docs: auto generated documentation for providers (#2543)

# What does this PR do? Simple approach to get some provider pages in the docs. Add or update description fields in the provider configuration class using Pydantic’s Field, ensuring these descriptions are clear and complete, as they will be used to auto-generate provider documentation via ./scripts/distro_codegen.py instead of editing the docs manually. Signed-off-by: Sébastien Han <seb@redhat.com>
2025-07-04 13:15:24 +00:00 · 2025-06-30 15:13:20 +02:00 · 2025-06-30 15:13:20 +02:00 · c9a49a80e8
commit c9a49a80e8
parent 8d8e90d78e
96 changed files with 2562 additions and 65 deletions
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@ -14,7 +14,7 @@ repos:
    -   id: check-added-large-files
        args: ['--maxkb=1000']
    -   id: end-of-file-fixer
-        exclude: '^(.*\.svg)$'
+        exclude: '^(.*\.svg|.*\.md)$'
    -   id: no-commit-to-branch
    -   id: check-yaml
        args: ["--unsafe"]
@ -95,6 +95,15 @@ repos:
        pass_filenames: false
        require_serial: true
        files: ^llama_stack/templates/.*$|^llama_stack/providers/.*/inference/.*/models\.py$
      - id: provider-codegen
        name: Provider Codegen
        additional_dependencies:
          - uv==0.7.8
        entry: uv run --group codegen ./scripts/provider_codegen.py
        language: python
        pass_filenames: false
        require_serial: true
        files: ^llama_stack/providers/.*$
      - id: openapi-codegen
        name: API Spec Codegen
        additional_dependencies:
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@ -139,6 +139,8 @@ uv sync
  justification for bypassing the check.
 * Don't use unicode characters in the codebase. ASCII-only is preferred for compatibility or
  readability reasons.
 * Providers configuration class should be Pydantic Field class. It should have a `description` field
  that describes the configuration. These descriptions will be used to generate the provider documentation.
 ## Common Tasks
@ -157,10 +159,19 @@ cd llama-stack
 LLAMA_STACK_DIR=$(pwd) LLAMA_STACK_CLIENT_DIR=../llama-stack-client-python llama stack build --template <...>
 ```
 ### Updating distribution configurations
-### Updating Provider Configurations
+If you have made changes to a provider's configuration in any form (introducing a new config key, or
 changing models, etc.), you should run `./scripts/distro_codegen.py` to re-generate various YAML
 files as well as the documentation. You should not change `docs/source/.../distributions/` files
 manually as they are auto-generated.
-If you have made changes to a provider's configuration in any form (introducing a new config key, or changing models, etc.), you should run `./scripts/distro_codegen.py` to re-generate various YAML files as well as the documentation. You should not change `docs/source/.../distributions/` files manually as they are auto-generated.
+### Updating the provider documentation
 If you have made changes to a provider's configuration, you should run `./scripts/distro_codegen.py`
 to re-generate the documentation. You should not change `docs/source/.../providers/` files manually
 as they are auto-generated.
 Note that the provider "description" field will be used to generate the provider documentation.
 ### Building the Documentation
--- a/docs/source/getting_started/index.md
+++ b/docs/source/getting_started/index.md
@ -6,7 +6,7 @@ Llama Stack is a stateful service with REST APIs to support the seamless transit
 environments. You can build and test using a local server first and deploy to a hosted endpoint for production.
 In this guide, we'll walk through how to build a RAG application locally using Llama Stack with [Ollama](https://ollama.com/)
-as the inference [provider](../providers/index.md#inference) for a Llama Model.
+as the inference [provider](../providers/inference/index) for a Llama Model.
 #### Step 1: Install and setup
 1. Install [uv](https://docs.astral.sh/uv/)
--- a/docs/source/providers/agents/index.md
+++ b/docs/source/providers/agents/index.md
@ -0,0 +1,5 @@
 # Agents Providers
 This section contains documentation for all available providers for the **agents** API.
 - [inline::meta-reference](inline_meta-reference.md)
--- a/docs/source/providers/agents/inline_meta-reference.md
+++ b/docs/source/providers/agents/inline_meta-reference.md
@ -0,0 +1,26 @@
 # inline::meta-reference
 ## Description
 Meta's reference implementation of an agent system that can use tools, access vector databases, and perform complex reasoning tasks.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `persistence_store` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
 | `responses_store` | `utils.sqlstore.sqlstore.SqliteSqlStoreConfig \| utils.sqlstore.sqlstore.PostgresSqlStoreConfig` | No | sqlite |  |
 ## Sample Configuration
 ```yaml
 persistence_store:
  type: sqlite
  namespace: null
  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/agents_store.db
 responses_store:
  type: sqlite
  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/responses_store.db
 ```
--- a/docs/source/providers/datasetio/index.md
+++ b/docs/source/providers/datasetio/index.md
@ -0,0 +1,7 @@
 # Datasetio Providers
 This section contains documentation for all available providers for the **datasetio** API.
 - [inline::localfs](inline_localfs.md)
 - [remote::huggingface](remote_huggingface.md)
 - [remote::nvidia](remote_nvidia.md)
--- a/docs/source/providers/datasetio/inline_localfs.md
+++ b/docs/source/providers/datasetio/inline_localfs.md
@ -0,0 +1,22 @@
 # inline::localfs
 ## Description
 Local filesystem-based dataset I/O provider for reading and writing datasets to local storage.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
 ## Sample Configuration
 ```yaml
 kvstore:
  type: sqlite
  namespace: null
  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/localfs_datasetio.db
 ```
--- a/docs/source/providers/datasetio/remote_huggingface.md
+++ b/docs/source/providers/datasetio/remote_huggingface.md
@ -0,0 +1,22 @@
 # remote::huggingface
 ## Description
 HuggingFace datasets provider for accessing and managing datasets from the HuggingFace Hub.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
 ## Sample Configuration
 ```yaml
 kvstore:
  type: sqlite
  namespace: null
  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/huggingface_datasetio.db
 ```
--- a/docs/source/providers/datasetio/remote_nvidia.md
+++ b/docs/source/providers/datasetio/remote_nvidia.md
@ -0,0 +1,25 @@
 # remote::nvidia
 ## Description
 NVIDIA's dataset I/O provider for accessing datasets from NVIDIA's data platform.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | The NVIDIA API key. |
 | `dataset_namespace` | `str \| None` | No | default | The NVIDIA dataset namespace. |
 | `project_id` | `str \| None` | No | test-project | The NVIDIA project ID. |
 | `datasets_url` | `<class 'str'>` | No | http://nemo.test | Base URL for the NeMo Dataset API |
 ## Sample Configuration
 ```yaml
 api_key: ${env.NVIDIA_API_KEY:+}
 dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
 project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
 datasets_url: ${env.NVIDIA_DATASETS_URL:=http://nemo.test}
 ```
--- a/docs/source/providers/eval/index.md
+++ b/docs/source/providers/eval/index.md
@ -0,0 +1,6 @@
 # Eval Providers
 This section contains documentation for all available providers for the **eval** API.
 - [inline::meta-reference](inline_meta-reference.md)
 - [remote::nvidia](remote_nvidia.md)
--- a/docs/source/providers/eval/inline_meta-reference.md
+++ b/docs/source/providers/eval/inline_meta-reference.md
@ -0,0 +1,22 @@
 # inline::meta-reference
 ## Description
 Meta's reference implementation of evaluation tasks with support for multiple languages and evaluation metrics.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
 ## Sample Configuration
 ```yaml
 kvstore:
  type: sqlite
  namespace: null
  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/meta_reference_eval.db
 ```
--- a/docs/source/providers/eval/remote_nvidia.md
+++ b/docs/source/providers/eval/remote_nvidia.md
@ -0,0 +1,19 @@
 # remote::nvidia
 ## Description
 NVIDIA's evaluation provider for running evaluation tasks on NVIDIA's platform.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `evaluator_url` | `<class 'str'>` | No | http://0.0.0.0:7331 | The url for accessing the evaluator service |
 ## Sample Configuration
 ```yaml
 evaluator_url: ${env.NVIDIA_EVALUATOR_URL:=http://localhost:7331}
 ```
--- a/docs/source/providers/files/index.md
+++ b/docs/source/providers/files/index.md
@ -0,0 +1,5 @@
 # Files Providers
 This section contains documentation for all available providers for the **files** API.
 - [inline::localfs](inline_localfs.md)
--- a/docs/source/providers/files/inline_localfs.md
+++ b/docs/source/providers/files/inline_localfs.md
@ -0,0 +1,24 @@
 # inline::localfs
 ## Description
 Local filesystem-based file storage provider for managing files and documents locally.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `storage_dir` | `<class 'str'>` | No | PydanticUndefined | Directory to store uploaded files |
 | `metadata_store` | `utils.sqlstore.sqlstore.SqliteSqlStoreConfig \| utils.sqlstore.sqlstore.PostgresSqlStoreConfig` | No | sqlite | SQL store configuration for file metadata |
 | `ttl_secs` | `<class 'int'>` | No | 31536000 |  |
 ## Sample Configuration
 ```yaml
 storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/dummy/files}
 metadata_store:
  type: sqlite
  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/files_metadata.db
 ```
--- a/docs/source/providers/index.md
+++ b/docs/source/providers/index.md
@ -18,60 +18,92 @@ Llama Stack supports external providers that live outside of the main codebase.
 ## Agents
 Run multi-step agentic workflows with LLMs with tool usage, memory (RAG), etc.
 ```{toctree}
 :maxdepth: 1
 agents/index
 ```
 ## DatasetIO
 Interfaces with datasets and data loaders.
 ## Eval
 Generates outputs (via Inference or Agents) and perform scoring.
 ## Inference
 Runs inference with an LLM.
 ## Post Training
 Fine-tunes a model.
 #### Post Training Providers
 The following providers are available for Post Training:
 ```{toctree}
 :maxdepth: 1
-external
+datasetio/index
-post_training/huggingface
+```
-post_training/torchtune
+
-post_training/nvidia_nemo
+## Eval
 Generates outputs (via Inference or Agents) and perform scoring.
 ```{toctree}
 :maxdepth: 1
 eval/index
 ```
 ## Inference
 Runs inference with an LLM.
 ```{toctree}
 :maxdepth: 1
 inference/index
 ```
 ## Post Training
 Fine-tunes a model.
 ```{toctree}
 :maxdepth: 1
 post_training/index
 ```
 ## Safety
 Applies safety policies to the output at a Systems (not only model) level.
 ```{toctree}
 :maxdepth: 1
 safety/index
 ```
 ## Scoring
 Evaluates the outputs of the system.
 ```{toctree}
 :maxdepth: 1
 scoring/index
 ```
 ## Telemetry
 Collects telemetry data from the system.
 ```{toctree}
 :maxdepth: 1
 telemetry/index
 ```
 ## Tool Runtime
 Is associated with the ToolGroup resouces.
 ```{toctree}
 :maxdepth: 1
 tool_runtime/index
 ```
 ## Vector IO
 Vector IO refers to operations on vector databases, such as adding documents, searching, and deleting documents.
 Vector IO plays a crucial role in [Retreival Augmented Generation (RAG)](../..//building_applications/rag), where the vector
 io and database are used to store and retrieve documents for retrieval.
 #### Vector IO Providers
 The following providers (i.e., databases) are available for Vector IO:
 ```{toctree}
 :maxdepth: 1
-external
+vector_io/index
 vector_io/faiss
 vector_io/sqlite-vec
 vector_io/chromadb
 vector_io/pgvector
 vector_io/qdrant
 vector_io/milvus
 vector_io/weaviate
 ```
--- a/docs/source/providers/inference/index.md
+++ b/docs/source/providers/inference/index.md
@ -0,0 +1,32 @@
 # Inference Providers
 This section contains documentation for all available providers for the **inference** API.
 - [inline::meta-reference](inline_meta-reference.md)
 - [inline::sentence-transformers](inline_sentence-transformers.md)
 - [inline::vllm](inline_vllm.md)
 - [remote::anthropic](remote_anthropic.md)
 - [remote::bedrock](remote_bedrock.md)
 - [remote::cerebras](remote_cerebras.md)
 - [remote::cerebras-openai-compat](remote_cerebras-openai-compat.md)
 - [remote::databricks](remote_databricks.md)
 - [remote::fireworks](remote_fireworks.md)
 - [remote::fireworks-openai-compat](remote_fireworks-openai-compat.md)
 - [remote::gemini](remote_gemini.md)
 - [remote::groq](remote_groq.md)
 - [remote::groq-openai-compat](remote_groq-openai-compat.md)
 - [remote::hf::endpoint](remote_hf_endpoint.md)
 - [remote::hf::serverless](remote_hf_serverless.md)
 - [remote::llama-openai-compat](remote_llama-openai-compat.md)
 - [remote::nvidia](remote_nvidia.md)
 - [remote::ollama](remote_ollama.md)
 - [remote::openai](remote_openai.md)
 - [remote::passthrough](remote_passthrough.md)
 - [remote::runpod](remote_runpod.md)
 - [remote::sambanova](remote_sambanova.md)
 - [remote::sambanova-openai-compat](remote_sambanova-openai-compat.md)
 - [remote::tgi](remote_tgi.md)
 - [remote::together](remote_together.md)
 - [remote::together-openai-compat](remote_together-openai-compat.md)
 - [remote::vllm](remote_vllm.md)
 - [remote::watsonx](remote_watsonx.md)
--- a/docs/source/providers/inference/inline_meta-reference.md
+++ b/docs/source/providers/inference/inline_meta-reference.md
@ -0,0 +1,32 @@
 # inline::meta-reference
 ## Description
 Meta's reference implementation of inference with support for various model formats and optimization techniques.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `model` | `str \| None` | No |  |  |
 | `torch_seed` | `int \| None` | No |  |  |
 | `max_seq_len` | `<class 'int'>` | No | 4096 |  |
 | `max_batch_size` | `<class 'int'>` | No | 1 |  |
 | `model_parallel_size` | `int \| None` | No |  |  |
 | `create_distributed_process_group` | `<class 'bool'>` | No | True |  |
 | `checkpoint_dir` | `str \| None` | No |  |  |
 | `quantization` | `Bf16QuantizationConfig \| Fp8QuantizationConfig \| Int4QuantizationConfig, annotation=NoneType, required=True, discriminator='type'` | No |  |  |
 ## Sample Configuration
 ```yaml
 model: Llama3.2-3B-Instruct
 checkpoint_dir: ${env.CHECKPOINT_DIR:=null}
 quantization:
  type: ${env.QUANTIZATION_TYPE:=bf16}
 model_parallel_size: ${env.MODEL_PARALLEL_SIZE:=0}
 max_batch_size: ${env.MAX_BATCH_SIZE:=1}
 max_seq_len: ${env.MAX_SEQ_LEN:=4096}
 ```
--- a/docs/source/providers/inference/inline_sentence-transformers.md
+++ b/docs/source/providers/inference/inline_sentence-transformers.md
@ -0,0 +1,13 @@
 # inline::sentence-transformers
 ## Description
 Sentence Transformers inference provider for text embeddings and similarity search.
 ## Sample Configuration
 ```yaml
 {}
 ```
--- a/docs/source/providers/inference/inline_vllm.md
+++ b/docs/source/providers/inference/inline_vllm.md
@ -0,0 +1,29 @@
 # inline::vllm
 ## Description
 vLLM inference provider for high-performance model serving with PagedAttention and continuous batching.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `tensor_parallel_size` | `<class 'int'>` | No | 1 | Number of tensor parallel replicas (number of GPUs to use). |
 | `max_tokens` | `<class 'int'>` | No | 4096 | Maximum number of tokens to generate. |
 | `max_model_len` | `<class 'int'>` | No | 4096 | Maximum context length to use during serving. |
 | `max_num_seqs` | `<class 'int'>` | No | 4 | Maximum parallel batch size for generation. |
 | `enforce_eager` | `<class 'bool'>` | No | False | Whether to use eager mode for inference (otherwise cuda graphs are used). |
 | `gpu_memory_utilization` | `<class 'float'>` | No | 0.3 | How much GPU memory will be allocated when this provider has finished loading, including memory that was already allocated before loading. |
 ## Sample Configuration
 ```yaml
 tensor_parallel_size: ${env.TENSOR_PARALLEL_SIZE:=1}
 max_tokens: ${env.MAX_TOKENS:=4096}
 max_model_len: ${env.MAX_MODEL_LEN:=4096}
 max_num_seqs: ${env.MAX_NUM_SEQS:=4}
 enforce_eager: ${env.ENFORCE_EAGER:=False}
 gpu_memory_utilization: ${env.GPU_MEMORY_UTILIZATION:=0.3}
 ```
--- a/docs/source/providers/inference/remote_anthropic.md
+++ b/docs/source/providers/inference/remote_anthropic.md
@ -0,0 +1,19 @@
 # remote::anthropic
 ## Description
 Anthropic inference provider for accessing Claude models and Anthropic's AI services.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | API key for Anthropic models |
 ## Sample Configuration
 ```yaml
 api_key: ${env.ANTHROPIC_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_bedrock.md
+++ b/docs/source/providers/inference/remote_bedrock.md
@ -0,0 +1,28 @@
 # remote::bedrock
 ## Description
 AWS Bedrock inference provider for accessing various AI models through AWS's managed service.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `aws_access_key_id` | `str \| None` | No |  | The AWS access key to use. Default use environment variable: AWS_ACCESS_KEY_ID |
 | `aws_secret_access_key` | `str \| None` | No |  | The AWS secret access key to use. Default use environment variable: AWS_SECRET_ACCESS_KEY |
 | `aws_session_token` | `str \| None` | No |  | The AWS session token to use. Default use environment variable: AWS_SESSION_TOKEN |
 | `region_name` | `str \| None` | No |  | The default AWS Region to use, for example, us-west-1 or us-west-2.Default use environment variable: AWS_DEFAULT_REGION |
 | `profile_name` | `str \| None` | No |  | The profile name that contains credentials to use.Default use environment variable: AWS_PROFILE |
 | `total_max_attempts` | `int \| None` | No |  | An integer representing the maximum number of attempts that will be made for a single request, including the initial attempt. Default use environment variable: AWS_MAX_ATTEMPTS |
 | `retry_mode` | `str \| None` | No |  | A string representing the type of retries Boto3 will perform.Default use environment variable: AWS_RETRY_MODE |
 | `connect_timeout` | `float \| None` | No | 60 | The time in seconds till a timeout exception is thrown when attempting to make a connection. The default is 60 seconds. |
 | `read_timeout` | `float \| None` | No | 60 | The time in seconds till a timeout exception is thrown when attempting to read from a connection.The default is 60 seconds. |
 | `session_ttl` | `int \| None` | No | 3600 | The time in seconds till a session expires. The default is 3600 seconds (1 hour). |
 ## Sample Configuration
 ```yaml
 {}
 ```
--- a/docs/source/providers/inference/remote_cerebras-openai-compat.md
+++ b/docs/source/providers/inference/remote_cerebras-openai-compat.md
@ -0,0 +1,21 @@
 # remote::cerebras-openai-compat
 ## Description
 Cerebras OpenAI-compatible provider for using Cerebras models with OpenAI API format.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | The Cerebras API key |
 | `openai_compat_api_base` | `<class 'str'>` | No | https://api.cerebras.ai/v1 | The URL for the Cerebras API server |
 ## Sample Configuration
 ```yaml
 openai_compat_api_base: https://api.cerebras.ai/v1
 api_key: ${env.CEREBRAS_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_cerebras.md
+++ b/docs/source/providers/inference/remote_cerebras.md
@ -0,0 +1,21 @@
 # remote::cerebras
 ## Description
 Cerebras inference provider for running models on Cerebras Cloud platform.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `base_url` | `<class 'str'>` | No | https://api.cerebras.ai | Base URL for the Cerebras API |
 | `api_key` | `pydantic.types.SecretStr \| None` | No |  | Cerebras API Key |
 ## Sample Configuration
 ```yaml
 base_url: https://api.cerebras.ai
 api_key: ${env.CEREBRAS_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_databricks.md
+++ b/docs/source/providers/inference/remote_databricks.md
@ -0,0 +1,21 @@
 # remote::databricks
 ## Description
 Databricks inference provider for running models on Databricks' unified analytics platform.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `<class 'str'>` | No |  | The URL for the Databricks model serving endpoint |
 | `api_token` | `<class 'str'>` | No |  | The Databricks API token |
 ## Sample Configuration
 ```yaml
 url: ${env.DATABRICKS_URL}
 api_token: ${env.DATABRICKS_API_TOKEN}
 ```
--- a/docs/source/providers/inference/remote_fireworks-openai-compat.md
+++ b/docs/source/providers/inference/remote_fireworks-openai-compat.md
@ -0,0 +1,21 @@
 # remote::fireworks-openai-compat
 ## Description
 Fireworks AI OpenAI-compatible provider for using Fireworks models with OpenAI API format.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | The Fireworks API key |
 | `openai_compat_api_base` | `<class 'str'>` | No | https://api.fireworks.ai/inference/v1 | The URL for the Fireworks API server |
 ## Sample Configuration
 ```yaml
 openai_compat_api_base: https://api.fireworks.ai/inference/v1
 api_key: ${env.FIREWORKS_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_fireworks.md
+++ b/docs/source/providers/inference/remote_fireworks.md
@ -0,0 +1,21 @@
 # remote::fireworks
 ## Description
 Fireworks AI inference provider for Llama models and other AI models on the Fireworks platform.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `<class 'str'>` | No | https://api.fireworks.ai/inference/v1 | The URL for the Fireworks server |
 | `api_key` | `pydantic.types.SecretStr \| None` | No |  | The Fireworks.ai API Key |
 ## Sample Configuration
 ```yaml
 url: https://api.fireworks.ai/inference/v1
 api_key: ${env.FIREWORKS_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_gemini.md
+++ b/docs/source/providers/inference/remote_gemini.md
@ -0,0 +1,19 @@
 # remote::gemini
 ## Description
 Google Gemini inference provider for accessing Gemini models and Google's AI services.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | API key for Gemini models |
 ## Sample Configuration
 ```yaml
 api_key: ${env.GEMINI_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_groq-openai-compat.md
+++ b/docs/source/providers/inference/remote_groq-openai-compat.md
@ -0,0 +1,21 @@
 # remote::groq-openai-compat
 ## Description
 Groq OpenAI-compatible provider for using Groq models with OpenAI API format.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | The Groq API key |
 | `openai_compat_api_base` | `<class 'str'>` | No | https://api.groq.com/openai/v1 | The URL for the Groq API server |
 ## Sample Configuration
 ```yaml
 openai_compat_api_base: https://api.groq.com/openai/v1
 api_key: ${env.GROQ_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_groq.md
+++ b/docs/source/providers/inference/remote_groq.md
@ -0,0 +1,21 @@
 # remote::groq
 ## Description
 Groq inference provider for ultra-fast inference using Groq's LPU technology.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | The Groq API key |
 | `url` | `<class 'str'>` | No | https://api.groq.com | The URL for the Groq AI server |
 ## Sample Configuration
 ```yaml
 url: https://api.groq.com
 api_key: ${env.GROQ_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_hf_endpoint.md
+++ b/docs/source/providers/inference/remote_hf_endpoint.md
@ -0,0 +1,21 @@
 # remote::hf::endpoint
 ## Description
 HuggingFace Inference Endpoints provider for dedicated model serving.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `endpoint_name` | `<class 'str'>` | No | PydanticUndefined | 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 \| None` | No |  | Your Hugging Face user access token (will default to locally saved token if not provided) |
 ## Sample Configuration
 ```yaml
 endpoint_name: ${env.INFERENCE_ENDPOINT_NAME}
 api_token: ${env.HF_API_TOKEN}
 ```
--- a/docs/source/providers/inference/remote_hf_serverless.md
+++ b/docs/source/providers/inference/remote_hf_serverless.md
@ -0,0 +1,21 @@
 # remote::hf::serverless
 ## Description
 HuggingFace Inference API serverless provider for on-demand model inference.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `huggingface_repo` | `<class 'str'>` | No | PydanticUndefined | The model ID of the model on the Hugging Face Hub (e.g. 'meta-llama/Meta-Llama-3.1-70B-Instruct') |
 | `api_token` | `pydantic.types.SecretStr \| None` | No |  | Your Hugging Face user access token (will default to locally saved token if not provided) |
 ## Sample Configuration
 ```yaml
 huggingface_repo: ${env.INFERENCE_MODEL}
 api_token: ${env.HF_API_TOKEN}
 ```
--- a/docs/source/providers/inference/remote_llama-openai-compat.md
+++ b/docs/source/providers/inference/remote_llama-openai-compat.md
@ -0,0 +1,21 @@
 # remote::llama-openai-compat
 ## Description
 Llama OpenAI-compatible provider for using Llama models with OpenAI API format.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | The Llama API key |
 | `openai_compat_api_base` | `<class 'str'>` | No | https://api.llama.com/compat/v1/ | The URL for the Llama API server |
 ## Sample Configuration
 ```yaml
 openai_compat_api_base: https://api.llama.com/compat/v1/
 api_key: ${env.LLAMA_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_nvidia.md
+++ b/docs/source/providers/inference/remote_nvidia.md
@ -0,0 +1,24 @@
 # remote::nvidia
 ## Description
 NVIDIA inference provider for accessing NVIDIA NIM models and AI services.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `<class 'str'>` | No | https://integrate.api.nvidia.com | A base url for accessing the NVIDIA NIM |
 | `api_key` | `pydantic.types.SecretStr \| None` | No |  | The NVIDIA API key, only needed of using the hosted service |
 | `timeout` | `<class 'int'>` | No | 60 | Timeout for the HTTP requests |
 | `append_api_version` | `<class 'bool'>` | No | True | When set to false, the API version will not be appended to the base_url. By default, it is true. |
 ## Sample Configuration
 ```yaml
 url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
 api_key: ${env.NVIDIA_API_KEY:+}
 append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
 ```
--- a/docs/source/providers/inference/remote_ollama.md
+++ b/docs/source/providers/inference/remote_ollama.md
@ -0,0 +1,21 @@
 # remote::ollama
 ## Description
 Ollama inference provider for running local models through the Ollama runtime.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `<class 'str'>` | No | http://localhost:11434 |  |
 | `raise_on_connect_error` | `<class 'bool'>` | No | True |  |
 ## Sample Configuration
 ```yaml
 url: ${env.OLLAMA_URL:=http://localhost:11434}
 raise_on_connect_error: true
 ```
--- a/docs/source/providers/inference/remote_openai.md
+++ b/docs/source/providers/inference/remote_openai.md
@ -0,0 +1,19 @@
 # remote::openai
 ## Description
 OpenAI inference provider for accessing GPT models and other OpenAI services.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | API key for OpenAI models |
 ## Sample Configuration
 ```yaml
 api_key: ${env.OPENAI_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_passthrough.md
+++ b/docs/source/providers/inference/remote_passthrough.md
@ -0,0 +1,21 @@
 # remote::passthrough
 ## Description
 Passthrough inference provider for connecting to any external inference service not directly supported.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `<class 'str'>` | No |  | The URL for the passthrough endpoint |
 | `api_key` | `pydantic.types.SecretStr \| None` | No |  | API Key for the passthrouth endpoint |
 ## Sample Configuration
 ```yaml
 url: ${env.PASSTHROUGH_URL}
 api_key: ${env.PASSTHROUGH_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_runpod.md
+++ b/docs/source/providers/inference/remote_runpod.md
@ -0,0 +1,21 @@
 # remote::runpod
 ## Description
 RunPod inference provider for running models on RunPod's cloud GPU platform.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `str \| None` | No |  | The URL for the Runpod model serving endpoint |
 | `api_token` | `str \| None` | No |  | The API token |
 ## Sample Configuration
 ```yaml
 url: ${env.RUNPOD_URL:+}
 api_token: ${env.RUNPOD_API_TOKEN:+}
 ```
--- a/docs/source/providers/inference/remote_sambanova-openai-compat.md
+++ b/docs/source/providers/inference/remote_sambanova-openai-compat.md
@ -0,0 +1,21 @@
 # remote::sambanova-openai-compat
 ## Description
 SambaNova OpenAI-compatible provider for using SambaNova models with OpenAI API format.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | The SambaNova API key |
 | `openai_compat_api_base` | `<class 'str'>` | No | https://api.sambanova.ai/v1 | The URL for the SambaNova API server |
 ## Sample Configuration
 ```yaml
 openai_compat_api_base: https://api.sambanova.ai/v1
 api_key: ${env.SAMBANOVA_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_sambanova.md
+++ b/docs/source/providers/inference/remote_sambanova.md
@ -0,0 +1,21 @@
 # remote::sambanova
 ## Description
 SambaNova inference provider for running models on SambaNova's dataflow architecture.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `<class 'str'>` | No | https://api.sambanova.ai/v1 | The URL for the SambaNova AI server |
 | `api_key` | `pydantic.types.SecretStr \| None` | No |  | The SambaNova cloud API Key |
 ## Sample Configuration
 ```yaml
 url: https://api.sambanova.ai/v1
 api_key: ${env.SAMBANOVA_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_tgi.md
+++ b/docs/source/providers/inference/remote_tgi.md
@ -0,0 +1,19 @@
 # remote::tgi
 ## Description
 Text Generation Inference (TGI) provider for HuggingFace model serving.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `<class 'str'>` | No | PydanticUndefined | The URL for the TGI serving endpoint |
 ## Sample Configuration
 ```yaml
 url: ${env.TGI_URL}
 ```
--- a/docs/source/providers/inference/remote_together-openai-compat.md
+++ b/docs/source/providers/inference/remote_together-openai-compat.md
@ -0,0 +1,21 @@
 # remote::together-openai-compat
 ## Description
 Together AI OpenAI-compatible provider for using Together models with OpenAI API format.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | The Together API key |
 | `openai_compat_api_base` | `<class 'str'>` | No | https://api.together.xyz/v1 | The URL for the Together API server |
 ## Sample Configuration
 ```yaml
 openai_compat_api_base: https://api.together.xyz/v1
 api_key: ${env.TOGETHER_API_KEY}
 ```
--- a/docs/source/providers/inference/remote_together.md
+++ b/docs/source/providers/inference/remote_together.md
@ -0,0 +1,21 @@
 # remote::together
 ## Description
 Together AI inference provider for open-source models and collaborative AI development.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `<class 'str'>` | No | https://api.together.xyz/v1 | The URL for the Together AI server |
 | `api_key` | `pydantic.types.SecretStr \| None` | No |  | The Together AI API Key |
 ## Sample Configuration
 ```yaml
 url: https://api.together.xyz/v1
 api_key: ${env.TOGETHER_API_KEY:+}
 ```
--- a/docs/source/providers/inference/remote_vllm.md
+++ b/docs/source/providers/inference/remote_vllm.md
@ -0,0 +1,25 @@
 # remote::vllm
 ## Description
 Remote vLLM inference provider for connecting to vLLM servers.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `str \| None` | No |  | The URL for the vLLM model serving endpoint |
 | `max_tokens` | `<class 'int'>` | No | 4096 | Maximum number of tokens to generate. |
 | `api_token` | `str \| None` | No | fake | The API token |
 | `tls_verify` | `bool \| str` | No | True | Whether to verify TLS certificates. Can be a boolean or a path to a CA certificate file. |
 ## Sample Configuration
 ```yaml
 url: ${env.VLLM_URL}
 max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
 api_token: ${env.VLLM_API_TOKEN:=fake}
 tls_verify: ${env.VLLM_TLS_VERIFY:=true}
 ```
--- a/docs/source/providers/inference/remote_watsonx.md
+++ b/docs/source/providers/inference/remote_watsonx.md
@ -0,0 +1,24 @@
 # remote::watsonx
 ## Description
 IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform.
 ## Configuration
 | 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 |
 | `project_id` | `str \| None` | No |  | The Project ID key, only needed of using the hosted service |
 | `timeout` | `<class 'int'>` | No | 60 | Timeout for the HTTP requests |
 ## Sample Configuration
 ```yaml
 url: ${env.WATSONX_BASE_URL:=https://us-south.ml.cloud.ibm.com}
 api_key: ${env.WATSONX_API_KEY:+}
 project_id: ${env.WATSONX_PROJECT_ID:+}
 ```
--- a/docs/source/providers/post_training/index.md
+++ b/docs/source/providers/post_training/index.md
@ -0,0 +1,7 @@
 # Post_Training Providers
 This section contains documentation for all available providers for the **post_training** API.
 - [inline::huggingface](inline_huggingface.md)
 - [inline::torchtune](inline_torchtune.md)
 - [remote::nvidia](remote_nvidia.md)
--- a/docs/source/providers/post_training/inline_huggingface.md
+++ b/docs/source/providers/post_training/inline_huggingface.md
@ -0,0 +1,36 @@
 # inline::huggingface
 ## Description
 HuggingFace-based post-training provider for fine-tuning models using the HuggingFace ecosystem.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `device` | `<class 'str'>` | No | cuda |  |
 | `distributed_backend` | `Literal['fsdp', 'deepspeed'` | No |  |  |
 | `checkpoint_format` | `Literal['full_state', 'huggingface'` | No | huggingface |  |
 | `chat_template` | `<class 'str'>` | No | <|user|>
 {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 |  |
 | `logging_steps` | `<class 'int'>` | No | 10 |  |
 | `warmup_ratio` | `<class 'float'>` | No | 0.1 |  |
 | `weight_decay` | `<class 'float'>` | No | 0.01 |  |
 | `dataloader_num_workers` | `<class 'int'>` | No | 4 |  |
 | `dataloader_pin_memory` | `<class 'bool'>` | No | True |  |
 ## Sample Configuration
 ```yaml
 checkpoint_format: huggingface
 distributed_backend: null
 device: cpu
 ```
--- a/docs/source/providers/post_training/inline_torchtune.md
+++ b/docs/source/providers/post_training/inline_torchtune.md
@ -0,0 +1,20 @@
 # inline::torchtune
 ## Description
 TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `torch_seed` | `int \| None` | No |  |  |
 | `checkpoint_format` | `Literal['meta', 'huggingface'` | No | meta |  |
 ## Sample Configuration
 ```yaml
 checkpoint_format: meta
 ```
--- a/docs/source/providers/post_training/remote_nvidia.md
+++ b/docs/source/providers/post_training/remote_nvidia.md
@ -0,0 +1,28 @@
 # remote::nvidia
 ## Description
 NVIDIA's post-training provider for fine-tuning models on NVIDIA's platform.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | The NVIDIA API key. |
 | `dataset_namespace` | `str \| None` | No | default | The NVIDIA dataset namespace. |
 | `project_id` | `str \| None` | No | test-example-model@v1 | The NVIDIA project ID. |
 | `customizer_url` | `str \| None` | No |  | Base URL for the NeMo Customizer API |
 | `timeout` | `<class 'int'>` | No | 300 | Timeout for the NVIDIA Post Training API |
 | `max_retries` | `<class 'int'>` | No | 3 | Maximum number of retries for the NVIDIA Post Training API |
 | `output_model_dir` | `<class 'str'>` | No | test-example-model@v1 | Directory to save the output model |
 ## Sample Configuration
 ```yaml
 api_key: ${env.NVIDIA_API_KEY:+}
 dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
 project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
 customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:=http://nemo.test}
 ```
--- a/docs/source/providers/safety/index.md
+++ b/docs/source/providers/safety/index.md
@ -0,0 +1,10 @@
 # Safety Providers
 This section contains documentation for all available providers for the **safety** API.
 - [inline::code-scanner](inline_code-scanner.md)
 - [inline::llama-guard](inline_llama-guard.md)
 - [inline::prompt-guard](inline_prompt-guard.md)
 - [remote::bedrock](remote_bedrock.md)
 - [remote::nvidia](remote_nvidia.md)
 - [remote::sambanova](remote_sambanova.md)
--- a/docs/source/providers/safety/inline_code-scanner.md
+++ b/docs/source/providers/safety/inline_code-scanner.md
@ -0,0 +1,13 @@
 # inline::code-scanner
 ## Description
 Code Scanner safety provider for detecting security vulnerabilities and unsafe code patterns.
 ## Sample Configuration
 ```yaml
 {}
 ```
--- a/docs/source/providers/safety/inline_llama-guard.md
+++ b/docs/source/providers/safety/inline_llama-guard.md
@ -0,0 +1,19 @@
 # inline::llama-guard
 ## Description
 Llama Guard safety provider for content moderation and safety filtering using Meta's Llama Guard model.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `excluded_categories` | `list[str` | No | [] |  |
 ## Sample Configuration
 ```yaml
 excluded_categories: []
 ```
--- a/docs/source/providers/safety/inline_prompt-guard.md
+++ b/docs/source/providers/safety/inline_prompt-guard.md
@ -0,0 +1,19 @@
 # inline::prompt-guard
 ## Description
 Prompt Guard safety provider for detecting and filtering unsafe prompts and content.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `guard_type` | `<class 'str'>` | No | injection |  |
 ## Sample Configuration
 ```yaml
 guard_type: injection
 ```
--- a/docs/source/providers/safety/remote_bedrock.md
+++ b/docs/source/providers/safety/remote_bedrock.md
@ -0,0 +1,28 @@
 # remote::bedrock
 ## Description
 AWS Bedrock safety provider for content moderation using AWS's safety services.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `aws_access_key_id` | `str \| None` | No |  | The AWS access key to use. Default use environment variable: AWS_ACCESS_KEY_ID |
 | `aws_secret_access_key` | `str \| None` | No |  | The AWS secret access key to use. Default use environment variable: AWS_SECRET_ACCESS_KEY |
 | `aws_session_token` | `str \| None` | No |  | The AWS session token to use. Default use environment variable: AWS_SESSION_TOKEN |
 | `region_name` | `str \| None` | No |  | The default AWS Region to use, for example, us-west-1 or us-west-2.Default use environment variable: AWS_DEFAULT_REGION |
 | `profile_name` | `str \| None` | No |  | The profile name that contains credentials to use.Default use environment variable: AWS_PROFILE |
 | `total_max_attempts` | `int \| None` | No |  | An integer representing the maximum number of attempts that will be made for a single request, including the initial attempt. Default use environment variable: AWS_MAX_ATTEMPTS |
 | `retry_mode` | `str \| None` | No |  | A string representing the type of retries Boto3 will perform.Default use environment variable: AWS_RETRY_MODE |
 | `connect_timeout` | `float \| None` | No | 60 | The time in seconds till a timeout exception is thrown when attempting to make a connection. The default is 60 seconds. |
 | `read_timeout` | `float \| None` | No | 60 | The time in seconds till a timeout exception is thrown when attempting to read from a connection.The default is 60 seconds. |
 | `session_ttl` | `int \| None` | No | 3600 | The time in seconds till a session expires. The default is 3600 seconds (1 hour). |
 ## Sample Configuration
 ```yaml
 {}
 ```
--- a/docs/source/providers/safety/remote_nvidia.md
+++ b/docs/source/providers/safety/remote_nvidia.md
@ -0,0 +1,21 @@
 # remote::nvidia
 ## Description
 NVIDIA's safety provider for content moderation and safety filtering.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `guardrails_service_url` | `<class 'str'>` | No | http://0.0.0.0:7331 | The url for accessing the Guardrails service |
 | `config_id` | `str \| None` | No | self-check | Guardrails configuration ID to use from the Guardrails configuration store |
 ## Sample Configuration
 ```yaml
 guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:=http://localhost:7331}
 config_id: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:=self-check}
 ```
--- a/docs/source/providers/safety/remote_sambanova.md
+++ b/docs/source/providers/safety/remote_sambanova.md
@ -0,0 +1,21 @@
 # remote::sambanova
 ## Description
 SambaNova's safety provider for content moderation and safety filtering.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `<class 'str'>` | No | https://api.sambanova.ai/v1 | The URL for the SambaNova AI server |
 | `api_key` | `pydantic.types.SecretStr \| None` | No |  | The SambaNova cloud API Key |
 ## Sample Configuration
 ```yaml
 url: https://api.sambanova.ai/v1
 api_key: ${env.SAMBANOVA_API_KEY}
 ```
--- a/docs/source/providers/scoring/index.md
+++ b/docs/source/providers/scoring/index.md
@ -0,0 +1,7 @@
 # Scoring Providers
 This section contains documentation for all available providers for the **scoring** API.
 - [inline::basic](inline_basic.md)
 - [inline::braintrust](inline_braintrust.md)
 - [inline::llm-as-judge](inline_llm-as-judge.md)
--- a/docs/source/providers/scoring/inline_basic.md
+++ b/docs/source/providers/scoring/inline_basic.md
@ -0,0 +1,13 @@
 # inline::basic
 ## Description
 Basic scoring provider for simple evaluation metrics and scoring functions.
 ## Sample Configuration
 ```yaml
 {}
 ```
--- a/docs/source/providers/scoring/inline_braintrust.md
+++ b/docs/source/providers/scoring/inline_braintrust.md
@ -0,0 +1,19 @@
 # inline::braintrust
 ## Description
 Braintrust scoring provider for evaluation and scoring using the Braintrust platform.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `openai_api_key` | `str \| None` | No |  | The OpenAI API Key |
 ## Sample Configuration
 ```yaml
 openai_api_key: ${env.OPENAI_API_KEY:+}
 ```
--- a/docs/source/providers/scoring/inline_llm-as-judge.md
+++ b/docs/source/providers/scoring/inline_llm-as-judge.md
@ -0,0 +1,13 @@
 # inline::llm-as-judge
 ## Description
 LLM-as-judge scoring provider that uses language models to evaluate and score responses.
 ## Sample Configuration
 ```yaml
 {}
 ```
--- a/docs/source/providers/telemetry/index.md
+++ b/docs/source/providers/telemetry/index.md
@ -0,0 +1,5 @@
 # Telemetry Providers
 This section contains documentation for all available providers for the **telemetry** API.
 - [inline::meta-reference](inline_meta-reference.md)
--- a/docs/source/providers/telemetry/inline_meta-reference.md
+++ b/docs/source/providers/telemetry/inline_meta-reference.md
@ -0,0 +1,25 @@
 # inline::meta-reference
 ## Description
 Meta's reference implementation of telemetry and observability using OpenTelemetry.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `otel_trace_endpoint` | `str \| None` | No |  | The OpenTelemetry collector endpoint URL for traces |
 | `otel_metric_endpoint` | `str \| None` | No |  | The OpenTelemetry collector endpoint URL for metrics |
 | `service_name` | `<class 'str'>` | No |  | The service name to use for telemetry |
 | `sinks` | `list[inline.telemetry.meta_reference.config.TelemetrySink` | No | [<TelemetrySink.CONSOLE: 'console'>, <TelemetrySink.SQLITE: 'sqlite'>] | List of telemetry sinks to enable (possible values: otel, sqlite, console) |
 | `sqlite_db_path` | `<class 'str'>` | No | ~/.llama/runtime/trace_store.db | The path to the SQLite database to use for storing traces |
 ## Sample Configuration
 ```yaml
 service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
 sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
 sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/trace_store.db
 ```
--- a/docs/source/providers/tool_runtime/index.md
+++ b/docs/source/providers/tool_runtime/index.md
@ -0,0 +1,10 @@
 # Tool_Runtime Providers
 This section contains documentation for all available providers for the **tool_runtime** API.
 - [inline::rag-runtime](inline_rag-runtime.md)
 - [remote::bing-search](remote_bing-search.md)
 - [remote::brave-search](remote_brave-search.md)
 - [remote::model-context-protocol](remote_model-context-protocol.md)
 - [remote::tavily-search](remote_tavily-search.md)
 - [remote::wolfram-alpha](remote_wolfram-alpha.md)
--- a/docs/source/providers/tool_runtime/inline_rag-runtime.md
+++ b/docs/source/providers/tool_runtime/inline_rag-runtime.md
@ -0,0 +1,13 @@
 # inline::rag-runtime
 ## Description
 RAG (Retrieval-Augmented Generation) tool runtime for document ingestion, chunking, and semantic search.
 ## Sample Configuration
 ```yaml
 {}
 ```
--- a/docs/source/providers/tool_runtime/remote_bing-search.md
+++ b/docs/source/providers/tool_runtime/remote_bing-search.md
@ -0,0 +1,20 @@
 # remote::bing-search
 ## Description
 Bing Search tool for web search capabilities using Microsoft's search engine.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  |  |
 | `top_k` | `<class 'int'>` | No | 3 |  |
 ## Sample Configuration
 ```yaml
 api_key: ${env.BING_API_KEY:}
 ```
--- a/docs/source/providers/tool_runtime/remote_brave-search.md
+++ b/docs/source/providers/tool_runtime/remote_brave-search.md
@ -0,0 +1,21 @@
 # remote::brave-search
 ## Description
 Brave Search tool for web search capabilities with privacy-focused results.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | The Brave Search API Key |
 | `max_results` | `<class 'int'>` | No | 3 | The maximum number of results to return |
 ## Sample Configuration
 ```yaml
 api_key: ${env.BRAVE_SEARCH_API_KEY:+}
 max_results: 3
 ```
--- a/docs/source/providers/tool_runtime/remote_model-context-protocol.md
+++ b/docs/source/providers/tool_runtime/remote_model-context-protocol.md
@ -0,0 +1,13 @@
 # remote::model-context-protocol
 ## Description
 Model Context Protocol (MCP) tool for standardized tool calling and context management.
 ## Sample Configuration
 ```yaml
 {}
 ```
--- a/docs/source/providers/tool_runtime/remote_tavily-search.md
+++ b/docs/source/providers/tool_runtime/remote_tavily-search.md
@ -0,0 +1,21 @@
 # remote::tavily-search
 ## Description
 Tavily Search tool for AI-optimized web search with structured results.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  | The Tavily Search API Key |
 | `max_results` | `<class 'int'>` | No | 3 | The maximum number of results to return |
 ## Sample Configuration
 ```yaml
 api_key: ${env.TAVILY_SEARCH_API_KEY:+}
 max_results: 3
 ```
--- a/docs/source/providers/tool_runtime/remote_wolfram-alpha.md
+++ b/docs/source/providers/tool_runtime/remote_wolfram-alpha.md
@ -0,0 +1,19 @@
 # remote::wolfram-alpha
 ## Description
 Wolfram Alpha tool for computational knowledge and mathematical calculations.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `api_key` | `str \| None` | No |  |  |
 ## Sample Configuration
 ```yaml
 api_key: ${env.WOLFRAM_ALPHA_API_KEY:+}
 ```
--- a/docs/source/providers/vector_io/index.md
+++ b/docs/source/providers/vector_io/index.md
@ -0,0 +1,16 @@
 # Vector_Io Providers
 This section contains documentation for all available providers for the **vector_io** API.
 - [inline::chromadb](inline_chromadb.md)
 - [inline::faiss](inline_faiss.md)
 - [inline::meta-reference](inline_meta-reference.md)
 - [inline::milvus](inline_milvus.md)
 - [inline::qdrant](inline_qdrant.md)
 - [inline::sqlite-vec](inline_sqlite-vec.md)
 - [inline::sqlite_vec](inline_sqlite_vec.md)
 - [remote::chromadb](remote_chromadb.md)
 - [remote::milvus](remote_milvus.md)
 - [remote::pgvector](remote_pgvector.md)
 - [remote::qdrant](remote_qdrant.md)
 - [remote::weaviate](remote_weaviate.md)
--- a/docs/source/providers/vector_io/inline_chromadb.md
+++ b/docs/source/providers/vector_io/inline_chromadb.md
@ -0,0 +1,52 @@
 # 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 |
 |-------|------|----------|---------|-------------|
 | `db_path` | `<class 'str'>` | No | PydanticUndefined |  |
 ## Sample Configuration
 ```yaml
 db_path: ${env.CHROMADB_PATH}
 ```
--- a/docs/source/providers/vector_io/inline_faiss.md
+++ b/docs/source/providers/vector_io/inline_faiss.md
@ -1,7 +1,7 @@
---
+# inline::faiss
-orphan: true
+
---
+## Description
-# Faiss
+
 [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.
@ -31,3 +31,21 @@ 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 |
 |-------|------|----------|---------|-------------|
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
 ## Sample Configuration
 ```yaml
 kvstore:
  type: sqlite
  namespace: null
  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/faiss_store.db
 ```
--- a/docs/source/providers/vector_io/inline_meta-reference.md
+++ b/docs/source/providers/vector_io/inline_meta-reference.md
@ -0,0 +1,26 @@
 # inline::meta-reference
 ## Description
 Meta's reference implementation of a vector database.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
 ## Sample Configuration
 ```yaml
 kvstore:
  type: sqlite
  namespace: null
  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/faiss_store.db
 ```
 ## Deprecation Notice
 ⚠️ **Warning**: Please use the `inline::faiss` provider instead.
--- a/docs/source/providers/vector_io/inline_milvus.md
+++ b/docs/source/providers/vector_io/inline_milvus.md
@ -0,0 +1,26 @@
 # inline::milvus
 ## Description
 Please refer to the remote provider documentation.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `db_path` | `<class 'str'>` | No | PydanticUndefined |  |
 | `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
 ## Sample Configuration
 ```yaml
 db_path: ${env.MILVUS_DB_PATH:=~/.llama/dummy/milvus.db}
 kvstore:
  type: sqlite
  namespace: null
  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/${env.MILVUS_KVSTORE_DB_PATH:=~/.llama/dummy/milvus_registry.db}
 ```
--- a/docs/source/providers/vector_io/inline_qdrant.md
+++ b/docs/source/providers/vector_io/inline_qdrant.md
@ -1,7 +1,7 @@
---
+# inline::qdrant
-orphan: true
+
---
+## Description
-# Qdrant
+
 [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.
@ -44,3 +44,18 @@ 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 |
 |-------|------|----------|---------|-------------|
 | `path` | `<class 'str'>` | No | PydanticUndefined |  |
 ## Sample Configuration
 ```yaml
 path: ${env.QDRANT_PATH:=~/.llama/~/.llama/dummy}/qdrant.db
 ```
--- a/docs/source/providers/vector_io/inline_sqlite-vec.md
+++ b/docs/source/providers/vector_io/inline_sqlite-vec.md
@ -1,7 +1,7 @@
---
+# inline::sqlite-vec
-orphan: true
+
---
+## Description
-# SQLite-Vec
+
 [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.
@ -199,3 +199,18 @@ pip install sqlite-vec
 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 |
 |-------|------|----------|---------|-------------|
 | `db_path` | `<class 'str'>` | No | PydanticUndefined |  |
 ## Sample Configuration
 ```yaml
 db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/sqlite_vec.db
 ```
--- a/docs/source/providers/vector_io/inline_sqlite_vec.md
+++ b/docs/source/providers/vector_io/inline_sqlite_vec.md
@ -0,0 +1,25 @@
 # inline::sqlite_vec
 ## Description
 Please refer to the sqlite-vec provider documentation.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `db_path` | `<class 'str'>` | No | PydanticUndefined |  |
 ## Sample Configuration
 ```yaml
 db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/sqlite_vec.db
 ```
 ## Deprecation Notice
 ⚠️ **Warning**: Please use the `inline::sqlite-vec` provider (notice the hyphen instead of underscore) instead.
--- a/docs/source/providers/vector_io/remote_chromadb.md
+++ b/docs/source/providers/vector_io/remote_chromadb.md
@ -1,7 +1,7 @@
---
+# remote::chromadb
-orphan: true
+
---
+## Description
-# Chroma
+
 [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.
@ -34,3 +34,18 @@ 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 |
 |-------|------|----------|---------|-------------|
 | `url` | `str \| None` | No | PydanticUndefined |  |
 ## Sample Configuration
 ```yaml
 url: ${env.CHROMADB_URL}
 ```
--- a/docs/source/providers/vector_io/remote_milvus.md
+++ b/docs/source/providers/vector_io/remote_milvus.md
@ -1,7 +1,7 @@
---
+# remote::milvus
-orphan: true
+
---
+## Description
-# Milvus
+
 [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.
@ -96,7 +96,7 @@ vector_io:
 #### 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).
+- **`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).
@ -105,3 +105,24 @@ vector_io:
 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 | PydanticUndefined | The URI of the Milvus server |
 | `token` | `str \| None` | No | PydanticUndefined | The token of the Milvus server |
 | `consistency_level` | `<class 'str'>` | No | Strong | The consistency level of the Milvus server |
 | `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
 uri: ${env.MILVUS_ENDPOINT}
 token: ${env.MILVUS_TOKEN}
 ```
--- a/docs/source/providers/vector_io/remote_pgvector.md
+++ b/docs/source/providers/vector_io/remote_pgvector.md
@ -1,7 +1,7 @@
---
+# remote::pgvector
-orphan: true
+
---
+## Description
-# Postgres PGVector
+
 [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.
@ -29,3 +29,26 @@ 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 |
 |-------|------|----------|---------|-------------|
 | `host` | `str \| None` | No | localhost |  |
 | `port` | `int \| None` | No | 5432 |  |
 | `db` | `str \| None` | No | postgres |  |
 | `user` | `str \| None` | No | postgres |  |
 | `password` | `str \| None` | No | mysecretpassword |  |
 ## Sample Configuration
 ```yaml
 host: ${env.PGVECTOR_HOST:=localhost}
 port: ${env.PGVECTOR_PORT:=5432}
 db: ${env.PGVECTOR_DB}
 user: ${env.PGVECTOR_USER}
 password: ${env.PGVECTOR_PASSWORD}
 ```
--- a/docs/source/providers/vector_io/remote_qdrant.md
+++ b/docs/source/providers/vector_io/remote_qdrant.md
@ -0,0 +1,30 @@
 # remote::qdrant
 ## Description
 Please refer to the inline provider documentation.
 ## Configuration
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `location` | `str \| None` | No |  |  |
 | `url` | `str \| None` | No |  |  |
 | `port` | `int \| None` | No | 6333 |  |
 | `grpc_port` | `<class 'int'>` | No | 6334 |  |
 | `prefer_grpc` | `<class 'bool'>` | No | False |  |
 | `https` | `bool \| None` | No |  |  |
 | `api_key` | `str \| None` | No |  |  |
 | `prefix` | `str \| None` | No |  |  |
 | `timeout` | `int \| None` | No |  |  |
 | `host` | `str \| None` | No |  |  |
 ## Sample Configuration
 ```yaml
 api_key: ${env.QDRANT_API_KEY}
 ```
--- a/docs/source/providers/vector_io/remote_weaviate.md
+++ b/docs/source/providers/vector_io/remote_weaviate.md
@ -1,7 +1,7 @@
---
+# remote::weaviate
-orphan: true
+
---
+## Description
-# Weaviate
+
 [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.
@ -31,3 +31,12 @@ To install Weaviate see the [Weaviate quickstart documentation](https://weaviate
 ## Documentation
 See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more details about Weaviate in general.
 ## Sample Configuration
 ```yaml
 {}
 ```
--- a/llama_stack/providers/datatypes.py
+++ b/llama_stack/providers/datatypes.py
@ -141,6 +141,12 @@ Fully-qualified name of the module to import. The module is expected to have:
    provider_data_validator: str | None = Field(
        default=None,
    )
    description: str | None = Field(
        default=None,
        description="""
 A description of the provider. This is used to display in the documentation.
 """,
    )
@json_schema_type
@ -167,6 +173,12 @@ Fully-qualified name of the module to import. The module is expected to have:
    provider_data_validator: str | None = Field(
        default=None,
    )
    description: str | None = Field(
        default=None,
        description="""
 A description of the provider. This is used to display in the documentation.
 """,
    )
 class RemoteProviderConfig(BaseModel):
--- a/llama_stack/providers/inline/telemetry/meta_reference/config.py
+++ b/llama_stack/providers/inline/telemetry/meta_reference/config.py
@ -38,7 +38,7 @@ class TelemetryConfig(BaseModel):
        description="List of telemetry sinks to enable (possible values: otel, sqlite, console)",
    )
    sqlite_db_path: str = Field(
-        default=(RUNTIME_BASE_DIR / "trace_store.db").as_posix(),
+        default_factory=lambda: (RUNTIME_BASE_DIR / "trace_store.db").as_posix(),
        description="The path to the SQLite database to use for storing traces",
    )
--- a/llama_stack/providers/registry/agents.py
+++ b/llama_stack/providers/registry/agents.py
@ -35,5 +35,6 @@ def available_providers() -> list[ProviderSpec]:
                Api.tool_runtime,
                Api.tool_groups,
            ],
            description="Meta's reference implementation of an agent system that can use tools, access vector databases, and perform complex reasoning tasks.",
        ),
    ]
--- a/llama_stack/providers/registry/datasetio.py
+++ b/llama_stack/providers/registry/datasetio.py
@ -23,6 +23,7 @@ def available_providers() -> list[ProviderSpec]:
            module="llama_stack.providers.inline.datasetio.localfs",
            config_class="llama_stack.providers.inline.datasetio.localfs.LocalFSDatasetIOConfig",
            api_dependencies=[],
            description="Local filesystem-based dataset I/O provider for reading and writing datasets to local storage.",
        ),
        remote_provider_spec(
            api=Api.datasetio,
@ -33,6 +34,7 @@ def available_providers() -> list[ProviderSpec]:
                ],
                module="llama_stack.providers.remote.datasetio.huggingface",
                config_class="llama_stack.providers.remote.datasetio.huggingface.HuggingfaceDatasetIOConfig",
                description="HuggingFace datasets provider for accessing and managing datasets from the HuggingFace Hub.",
            ),
        ),
        remote_provider_spec(
@ -44,6 +46,7 @@ def available_providers() -> list[ProviderSpec]:
                ],
                module="llama_stack.providers.remote.datasetio.nvidia",
                config_class="llama_stack.providers.remote.datasetio.nvidia.NvidiaDatasetIOConfig",
                description="NVIDIA's dataset I/O provider for accessing datasets from NVIDIA's data platform.",
            ),
        ),
    ]
--- a/llama_stack/providers/registry/eval.py
+++ b/llama_stack/providers/registry/eval.py
@ -23,6 +23,7 @@ def available_providers() -> list[ProviderSpec]:
                Api.inference,
                Api.agents,
            ],
            description="Meta's reference implementation of evaluation tasks with support for multiple languages and evaluation metrics.",
        ),
        remote_provider_spec(
            api=Api.eval,
@ -33,6 +34,7 @@ def available_providers() -> list[ProviderSpec]:
                ],
                module="llama_stack.providers.remote.eval.nvidia",
                config_class="llama_stack.providers.remote.eval.nvidia.NVIDIAEvalConfig",
                description="NVIDIA's evaluation provider for running evaluation tasks on NVIDIA's platform.",
            ),
            api_dependencies=[
                Api.datasetio,
--- a/llama_stack/providers/registry/files.py
+++ b/llama_stack/providers/registry/files.py
@ -21,5 +21,6 @@ def available_providers() -> list[ProviderSpec]:
            pip_packages=sql_store_pip_packages,
            module="llama_stack.providers.inline.files.localfs",
            config_class="llama_stack.providers.inline.files.localfs.config.LocalfsFilesImplConfig",
            description="Local filesystem-based file storage provider for managing files and documents locally.",
        ),
    ]
--- a/llama_stack/providers/registry/inference.py
+++ b/llama_stack/providers/registry/inference.py
@ -35,6 +35,7 @@ def available_providers() -> list[ProviderSpec]:
            pip_packages=META_REFERENCE_DEPS,
            module="llama_stack.providers.inline.inference.meta_reference",
            config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
            description="Meta's reference implementation of inference with support for various model formats and optimization techniques.",
        ),
        InlineProviderSpec(
            api=Api.inference,
@ -44,6 +45,7 @@ def available_providers() -> list[ProviderSpec]:
            ],
            module="llama_stack.providers.inline.inference.vllm",
            config_class="llama_stack.providers.inline.inference.vllm.VLLMConfig",
            description="vLLM inference provider for high-performance model serving with PagedAttention and continuous batching.",
        ),
        InlineProviderSpec(
            api=Api.inference,
@ -54,6 +56,7 @@ def available_providers() -> list[ProviderSpec]:
            ],
            module="llama_stack.providers.inline.inference.sentence_transformers",
            config_class="llama_stack.providers.inline.inference.sentence_transformers.config.SentenceTransformersInferenceConfig",
            description="Sentence Transformers inference provider for text embeddings and similarity search.",
        ),
        remote_provider_spec(
            api=Api.inference,
@ -64,6 +67,7 @@ def available_providers() -> list[ProviderSpec]:
                ],
                module="llama_stack.providers.remote.inference.cerebras",
                config_class="llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig",
                description="Cerebras inference provider for running models on Cerebras Cloud platform.",
            ),
        ),
        remote_provider_spec(
@ -73,6 +77,7 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["ollama", "aiohttp", "h11>=0.16.0"],
                config_class="llama_stack.providers.remote.inference.ollama.OllamaImplConfig",
                module="llama_stack.providers.remote.inference.ollama",
                description="Ollama inference provider for running local models through the Ollama runtime.",
            ),
        ),
        remote_provider_spec(
@ -82,6 +87,7 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["openai"],
                module="llama_stack.providers.remote.inference.vllm",
                config_class="llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig",
                description="Remote vLLM inference provider for connecting to vLLM servers.",
            ),
        ),
        remote_provider_spec(
@ -91,6 +97,7 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["huggingface_hub", "aiohttp"],
                module="llama_stack.providers.remote.inference.tgi",
                config_class="llama_stack.providers.remote.inference.tgi.TGIImplConfig",
                description="Text Generation Inference (TGI) provider for HuggingFace model serving.",
            ),
        ),
        remote_provider_spec(
@ -100,6 +107,7 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["huggingface_hub", "aiohttp"],
                module="llama_stack.providers.remote.inference.tgi",
                config_class="llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig",
                description="HuggingFace Inference API serverless provider for on-demand model inference.",
            ),
        ),
        remote_provider_spec(
@ -109,6 +117,7 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["huggingface_hub", "aiohttp"],
                module="llama_stack.providers.remote.inference.tgi",
                config_class="llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig",
                description="HuggingFace Inference Endpoints provider for dedicated model serving.",
            ),
        ),
        remote_provider_spec(
@ -121,6 +130,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.fireworks",
                config_class="llama_stack.providers.remote.inference.fireworks.FireworksImplConfig",
                provider_data_validator="llama_stack.providers.remote.inference.fireworks.FireworksProviderDataValidator",
                description="Fireworks AI inference provider for Llama models and other AI models on the Fireworks platform.",
            ),
        ),
        remote_provider_spec(
@ -133,6 +143,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.together",
                config_class="llama_stack.providers.remote.inference.together.TogetherImplConfig",
                provider_data_validator="llama_stack.providers.remote.inference.together.TogetherProviderDataValidator",
                description="Together AI inference provider for open-source models and collaborative AI development.",
            ),
        ),
        remote_provider_spec(
@ -142,6 +153,7 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["boto3"],
                module="llama_stack.providers.remote.inference.bedrock",
                config_class="llama_stack.providers.remote.inference.bedrock.BedrockConfig",
                description="AWS Bedrock inference provider for accessing various AI models through AWS's managed service.",
            ),
        ),
        remote_provider_spec(
@ -153,6 +165,7 @@ def available_providers() -> list[ProviderSpec]:
                ],
                module="llama_stack.providers.remote.inference.databricks",
                config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig",
                description="Databricks inference provider for running models on Databricks' unified analytics platform.",
            ),
        ),
        remote_provider_spec(
@ -164,6 +177,7 @@ def available_providers() -> list[ProviderSpec]:
                ],
                module="llama_stack.providers.remote.inference.nvidia",
                config_class="llama_stack.providers.remote.inference.nvidia.NVIDIAConfig",
                description="NVIDIA inference provider for accessing NVIDIA NIM models and AI services.",
            ),
        ),
        remote_provider_spec(
@ -173,6 +187,7 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["openai"],
                module="llama_stack.providers.remote.inference.runpod",
                config_class="llama_stack.providers.remote.inference.runpod.RunpodImplConfig",
                description="RunPod inference provider for running models on RunPod's cloud GPU platform.",
            ),
        ),
        remote_provider_spec(
@ -183,6 +198,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.openai",
                config_class="llama_stack.providers.remote.inference.openai.OpenAIConfig",
                provider_data_validator="llama_stack.providers.remote.inference.openai.config.OpenAIProviderDataValidator",
                description="OpenAI inference provider for accessing GPT models and other OpenAI services.",
            ),
        ),
        remote_provider_spec(
@ -193,6 +209,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.anthropic",
                config_class="llama_stack.providers.remote.inference.anthropic.AnthropicConfig",
                provider_data_validator="llama_stack.providers.remote.inference.anthropic.config.AnthropicProviderDataValidator",
                description="Anthropic inference provider for accessing Claude models and Anthropic's AI services.",
            ),
        ),
        remote_provider_spec(
@ -203,6 +220,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.gemini",
                config_class="llama_stack.providers.remote.inference.gemini.GeminiConfig",
                provider_data_validator="llama_stack.providers.remote.inference.gemini.config.GeminiProviderDataValidator",
                description="Google Gemini inference provider for accessing Gemini models and Google's AI services.",
            ),
        ),
        remote_provider_spec(
@ -213,6 +231,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.groq",
                config_class="llama_stack.providers.remote.inference.groq.GroqConfig",
                provider_data_validator="llama_stack.providers.remote.inference.groq.config.GroqProviderDataValidator",
                description="Groq inference provider for ultra-fast inference using Groq's LPU technology.",
            ),
        ),
        remote_provider_spec(
@ -223,6 +242,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.fireworks_openai_compat",
                config_class="llama_stack.providers.remote.inference.fireworks_openai_compat.config.FireworksCompatConfig",
                provider_data_validator="llama_stack.providers.remote.inference.fireworks_openai_compat.config.FireworksProviderDataValidator",
                description="Fireworks AI OpenAI-compatible provider for using Fireworks models with OpenAI API format.",
            ),
        ),
        remote_provider_spec(
@ -233,6 +253,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.llama_openai_compat",
                config_class="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaCompatConfig",
                provider_data_validator="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaProviderDataValidator",
                description="Llama OpenAI-compatible provider for using Llama models with OpenAI API format.",
            ),
        ),
        remote_provider_spec(
@ -243,6 +264,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.together_openai_compat",
                config_class="llama_stack.providers.remote.inference.together_openai_compat.config.TogetherCompatConfig",
                provider_data_validator="llama_stack.providers.remote.inference.together_openai_compat.config.TogetherProviderDataValidator",
                description="Together AI OpenAI-compatible provider for using Together models with OpenAI API format.",
            ),
        ),
        remote_provider_spec(
@ -253,6 +275,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.groq_openai_compat",
                config_class="llama_stack.providers.remote.inference.groq_openai_compat.config.GroqCompatConfig",
                provider_data_validator="llama_stack.providers.remote.inference.groq_openai_compat.config.GroqProviderDataValidator",
                description="Groq OpenAI-compatible provider for using Groq models with OpenAI API format.",
            ),
        ),
        remote_provider_spec(
@ -263,6 +286,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.sambanova_openai_compat",
                config_class="llama_stack.providers.remote.inference.sambanova_openai_compat.config.SambaNovaCompatConfig",
                provider_data_validator="llama_stack.providers.remote.inference.sambanova_openai_compat.config.SambaNovaProviderDataValidator",
                description="SambaNova OpenAI-compatible provider for using SambaNova models with OpenAI API format.",
            ),
        ),
        remote_provider_spec(
@ -273,6 +297,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.cerebras_openai_compat",
                config_class="llama_stack.providers.remote.inference.cerebras_openai_compat.config.CerebrasCompatConfig",
                provider_data_validator="llama_stack.providers.remote.inference.cerebras_openai_compat.config.CerebrasProviderDataValidator",
                description="Cerebras OpenAI-compatible provider for using Cerebras models with OpenAI API format.",
            ),
        ),
        remote_provider_spec(
@ -283,6 +308,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.sambanova",
                config_class="llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig",
                provider_data_validator="llama_stack.providers.remote.inference.sambanova.config.SambaNovaProviderDataValidator",
                description="SambaNova inference provider for running models on SambaNova's dataflow architecture.",
            ),
        ),
        remote_provider_spec(
@ -293,6 +319,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.passthrough",
                config_class="llama_stack.providers.remote.inference.passthrough.PassthroughImplConfig",
                provider_data_validator="llama_stack.providers.remote.inference.passthrough.PassthroughProviderDataValidator",
                description="Passthrough inference provider for connecting to any external inference service not directly supported.",
            ),
        ),
        remote_provider_spec(
@ -303,6 +330,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.inference.watsonx",
                config_class="llama_stack.providers.remote.inference.watsonx.WatsonXConfig",
                provider_data_validator="llama_stack.providers.remote.inference.watsonx.WatsonXProviderDataValidator",
                description="IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform.",
            ),
        ),
    ]
--- a/llama_stack/providers/registry/post_training.py
+++ b/llama_stack/providers/registry/post_training.py
@ -20,6 +20,7 @@ def available_providers() -> list[ProviderSpec]:
                Api.datasetio,
                Api.datasets,
            ],
            description="TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework.",
        ),
        InlineProviderSpec(
            api=Api.post_training,
@ -31,6 +32,7 @@ def available_providers() -> list[ProviderSpec]:
                Api.datasetio,
                Api.datasets,
            ],
            description="HuggingFace-based post-training provider for fine-tuning models using the HuggingFace ecosystem.",
        ),
        remote_provider_spec(
            api=Api.post_training,
@ -39,6 +41,7 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["requests", "aiohttp"],
                module="llama_stack.providers.remote.post_training.nvidia",
                config_class="llama_stack.providers.remote.post_training.nvidia.NvidiaPostTrainingConfig",
                description="NVIDIA's post-training provider for fine-tuning models on NVIDIA's platform.",
            ),
        ),
    ]
--- a/llama_stack/providers/registry/safety.py
+++ b/llama_stack/providers/registry/safety.py
@ -25,6 +25,7 @@ def available_providers() -> list[ProviderSpec]:
            ],
            module="llama_stack.providers.inline.safety.prompt_guard",
            config_class="llama_stack.providers.inline.safety.prompt_guard.PromptGuardConfig",
            description="Prompt Guard safety provider for detecting and filtering unsafe prompts and content.",
        ),
        InlineProviderSpec(
            api=Api.safety,
@ -35,6 +36,7 @@ def available_providers() -> list[ProviderSpec]:
            api_dependencies=[
                Api.inference,
            ],
            description="Llama Guard safety provider for content moderation and safety filtering using Meta's Llama Guard model.",
        ),
        InlineProviderSpec(
            api=Api.safety,
@ -44,6 +46,7 @@ def available_providers() -> list[ProviderSpec]:
            ],
            module="llama_stack.providers.inline.safety.code_scanner",
            config_class="llama_stack.providers.inline.safety.code_scanner.CodeScannerConfig",
            description="Code Scanner safety provider for detecting security vulnerabilities and unsafe code patterns.",
        ),
        remote_provider_spec(
            api=Api.safety,
@ -52,6 +55,7 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["boto3"],
                module="llama_stack.providers.remote.safety.bedrock",
                config_class="llama_stack.providers.remote.safety.bedrock.BedrockSafetyConfig",
                description="AWS Bedrock safety provider for content moderation using AWS's safety services.",
            ),
        ),
        remote_provider_spec(
@ -61,6 +65,7 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["requests"],
                module="llama_stack.providers.remote.safety.nvidia",
                config_class="llama_stack.providers.remote.safety.nvidia.NVIDIASafetyConfig",
                description="NVIDIA's safety provider for content moderation and safety filtering.",
            ),
        ),
        remote_provider_spec(
@ -71,6 +76,7 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.safety.sambanova",
                config_class="llama_stack.providers.remote.safety.sambanova.SambaNovaSafetyConfig",
                provider_data_validator="llama_stack.providers.remote.safety.sambanova.config.SambaNovaProviderDataValidator",
                description="SambaNova's safety provider for content moderation and safety filtering.",
            ),
        ),
    ]
--- a/llama_stack/providers/registry/scoring.py
+++ b/llama_stack/providers/registry/scoring.py
@ -20,6 +20,7 @@ def available_providers() -> list[ProviderSpec]:
                Api.datasetio,
                Api.datasets,
            ],
            description="Basic scoring provider for simple evaluation metrics and scoring functions.",
        ),
        InlineProviderSpec(
            api=Api.scoring,
@ -32,6 +33,7 @@ def available_providers() -> list[ProviderSpec]:
                Api.datasets,
                Api.inference,
            ],
            description="LLM-as-judge scoring provider that uses language models to evaluate and score responses.",
        ),
        InlineProviderSpec(
            api=Api.scoring,
@ -44,5 +46,6 @@ def available_providers() -> list[ProviderSpec]:
                Api.datasets,
            ],
            provider_data_validator="llama_stack.providers.inline.scoring.braintrust.BraintrustProviderDataValidator",
            description="Braintrust scoring provider for evaluation and scoring using the Braintrust platform.",
        ),
    ]
--- a/llama_stack/providers/registry/telemetry.py
+++ b/llama_stack/providers/registry/telemetry.py
@ -24,5 +24,6 @@ def available_providers() -> list[ProviderSpec]:
            optional_api_dependencies=[Api.datasetio],
            module="llama_stack.providers.inline.telemetry.meta_reference",
            config_class="llama_stack.providers.inline.telemetry.meta_reference.config.TelemetryConfig",
            description="Meta's reference implementation of telemetry and observability using OpenTelemetry.",
        ),
    ]
--- a/llama_stack/providers/registry/tool_runtime.py
+++ b/llama_stack/providers/registry/tool_runtime.py
@ -33,6 +33,7 @@ def available_providers() -> list[ProviderSpec]:
            module="llama_stack.providers.inline.tool_runtime.rag",
            config_class="llama_stack.providers.inline.tool_runtime.rag.config.RagToolRuntimeConfig",
            api_dependencies=[Api.vector_io, Api.inference],
            description="RAG (Retrieval-Augmented Generation) tool runtime for document ingestion, chunking, and semantic search.",
        ),
        remote_provider_spec(
            api=Api.tool_runtime,
@ -42,6 +43,7 @@ def available_providers() -> list[ProviderSpec]:
                config_class="llama_stack.providers.remote.tool_runtime.brave_search.config.BraveSearchToolConfig",
                pip_packages=["requests"],
                provider_data_validator="llama_stack.providers.remote.tool_runtime.brave_search.BraveSearchToolProviderDataValidator",
                description="Brave Search tool for web search capabilities with privacy-focused results.",
            ),
        ),
        remote_provider_spec(
@ -52,6 +54,7 @@ def available_providers() -> list[ProviderSpec]:
                config_class="llama_stack.providers.remote.tool_runtime.bing_search.config.BingSearchToolConfig",
                pip_packages=["requests"],
                provider_data_validator="llama_stack.providers.remote.tool_runtime.bing_search.BingSearchToolProviderDataValidator",
                description="Bing Search tool for web search capabilities using Microsoft's search engine.",
            ),
        ),
        remote_provider_spec(
@ -62,6 +65,7 @@ def available_providers() -> list[ProviderSpec]:
                config_class="llama_stack.providers.remote.tool_runtime.tavily_search.config.TavilySearchToolConfig",
                pip_packages=["requests"],
                provider_data_validator="llama_stack.providers.remote.tool_runtime.tavily_search.TavilySearchToolProviderDataValidator",
                description="Tavily Search tool for AI-optimized web search with structured results.",
            ),
        ),
        remote_provider_spec(
@ -72,6 +76,7 @@ def available_providers() -> list[ProviderSpec]:
                config_class="llama_stack.providers.remote.tool_runtime.wolfram_alpha.config.WolframAlphaToolConfig",
                pip_packages=["requests"],
                provider_data_validator="llama_stack.providers.remote.tool_runtime.wolfram_alpha.WolframAlphaToolProviderDataValidator",
                description="Wolfram Alpha tool for computational knowledge and mathematical calculations.",
            ),
        ),
        remote_provider_spec(
@ -82,6 +87,7 @@ def available_providers() -> list[ProviderSpec]:
                config_class="llama_stack.providers.remote.tool_runtime.model_context_protocol.config.MCPProviderConfig",
                pip_packages=["mcp"],
                provider_data_validator="llama_stack.providers.remote.tool_runtime.model_context_protocol.config.MCPProviderDataValidator",
                description="Model Context Protocol (MCP) tool for standardized tool calling and context management.",
            ),
        ),
    ]
--- a/llama_stack/providers/registry/vector_io.py
+++ b/llama_stack/providers/registry/vector_io.py
@ -25,6 +25,7 @@ def available_providers() -> list[ProviderSpec]:
            deprecation_warning="Please use the `inline::faiss` provider instead.",
            api_dependencies=[Api.inference],
            optional_api_dependencies=[Api.files],
            description="Meta's reference implementation of a vector database.",
        ),
        InlineProviderSpec(
            api=Api.vector_io,
@ -34,6 +35,36 @@ def available_providers() -> list[ProviderSpec]:
            config_class="llama_stack.providers.inline.vector_io.faiss.FaissVectorIOConfig",
            api_dependencies=[Api.inference],
            optional_api_dependencies=[Api.files],
            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
 ## 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.
 """,
        ),
        # NOTE: sqlite-vec cannot be bundled into the container image because it does not have a
        # source distribution and the wheels are not available for all platforms.
@ -45,6 +76,204 @@ def available_providers() -> list[ProviderSpec]:
            config_class="llama_stack.providers.inline.vector_io.sqlite_vec.SQLiteVectorIOConfig",
            api_dependencies=[Api.inference],
            optional_api_dependencies=[Api.files],
            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).
 """,
        ),
        InlineProviderSpec(
            api=Api.vector_io,
@ -55,6 +284,9 @@ def available_providers() -> list[ProviderSpec]:
            deprecation_warning="Please use the `inline::sqlite-vec` provider (notice the hyphen instead of underscore) instead.",
            api_dependencies=[Api.inference],
            optional_api_dependencies=[Api.files],
            description="""
 Please refer to the sqlite-vec provider documentation.
 """,
        ),
        remote_provider_spec(
            Api.vector_io,
@ -63,6 +295,39 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["chromadb-client"],
                module="llama_stack.providers.remote.vector_io.chroma",
                config_class="llama_stack.providers.remote.vector_io.chroma.ChromaVectorIOConfig",
                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.
 """,
            ),
            api_dependencies=[Api.inference],
        ),
@ -73,6 +338,40 @@ def available_providers() -> list[ProviderSpec]:
            module="llama_stack.providers.inline.vector_io.chroma",
            config_class="llama_stack.providers.inline.vector_io.chroma.ChromaVectorIOConfig",
            api_dependencies=[Api.inference],
            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.
 """,
        ),
        remote_provider_spec(
            Api.vector_io,
@ -81,6 +380,34 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["psycopg2-binary"],
                module="llama_stack.providers.remote.vector_io.pgvector",
                config_class="llama_stack.providers.remote.vector_io.pgvector.PGVectorVectorIOConfig",
                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
 ## 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 Faiss.
 3. Start storing and querying vectors.
 ## 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.
 """,
            ),
            api_dependencies=[Api.inference],
        ),
@ -92,6 +419,36 @@ def available_providers() -> list[ProviderSpec]:
                module="llama_stack.providers.remote.vector_io.weaviate",
                config_class="llama_stack.providers.remote.vector_io.weaviate.WeaviateVectorIOConfig",
                provider_data_validator="llama_stack.providers.remote.vector_io.weaviate.WeaviateRequestProviderData",
                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.
 """,
            ),
            api_dependencies=[Api.inference],
        ),
@ -102,6 +459,49 @@ def available_providers() -> list[ProviderSpec]:
            module="llama_stack.providers.inline.vector_io.qdrant",
            config_class="llama_stack.providers.inline.vector_io.qdrant.QdrantVectorIOConfig",
            api_dependencies=[Api.inference],
            description=r"""
 [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.
 """,
        ),
        remote_provider_spec(
            Api.vector_io,
@ -110,6 +510,9 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["qdrant-client"],
                module="llama_stack.providers.remote.vector_io.qdrant",
                config_class="llama_stack.providers.remote.vector_io.qdrant.QdrantVectorIOConfig",
                description="""
 Please refer to the inline provider documentation.
 """,
            ),
            api_dependencies=[Api.inference],
        ),
@ -120,6 +523,110 @@ def available_providers() -> list[ProviderSpec]:
                pip_packages=["pymilvus"],
                module="llama_stack.providers.remote.vector_io.milvus",
                config_class="llama_stack.providers.remote.vector_io.milvus.MilvusVectorIOConfig",
                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
 ## 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
 You can install Milvus using pymilvus:
 ```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).
 ## 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).
 """,
            ),
            api_dependencies=[Api.inference],
        ),
@ -131,5 +638,8 @@ def available_providers() -> list[ProviderSpec]:
            config_class="llama_stack.providers.inline.vector_io.milvus.MilvusVectorIOConfig",
            api_dependencies=[Api.inference],
            optional_api_dependencies=[Api.files],
            description="""
 Please refer to the remote provider documentation.
 """,
        ),
    ]
--- a/llama_stack/providers/remote/vector_io/milvus/config.py
+++ b/llama_stack/providers/remote/vector_io/milvus/config.py
@ -6,17 +6,19 @@
 from typing import Any
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field
 from llama_stack.schema_utils import json_schema_type
@json_schema_type
 class MilvusVectorIOConfig(BaseModel):
-    uri: str
+    uri: str = Field(description="The URI of the Milvus server")
-    token: str | None = None
+    token: str | None = Field(description="The token of the Milvus server")
-    consistency_level: str = "Strong"
+    consistency_level: str = Field(description="The consistency level of the Milvus server", default="Strong")
    # 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.
    model_config = ConfigDict(extra="allow")
    @classmethod
--- a/scripts/provider_codegen.py
+++ b/scripts/provider_codegen.py
@ -0,0 +1,332 @@
 #!/usr/bin/env python
 # Copyright (c) Meta Platforms, Inc. and affiliates.
 # All rights reserved.
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 import subprocess
 import sys
 from pathlib import Path
 from typing import Any
 from rich.progress import Progress, SpinnerColumn, TextColumn
 from llama_stack.distribution.distribution import get_provider_registry
 REPO_ROOT = Path(__file__).parent.parent
 class ChangedPathTracker:
    """Track a list of paths we may have changed."""
    def __init__(self):
        self._changed_paths = []
    def add_paths(self, *paths):
        for path in paths:
            path = str(path)
            if path not in self._changed_paths:
                self._changed_paths.append(path)
    def changed_paths(self):
        return self._changed_paths
 def get_config_class_info(config_class_path: str) -> dict[str, Any]:
    """Extract configuration information from a config class."""
    try:
        module_path, class_name = config_class_path.rsplit(".", 1)
        module = __import__(module_path, fromlist=[class_name])
        config_class = getattr(module, class_name)
        docstring = config_class.__doc__ or ""
        accepts_extra_config = False
        try:
            schema = config_class.model_json_schema()
            if schema.get("additionalProperties") is True:
                accepts_extra_config = True
        except Exception:
            if hasattr(config_class, "model_config"):
                model_config = config_class.model_config
                if hasattr(model_config, "extra") and model_config.extra == "allow":
                    accepts_extra_config = True
                elif isinstance(model_config, dict) and model_config.get("extra") == "allow":
                    accepts_extra_config = True
        fields_info = {}
        if hasattr(config_class, "model_fields"):
            for field_name, field in config_class.model_fields.items():
                field_type = str(field.annotation) if field.annotation else "Any"
                field_type = field_type.replace("typing.", "").replace("Optional[", "").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
                if field.default_factory is not None:
                    try:
                        default_value = field.default_factory()
                        # 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 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}"
                    except Exception:
                        default_value = ""
                elif field.default is None:
                    default_value = ""
                field_info = {
                    "type": field_type,
                    "description": field.description or "",
                    "default": default_value,
                    "required": field.default is None and not field.is_required,
                }
                fields_info[field_name] = field_info
        if accepts_extra_config:
            config_description = "Additional configuration options that will be forwarded to the underlying provider"
            try:
                import inspect
                source = inspect.getsource(config_class)
                lines = source.split("\n")
                for i, line in enumerate(lines):
                    if "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()
                            if stripped.startswith("#"):
                                comments.append(stripped[1:].strip())
                            elif stripped == "":
                                continue
                            else:
                                break
                        if comments:
                            config_description = " ".join(reversed(comments))
                        break
            except Exception:
                pass
            fields_info["config"] = {
                "type": "dict",
                "description": config_description,
                "default": "{}",
                "required": False,
            }
        return {
            "docstring": docstring,
            "fields": fields_info,
            "sample_config": getattr(config_class, "sample_run_config", None),
            "accepts_extra_config": accepts_extra_config,
        }
    except Exception as e:
        return {
            "error": f"Failed to load config class {config_class_path}: {str(e)}",
            "docstring": "",
            "fields": {},
            "sample_config": None,
            "accepts_extra_config": False,
        }
 def generate_provider_docs(provider_spec: Any, api_name: str) -> str:
    """Generate markdown documentation for a provider."""
    provider_type = provider_spec.provider_type
    config_class = provider_spec.config_class
    config_info = get_config_class_info(config_class)
    md_lines = []
    md_lines.append(f"# {provider_type}")
    md_lines.append("")
    description = ""
    if hasattr(provider_spec, "description") and provider_spec.description:
        description = provider_spec.description
    elif (
        hasattr(provider_spec, "adapter")
        and hasattr(provider_spec.adapter, "description")
        and provider_spec.adapter.description
    ):
        description = provider_spec.adapter.description
    elif config_info.get("docstring"):
        description = config_info["docstring"]
    if description:
        md_lines.append("## Description")
        md_lines.append("")
        md_lines.append(description)
        md_lines.append("")
    if config_info.get("fields"):
        md_lines.append("## Configuration")
        md_lines.append("")
        md_lines.append("| Field | Type | Required | Default | Description |")
        md_lines.append("|-------|------|----------|---------|-------------|")
        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 = str(field_info["default"]) if field_info["default"] is not None else ""
            description = field_info["description"] or ""
            md_lines.append(f"| `{field_name}` | `{field_type}` | {required} | {default} | {description} |")
        md_lines.append("")
        if config_info.get("accepts_extra_config"):
            md_lines.append(
                "> **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."
            )
            md_lines.append("")
    if config_info.get("sample_config"):
        md_lines.append("## Sample Configuration")
        md_lines.append("")
        md_lines.append("```yaml")
        try:
            sample_config_func = config_info["sample_config"]
            import inspect
            import yaml
            if sample_config_func is not None:
                sig = inspect.signature(sample_config_func)
                if "__distro_dir__" in sig.parameters:
                    sample_config = sample_config_func(__distro_dir__="~/.llama/dummy")
                else:
                    sample_config = sample_config_func()
                def convert_pydantic_to_dict(obj):
                    if hasattr(obj, "model_dump"):
                        return obj.model_dump()
                    elif hasattr(obj, "dict"):
                        return obj.dict()
                    elif isinstance(obj, dict):
                        return {k: convert_pydantic_to_dict(v) for k, v in obj.items()}
                    elif isinstance(obj, list):
                        return [convert_pydantic_to_dict(item) for item in obj]
                    else:
                        return obj
                sample_config_dict = convert_pydantic_to_dict(sample_config)
                md_lines.append(yaml.dump(sample_config_dict, default_flow_style=False, sort_keys=False))
            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 hasattr(provider_spec, "deprecation_warning") and provider_spec.deprecation_warning:
        md_lines.append("## Deprecation Notice")
        md_lines.append("")
        md_lines.append(f"⚠️ **Warning**: {provider_spec.deprecation_warning}")
        md_lines.append("")
    if hasattr(provider_spec, "deprecation_error") and provider_spec.deprecation_error:
        md_lines.append("## Deprecation Error")
        md_lines.append("")
        md_lines.append(f"❌ **Error**: {provider_spec.deprecation_error}")
    return "\n".join(md_lines) + "\n"
 def process_provider_registry(progress, change_tracker: ChangedPathTracker) -> None:
    """Process the complete provider registry."""
    progress.print("Processing provider registry")
    try:
        provider_registry = get_provider_registry()
        for api, providers in provider_registry.items():
            api_name = api.value
            doc_output_dir = REPO_ROOT / "docs" / "source" / "providers" / api_name
            doc_output_dir.mkdir(parents=True, exist_ok=True)
            change_tracker.add_paths(doc_output_dir)
            index_content = []
            index_content.append(f"# {api_name.title()} Providers")
            index_content.append("")
            index_content.append(
                f"This section contains documentation for all available providers for the **{api_name}** API."
            )
            index_content.append("")
            for provider_type, provider in sorted(providers.items()):
                provider_doc_file = doc_output_dir / f"{provider_type.replace('::', '_').replace(':', '_')}.md"
                provider_docs = generate_provider_docs(provider, api_name)
                provider_doc_file.write_text(provider_docs)
                change_tracker.add_paths(provider_doc_file)
                index_content.append(f"- [{provider_type}]({provider_doc_file.name})")
            index_file = doc_output_dir / "index.md"
            index_file.write_text("\n".join(index_content))
            change_tracker.add_paths(index_file)
    except Exception as e:
        progress.print(f"[red]Error processing provider registry: {str(e)}")
        raise e
 def check_for_changes(change_tracker: ChangedPathTracker) -> bool:
    """Check if there are any uncommitted changes, including new files."""
    has_changes = False
    for path in change_tracker.changed_paths():
        result = subprocess.run(
            ["git", "diff", "--exit-code", path],
            cwd=REPO_ROOT,
            capture_output=True,
        )
        if result.returncode != 0:
            print(f"Change detected in '{path}'.", file=sys.stderr)
            has_changes = True
        status_result = subprocess.run(
            ["git", "status", "--porcelain", path],
            cwd=REPO_ROOT,
            capture_output=True,
            text=True,
        )
        for line in status_result.stdout.splitlines():
            if line.startswith("??"):
                print(f"New file detected: '{path}'.", file=sys.stderr)
                has_changes = True
    return has_changes
 def main():
    change_tracker = ChangedPathTracker()
    with Progress(
        SpinnerColumn(),
        TextColumn("[progress.description]{task.description}"),
    ) as progress:
        task = progress.add_task("Processing provider registry...", total=1)
        process_provider_registry(progress, change_tracker)
        progress.update(task, advance=1)
    if check_for_changes(change_tracker):
        print(
            "Provider documentation changes detected. Please commit the changes.",
            file=sys.stderr,
        )
        sys.exit(1)
    sys.exit(0)
 if __name__ == "__main__":
    main()