_position: 13
+  It allows you to store and query vectors directly within a Weaviate database.
+  That means you're not limited to storing vectors in memory or in a separate service.
+
+  ## Features
+  Weaviate supports:
+  - Store embeddings and their metadata
+  - Vector search
+  - Full-text search
+  - Hybrid search
+  - Document storage
+  - Metadata filtering
+  - Multi-modal retrieval
+
+
+  ## Usage
+
+  To use Weaviate in your Llama Stack project, follow these steps:
+
+  1. Install the necessary dependencies.
+  2. Configure your Llama Stack project to use chroma.
+  3. Start storing and querying vectors.
+
+  ## Installation
+
+  To install Weaviate see the [Weaviate quickstart documentation](https://weaviate.io/developers/weaviate/quickstart).
+
+  ## Documentation
+  See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more details about Weaviate in general.
+sidebar_label: Remote - Weaviate
 title: remote::weaviate
 ---
 
@@ -9,10 +37,38 @@ title: remote::weaviate
 
 ## Description
 
+
 [Weaviate](https://weaviate.io/) is a vector database provider for Llama Stack.
 It allows you to store and query vectors directly within a Weaviate database.
 That means you're not limited to storing vectors in memory or in a separate service.
 
+## Features
+Weaviate supports:
+- Store embeddings and their metadata
+- Vector search
+- Full-text search
+- Hybrid search
+- Document storage
+- Metadata filtering
+- Multi-modal retrieval
+
+
+## Usage
+
+To use Weaviate in your Llama Stack project, follow these steps:
+
+1. Install the necessary dependencies.
+2. Configure your Llama Stack project to use chroma.
+3. Start storing and querying vectors.
+
+## Installation
+
+To install Weaviate see the [Weaviate quickstart documentation](https://weaviate.io/developers/weaviate/quickstart).
+
+## Documentation
+See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more details about Weaviate in general.
+
+
 ## Configuration
 
 | Field | Type | Required | Default | Description |

docs/source/distributions/self_hosted_distro/meta-reference-gpu.md

@@ -0,0 +1,125 @@
+---
+orphan: true
+---
+<!-- This file was auto-generated by distro_codegen.py, please edit source -->
+# Meta Reference GPU Distribution
+
+```{toctree}
+:maxdepth: 2
+:hidden:
+
+self
+```
+
+The `llamastack/distribution-meta-reference-gpu` distribution consists of the following provider configurations:
+
+| API | Provider(s) |
+|-----|-------------|
+| agents | `inline::meta-reference` |
+| datasetio | `remote::huggingface`, `inline::localfs` |
+| eval | `inline::meta-reference` |
+| inference | `inline::meta-reference` |
+| 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::rag-runtime`, `remote::model-context-protocol` |
+| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
+
+
+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.
+
+### Environment Variables
+
+The following environment variables can be configured:
+
+- `LLAMA_STACK_PORT`: Port for the Llama Stack distribution server (default: `8321`)
+- `INFERENCE_MODEL`: Inference model loaded into the Meta Reference server (default: `meta-llama/Llama-3.2-3B-Instruct`)
+- `INFERENCE_CHECKPOINT_DIR`: Directory containing the Meta Reference model checkpoint (default: `null`)
+- `SAFETY_MODEL`: Name of the safety (Llama-Guard) model to use (default: `meta-llama/Llama-Guard-3-1B`)
+- `SAFETY_CHECKPOINT_DIR`: Directory containing the Llama-Guard model checkpoint (default: `null`)
+
+
+## Prerequisite: Downloading Models
+
+Please use `llama model list --downloaded` to check that you have llama model checkpoints downloaded in `~/.llama` before proceeding. See [installation guide](../../references/llama_cli_reference/download_models.md) here to download the models. Run `llama model list` to see the available models to download, and `llama model download` to download the checkpoints.
+
+```
+$ llama model list --downloaded
+┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┓
+┃ Model                                   ┃ Size     ┃ Modified Time       ┃
+┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━┩
+│ Llama3.2-1B-Instruct:int4-qlora-eo8     │ 1.53 GB  │ 2025-02-26 11:22:28 │
+├─────────────────────────────────────────┼──────────┼─────────────────────┤
+│ Llama3.2-1B                             │ 2.31 GB  │ 2025-02-18 21:48:52 │
+├─────────────────────────────────────────┼──────────┼─────────────────────┤
+│ Prompt-Guard-86M                        │ 0.02 GB  │ 2025-02-26 11:29:28 │
+├─────────────────────────────────────────┼──────────┼─────────────────────┤
+│ Llama3.2-3B-Instruct:int4-spinquant-eo8 │ 3.69 GB  │ 2025-02-26 11:37:41 │
+├─────────────────────────────────────────┼──────────┼─────────────────────┤
+│ Llama3.2-3B                             │ 5.99 GB  │ 2025-02-18 21:51:26 │
+├─────────────────────────────────────────┼──────────┼─────────────────────┤
+│ Llama3.1-8B                             │ 14.97 GB │ 2025-02-16 10:36:37 │
+├─────────────────────────────────────────┼──────────┼─────────────────────┤
+│ Llama3.2-1B-Instruct:int4-spinquant-eo8 │ 1.51 GB  │ 2025-02-26 11:35:02 │
+├─────────────────────────────────────────┼──────────┼─────────────────────┤
+│ Llama-Guard-3-1B                        │ 2.80 GB  │ 2025-02-26 11:20:46 │
+├─────────────────────────────────────────┼──────────┼─────────────────────┤
+│ Llama-Guard-3-1B:int4                   │ 0.43 GB  │ 2025-02-26 11:33:33 │
+└─────────────────────────────────────────┴──────────┴─────────────────────┘
+```
+
+## Running the Distribution
+
+You can do this via venv or Docker which has a pre-built image.
+
+### Via Docker
+
+This method allows you to get started quickly without having to build the distribution code.
+
+```bash
+LLAMA_STACK_PORT=8321
+docker run \
+  -it \
+  --pull always \
+  --gpu all \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v ~/.llama:/root/.llama \
+  llamastack/distribution-meta-reference-gpu \
+  --port $LLAMA_STACK_PORT \
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
+```
+
+If you are using Llama Stack Safety / Shield APIs, use:
+
+```bash
+docker run \
+  -it \
+  --pull always \
+  --gpu all \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v ~/.llama:/root/.llama \
+  llamastack/distribution-meta-reference-gpu \
+  --port $LLAMA_STACK_PORT \
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
+```
+
+### Via venv
+
+Make sure you have done `uv pip install llama-stack` and have the Llama Stack CLI available.
+
+```bash
+llama stack build --distro meta-reference-gpu --image-type venv
+llama stack run distributions/meta-reference-gpu/run.yaml \
+  --port 8321 \
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
+```
+
+If you are using Llama Stack Safety / Shield APIs, use:
+
+```bash
+llama stack run distributions/meta-reference-gpu/run-with-safety.yaml \
+  --port 8321 \
+  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
+```

docs/source/distributions/self_hosted_distro/nvidia.md

@@ -0,0 +1,171 @@
+---
+orphan: true
+---
+<!-- This file was auto-generated by distro_codegen.py, please edit source -->
+# NVIDIA Distribution
+
+The `llamastack/distribution-nvidia` distribution consists of the following provider configurations.
+
+| API | Provider(s) |
+|-----|-------------|
+| agents | `inline::meta-reference` |
+| datasetio | `inline::localfs`, `remote::nvidia` |
+| eval | `remote::nvidia` |
+| files | `inline::localfs` |
+| inference | `remote::nvidia` |
+| post_training | `remote::nvidia` |
+| safety | `remote::nvidia` |
+| scoring | `inline::basic` |
+| telemetry | `inline::meta-reference` |
+| tool_runtime | `inline::rag-runtime` |
+| vector_io | `inline::faiss` |
+
+
+### Environment Variables
+
+The following environment variables can be configured:
+
+- `NVIDIA_API_KEY`: NVIDIA API Key (default: ``)
+- `NVIDIA_APPEND_API_VERSION`: Whether to append the API version to the base_url (default: `True`)
+- `NVIDIA_DATASET_NAMESPACE`: NVIDIA Dataset Namespace (default: `default`)
+- `NVIDIA_PROJECT_ID`: NVIDIA Project ID (default: `test-project`)
+- `NVIDIA_CUSTOMIZER_URL`: NVIDIA Customizer URL (default: `https://customizer.api.nvidia.com`)
+- `NVIDIA_OUTPUT_MODEL_DIR`: NVIDIA Output Model Directory (default: `test-example-model@v1`)
+- `GUARDRAILS_SERVICE_URL`: URL for the NeMo Guardrails Service (default: `http://0.0.0.0:7331`)
+- `NVIDIA_GUARDRAILS_CONFIG_ID`: NVIDIA Guardrail Configuration ID (default: `self-check`)
+- `NVIDIA_EVALUATOR_URL`: URL for the NeMo Evaluator Service (default: `http://0.0.0.0:7331`)
+- `INFERENCE_MODEL`: Inference model (default: `Llama3.1-8B-Instruct`)
+- `SAFETY_MODEL`: Name of the model to use for safety (default: `meta/llama-3.1-8b-instruct`)
+
+### Models
+
+The following models are available by default:
+
+- `meta/llama3-8b-instruct `
+- `meta/llama3-70b-instruct `
+- `meta/llama-3.1-8b-instruct `
+- `meta/llama-3.1-70b-instruct `
+- `meta/llama-3.1-405b-instruct `
+- `meta/llama-3.2-1b-instruct `
+- `meta/llama-3.2-3b-instruct `
+- `meta/llama-3.2-11b-vision-instruct `
+- `meta/llama-3.2-90b-vision-instruct `
+- `meta/llama-3.3-70b-instruct `
+- `nvidia/vila `
+- `nvidia/llama-3.2-nv-embedqa-1b-v2 `
+- `nvidia/nv-embedqa-e5-v5 `
+- `nvidia/nv-embedqa-mistral-7b-v2 `
+- `snowflake/arctic-embed-l `
+
+
+## Prerequisites
+### NVIDIA API Keys
+
+Make sure you have access to a NVIDIA API Key. You can get one by visiting [https://build.nvidia.com/](https://build.nvidia.com/). Use this key for the `NVIDIA_API_KEY` environment variable.
+
+### Deploy NeMo Microservices Platform
+The NVIDIA NeMo microservices platform supports end-to-end microservice deployment of a complete AI flywheel on your Kubernetes cluster through the NeMo Microservices Helm Chart. Please reference the [NVIDIA NeMo Microservices documentation](https://docs.nvidia.com/nemo/microservices/latest/about/index.html) for platform prerequisites and instructions to install and deploy the platform.
+
+## Supported Services
+Each Llama Stack API corresponds to a specific NeMo microservice. The core microservices (Customizer, Evaluator, Guardrails) are exposed by the same endpoint. The platform components (Data Store) are each exposed by separate endpoints.
+
+### Inference: NVIDIA NIM
+NVIDIA NIM is used for running inference with registered models. There are two ways to access NVIDIA NIMs:
+  1. Hosted (default): Preview APIs hosted at https://integrate.api.nvidia.com (Requires an API key)
+  2. Self-hosted: NVIDIA NIMs that run on your own infrastructure.
+
+The deployed platform includes the NIM Proxy microservice, which is the service that provides to access your NIMs (for example, to run inference on a model). Set the `NVIDIA_BASE_URL` environment variable to use your NVIDIA NIM Proxy deployment.
+
+### Datasetio API: NeMo Data Store
+The NeMo Data Store microservice serves as the default file storage solution for the NeMo microservices platform. It exposts APIs compatible with the Hugging Face Hub client (`HfApi`), so you can use the client to interact with Data Store. The `NVIDIA_DATASETS_URL` environment variable should point to your NeMo Data Store endpoint.
+
+See the {repopath}`NVIDIA Datasetio docs::llama_stack/providers/remote/datasetio/nvidia/README.md` for supported features and example usage.
+
+### Eval API: NeMo Evaluator
+The NeMo Evaluator microservice supports evaluation of LLMs. Launching an Evaluation job with NeMo Evaluator requires an Evaluation Config (an object that contains metadata needed by the job). A Llama Stack Benchmark maps to an Evaluation Config, so registering a Benchmark creates an Evaluation Config in NeMo Evaluator. The `NVIDIA_EVALUATOR_URL` environment variable should point to your NeMo Microservices endpoint.
+
+See the {repopath}`NVIDIA Eval docs::llama_stack/providers/remote/eval/nvidia/README.md` for supported features and example usage.
+
+### Post-Training API: NeMo Customizer
+The NeMo Customizer microservice supports fine-tuning models. You can reference {repopath}`this list of supported models::llama_stack/providers/remote/post_training/nvidia/models.py` that can be fine-tuned using Llama Stack. The `NVIDIA_CUSTOMIZER_URL` environment variable should point to your NeMo Microservices endpoint.
+
+See the {repopath}`NVIDIA Post-Training docs::llama_stack/providers/remote/post_training/nvidia/README.md` for supported features and example usage.
+
+### Safety API: NeMo Guardrails
+The NeMo Guardrails microservice sits between your application and the LLM, and adds checks and content moderation to a model. The `GUARDRAILS_SERVICE_URL` environment variable should point to your NeMo Microservices endpoint.
+
+See the {repopath}`NVIDIA Safety docs::llama_stack/providers/remote/safety/nvidia/README.md` for supported features and example usage.
+
+## Deploying models
+In order to use a registered model with the Llama Stack APIs, ensure the corresponding NIM is deployed to your environment. For example, you can use the NIM Proxy microservice to deploy `meta/llama-3.2-1b-instruct`.
+
+Note: For improved inference speeds, we need to use NIM with `fast_outlines` guided decoding system (specified in the request body). This is the default if you deployed the platform with the NeMo Microservices Helm Chart.
+```sh
+# URL to NeMo NIM Proxy service
+export NEMO_URL="http://nemo.test"
+
+curl --location "$NEMO_URL/v1/deployment/model-deployments" \
+   -H 'accept: application/json' \
+   -H 'Content-Type: application/json' \
+   -d '{
+      "name": "llama-3.2-1b-instruct",
+      "namespace": "meta",
+      "config": {
+         "model": "meta/llama-3.2-1b-instruct",
+         "nim_deployment": {
+            "image_name": "nvcr.io/nim/meta/llama-3.2-1b-instruct",
+            "image_tag": "1.8.3",
+            "pvc_size": "25Gi",
+            "gpu": 1,
+            "additional_envs": {
+               "NIM_GUIDED_DECODING_BACKEND": "fast_outlines"
+            }
+         }
+      }
+   }'
+```
+This NIM deployment should take approximately 10 minutes to go live. [See the docs](https://docs.nvidia.com/nemo/microservices/latest/get-started/tutorials/deploy-nims.html) for more information on how to deploy a NIM and verify it's available for inference.
+
+You can also remove a deployed NIM to free up GPU resources, if needed.
+```sh
+export NEMO_URL="http://nemo.test"
+
+curl -X DELETE "$NEMO_URL/v1/deployment/model-deployments/meta/llama-3.1-8b-instruct"
+```
+
+## Running Llama Stack with NVIDIA
+
+You can do this via venv (build code), or Docker which has a pre-built image.
+
+### Via Docker
+
+This method allows you to get started quickly without having to build the distribution code.
+
+```bash
+LLAMA_STACK_PORT=8321
+docker run \
+  -it \
+  --pull always \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v ./run.yaml:/root/my-run.yaml \
+  llamastack/distribution-nvidia \
+  --config /root/my-run.yaml \
+  --port $LLAMA_STACK_PORT \
+  --env NVIDIA_API_KEY=$NVIDIA_API_KEY
+```
+
+### Via venv
+
+If you've set up your local development environment, you can also build the image using your local virtual environment.
+
+```bash
+INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
+llama stack build --distro nvidia --image-type venv
+llama stack run ./run.yaml \
+  --port 8321 \
+  --env NVIDIA_API_KEY=$NVIDIA_API_KEY \
+  --env INFERENCE_MODEL=$INFERENCE_MODEL
+```
+
+## Example Notebooks
+For examples of how to use the NVIDIA Distribution to run inference, fine-tune, evaluate, and run safety checks on your LLMs, you can reference the example notebooks in {repopath}`docs/notebooks/nvidia`.

scripts/provider_codegen.py

@@ -10,11 +10,11 @@ import sys
 from pathlib import Path
 from typing import Any
 
-from llama_stack.core.distribution import get_provider_registry
-
 from pydantic_core import PydanticUndefined
 from rich.progress import Progress, SpinnerColumn, TextColumn
 
+from llama_stack.core.distribution import get_provider_registry
+
 REPO_ROOT = Path(__file__).parent.parent
 
 
@@ -22,9 +22,7 @@ def get_api_docstring(api_name: str) -> str | None:
     """Extract docstring from the API protocol class."""
     try:
         # Import the API module dynamically
-        api_module = __import__(
+        api_module = __import__(f"llama_stack.apis.{api_name}", fromlist=[api_name.title()])
-            f"llama_stack.apis.{api_name}", fromlist=[api_name.title()]
-        )
 
         # Get the main protocol class (usually capitalized API name)
         protocol_class_name = api_name.title()
@@ -72,10 +70,7 @@ def get_config_class_info(config_class_path: str) -> dict[str, Any]:
                 model_config = config_class.model_config
                 if hasattr(model_config, "extra") and model_config.extra == "allow":
                     accepts_extra_config = True
-                elif (
+                elif isinstance(model_config, dict) and model_config.get("extra") == "allow":
-                    isinstance(model_config, dict)
-                    and model_config.get("extra") == "allow"
-                ):
                     accepts_extra_config = True
 
         fields_info = {}
@@ -84,19 +79,9 @@ def get_config_class_info(config_class_path: str) -> dict[str, Any]:
                 field_type = str(field.annotation) if field.annotation else "Any"
 
                 # this string replace is ridiculous
-                field_type = (
+                field_type = field_type.replace("typing.", "").replace("Optional[", "").replace("]", "")
-                    field_type.replace("typing.", "")
+                field_type = field_type.replace("Annotated[", "").replace("FieldInfo(", "").replace(")", "")
-                    .replace("Optional[", "")
+                field_type = field_type.replace("llama_stack.apis.inference.inference.", "")
-                    .replace("]", "")
-                )
-                field_type = (
-                    field_type.replace("Annotated[", "")
-                    .replace("FieldInfo(", "")
-                    .replace(")", "")
-                )
-                field_type = field_type.replace(
-                    "llama_stack.apis.inference.inference.", ""
-                )
                 field_type = field_type.replace("llama_stack.providers.", "")
 
                 default_value = field.default
@@ -106,10 +91,7 @@ def get_config_class_info(config_class_path: str) -> dict[str, Any]:
                         # HACK ALERT:
                         # If the default value contains a path that looks like it came from RUNTIME_BASE_DIR,
                         # replace it with a generic ~/.llama/ path for documentation
-                        if (
+                        if isinstance(default_value, str) and "/.llama/" in default_value:
-                            isinstance(default_value, str)
-                            and "/.llama/" in default_value
-                        ):
                             if ".llama/" in default_value:
                                 path_part = default_value.split(".llama/")[-1]
                                 default_value = f"~/.llama/{path_part}"
@@ -135,11 +117,7 @@ def get_config_class_info(config_class_path: str) -> dict[str, Any]:
                 lines = source.split("\n")
 
                 for i, line in enumerate(lines):
-                    if (
+                    if "model_config" in line and "ConfigDict" in line and 'extra="allow"' in line:
-                        "model_config" in line
-                        and "ConfigDict" in line
-                        and 'extra="allow"' in line
-                    ):
                         comments = []
                         for j in range(i - 1, -1, -1):
                             stripped = lines[j].strip()
@@ -204,9 +182,7 @@ def generate_provider_docs(progress, provider_spec: Any, api_name: str) -> str:
     # Create sidebar label (clean up provider_type for display)
     sidebar_label = provider_type.replace("::", " - ").replace("_", " ")
     if sidebar_label.startswith("inline - "):
-        sidebar_label = sidebar_label[
+        sidebar_label = sidebar_label[9:].title()  # Remove "inline - " prefix and title case
-            9:
-        ].title()  # Remove "inline - " prefix and title case
     else:
         sidebar_label = sidebar_label.title()
 
@@ -219,7 +195,8 @@ def generate_provider_docs(progress, provider_spec: Any, api_name: str) -> str:
         if "\n" in description.strip():
             md_lines.append("description: |")
             for line in description.strip().split("\n"):
-                md_lines.append(f"  {line}")
+                # Avoid trailing whitespace by only adding spaces to non-empty lines
+                md_lines.append(f"  {line}" if line.strip() else "")
         else:
             # For single line descriptions, format properly for YAML
             clean_desc = description.strip().replace('"', '\\"')
@@ -248,14 +225,10 @@ def generate_provider_docs(progress, provider_spec: Any, api_name: str) -> str:
         for field_name, field_info in config_info["fields"].items():
             field_type = field_info["type"].replace("|", "\\|")
             required = "Yes" if field_info["required"] else "No"
-            default = (
+            default = str(field_info["default"]) if field_info["default"] is not None else ""
-                str(field_info["default"]) if field_info["default"] is not None else ""
-            )
             description_text = field_info["description"] or ""
 
-            md_lines.append(
+            md_lines.append(f"| `{field_name}` | `{field_type}` | {required} | {default} | {description_text} |")
-                f"| `{field_name}` | `{field_type}` | {required} | {default} | {description_text} |"
-            )
 
         md_lines.append("")
 
@@ -297,22 +270,16 @@ def generate_provider_docs(progress, provider_spec: Any, api_name: str) -> str:
                         return obj
 
                 sample_config_dict = convert_pydantic_to_dict(sample_config)
-                md_lines.append(
+                # Strip trailing newlines from yaml.dump to prevent extra blank lines
-                    yaml.dump(
+                yaml_output = yaml.dump(sample_config_dict, default_flow_style=False, sort_keys=False).rstrip()
-                        sample_config_dict, default_flow_style=False, sort_keys=False
+                md_lines.append(yaml_output)
-                    )
-                )
             else:
                 md_lines.append("# No sample configuration available.")
         except Exception as e:
             md_lines.append(f"# Error generating sample config: {str(e)}")
         md_lines.append("```")
-        md_lines.append("")
 
-    if (
+    if hasattr(provider_spec, "deprecation_warning") and provider_spec.deprecation_warning:
-        hasattr(provider_spec, "deprecation_warning")
-        and provider_spec.deprecation_warning
-    ):
         md_lines.append("## Deprecation Notice")
         md_lines.append("")
         md_lines.append(":::warning")
@@ -330,9 +297,7 @@ def generate_provider_docs(progress, provider_spec: Any, api_name: str) -> str:
     return "\n".join(md_lines) + "\n"
 
 
-def generate_index_docs(
+def generate_index_docs(api_name: str, api_docstring: str | None, provider_entries: list) -> str:
-    api_name: str, api_docstring: str | None, provider_entries: list
-) -> str:
     """Generate MDX documentation for the index file."""
     # Create sidebar label for the API
     sidebar_label = api_name.replace("_", " ").title()
@@ -360,9 +325,7 @@ def generate_index_docs(
         md_lines.append(f"{cleaned_docstring}")
         md_lines.append("")
 
-    md_lines.append(
+    md_lines.append(f"This section contains documentation for all available providers for the **{api_name}** API.")
-        f"This section contains documentation for all available providers for the **{api_name}** API."
-    )
     md_lines.append("")
 
     md_lines.append("## Providers")
@@ -373,9 +336,8 @@ def generate_index_docs(
         provider_name = entry["display_name"]
         filename = entry["filename"]
         md_lines.append(f"- [{provider_name}](./{filename})")
-    md_lines.append("")
 
-    return "\n".join(md_lines)
+    return "\n".join(md_lines) + "\n"
 
 
 def process_provider_registry(progress, change_tracker: ChangedPathTracker) -> None:
@@ -411,14 +373,10 @@ def process_provider_registry(progress, change_tracker: ChangedPathTracker) -> N
                 else:
                     display_name = display_name.title()
 
-                provider_entries.append(
+                provider_entries.append({"filename": filename, "display_name": display_name})
-                    {"filename": filename, "display_name": display_name}
-                )
 
             # Generate index file with frontmatter
-            index_content = generate_index_docs(
+            index_content = generate_index_docs(api_name, api_docstring, provider_entries)
-                api_name, api_docstring, provider_entries
-            )
             index_file = doc_output_dir / "index.mdx"
             index_file.write_text(index_content)
             change_tracker.add_paths(index_file)