Merge branch 'main' into enable-vector-stores-files-api-tests

.github/workflows/README.md

@@ -1,6 +1,6 @@
 # Llama Stack CI
 
-Llama Stack uses GitHub Actions for Continous Integration (CI). Below is a table detailing what CI the project includes and the purpose.
+Llama Stack uses GitHub Actions for Continuous Integration (CI). Below is a table detailing what CI the project includes and the purpose.
 
 | Name | File | Purpose |
 | ---- | ---- | ------- |

README.md

@@ -6,7 +6,6 @@
 [![Discord](https://img.shields.io/discord/1257833999603335178?color=6A7EC2&logo=discord&logoColor=ffffff)](https://discord.gg/llama-stack)
 [![Unit Tests](https://github.com/meta-llama/llama-stack/actions/workflows/unit-tests.yml/badge.svg?branch=main)](https://github.com/meta-llama/llama-stack/actions/workflows/unit-tests.yml?query=branch%3Amain)
 [![Integration Tests](https://github.com/meta-llama/llama-stack/actions/workflows/integration-tests.yml/badge.svg?branch=main)](https://github.com/meta-llama/llama-stack/actions/workflows/integration-tests.yml?query=branch%3Amain)
-![coverage badge](./coverage.svg)
 
 [**Quick Start**](https://llama-stack.readthedocs.io/en/latest/getting_started/index.html) | [**Documentation**](https://llama-stack.readthedocs.io/en/latest/index.html) | [**Colab Notebook**](./docs/getting_started.ipynb) | [**Discord**](https://discord.gg/llama-stack)
 

docs/_static/llama-stack-spec.html

@@ -15078,22 +15078,6 @@
             "DPOAlignmentConfig": {
                 "type": "object",
                 "properties": {
-                    "reward_scale": {
-                        "type": "number",
-                        "description": "Scaling factor for the reward signal"
-                    },
-                    "reward_clip": {
-                        "type": "number",
-                        "description": "Maximum absolute value for reward clipping"
-                    },
-                    "epsilon": {
-                        "type": "number",
-                        "description": "Small value added for numerical stability"
-                    },
-                    "gamma": {
-                        "type": "number",
-                        "description": "Discount factor for future rewards"
-                    },
                     "beta": {
                         "type": "number",
                         "description": "Temperature parameter for the DPO loss"
@@ -15106,10 +15090,6 @@
                 },
                 "additionalProperties": false,
                 "required": [
-                    "reward_scale",
-                    "reward_clip",
-                    "epsilon",
-                    "gamma",
                     "beta",
                     "loss_type"
                 ],

docs/_static/llama-stack-spec.yaml

@@ -11163,20 +11163,6 @@ components:
     DPOAlignmentConfig:
       type: object
       properties:
-        reward_scale:
-          type: number
-          description: Scaling factor for the reward signal
-        reward_clip:
-          type: number
-          description: >-
-            Maximum absolute value for reward clipping
-        epsilon:
-          type: number
-          description: >-
-            Small value added for numerical stability
-        gamma:
-          type: number
-          description: Discount factor for future rewards
         beta:
           type: number
           description: Temperature parameter for the DPO loss
@@ -11186,10 +11172,6 @@ components:
           description: The type of loss function to use for DPO
       additionalProperties: false
       required:
-        - reward_scale
-        - reward_clip
-        - epsilon
-        - gamma
         - beta
         - loss_type
       title: DPOAlignmentConfig

docs/source/providers/external/external-providers-guide.md

@@ -1,9 +1,4 @@
-# External Providers Guide
-
-Llama Stack supports external providers that live outside of the main codebase. This allows you to:
-- Create and maintain your own providers independently
-- Share providers with others without contributing to the main codebase
-- Keep provider-specific code separate from the core Llama Stack code
+# Creating External Providers
 
 ## Configuration
 
@@ -55,17 +50,6 @@ Llama Stack supports two types of external providers:
 1. **Remote Providers**: Providers that communicate with external services (e.g., cloud APIs)
 2. **Inline Providers**: Providers that run locally within the Llama Stack process
 
-## Known External Providers
-
-Here's a list of known external providers that you can use with Llama Stack:
-
-| Name | Description | API | Type | Repository |
-|------|-------------|-----|------|------------|
-| KubeFlow Training | Train models with KubeFlow | Post Training | Remote | [llama-stack-provider-kft](https://github.com/opendatahub-io/llama-stack-provider-kft) |
-| KubeFlow Pipelines | Train models with KubeFlow Pipelines | Post Training | Inline **and** Remote | [llama-stack-provider-kfp-trainer](https://github.com/opendatahub-io/llama-stack-provider-kfp-trainer) |
-| RamaLama | Inference models with RamaLama | Inference | Remote | [ramalama-stack](https://github.com/containers/ramalama-stack) |
-| TrustyAI LM-Eval | Evaluate models with TrustyAI LM-Eval | Eval | Remote | [llama-stack-provider-lmeval](https://github.com/trustyai-explainability/llama-stack-provider-lmeval) |
-
 ### Remote Provider Specification
 
 Remote providers are used when you need to communicate with external services. Here's an example for a custom Ollama provider:
@@ -119,9 +103,9 @@ container_image: custom-vector-store:latest  # optional
 - `provider_data_validator`: Optional validator for provider data
 - `container_image`: Optional container image to use instead of pip packages
 
-## Required Implementation
+## Required Fields
 
-## All Providers
+### All Providers
 
 All providers must contain a `get_provider_spec` function in their `provider` module. This is a standardized structure that Llama Stack expects and is necessary for getting things such as the config class. The `get_provider_spec` method returns a structure identical to the `adapter`. An example function may look like:
 
@@ -146,7 +130,7 @@ def get_provider_spec() -> ProviderSpec:
     )
 ```
 
-### Remote Providers
+#### Remote Providers
 
 Remote providers must expose a `get_adapter_impl()` function in their module that takes two arguments:
 1. `config`: An instance of the provider's config class
@@ -162,7 +146,7 @@ async def get_adapter_impl(
     return OllamaInferenceAdapter(config)
 ```
 
-### Inline Providers
+#### Inline Providers
 
 Inline providers must expose a `get_provider_impl()` function in their module that takes two arguments:
 1. `config`: An instance of the provider's config class
@@ -189,7 +173,40 @@ Version: 0.1.0
 Location: /path/to/venv/lib/python3.10/site-packages
 ```
 
-## Example using `external_providers_dir`: Custom Ollama Provider
+## Best Practices
+
+1. **Package Naming**: Use the prefix `llama-stack-provider-` for your provider packages to make them easily identifiable.
+
+2. **Version Management**: Keep your provider package versioned and compatible with the Llama Stack version you're using.
+
+3. **Dependencies**: Only include the minimum required dependencies in your provider package.
+
+4. **Documentation**: Include clear documentation in your provider package about:
+   - Installation requirements
+   - Configuration options
+   - Usage examples
+   - Any limitations or known issues
+
+5. **Testing**: Include tests in your provider package to ensure it works correctly with Llama Stack.
+You can refer to the [integration tests
+guide](https://github.com/meta-llama/llama-stack/blob/main/tests/integration/README.md) for more
+information. Execute the test for the Provider type you are developing.
+
+## Troubleshooting
+
+If your external provider isn't being loaded:
+
+1. Check that `module` points to a published pip package with a top level `provider` module including `get_provider_spec`.
+1. Check that the `external_providers_dir` path is correct and accessible.
+2. Verify that the YAML files are properly formatted.
+3. Ensure all required Python packages are installed.
+4. Check the Llama Stack server logs for any error messages - turn on debug logging to get more
+   information using `LLAMA_STACK_LOGGING=all=debug`.
+5. Verify that the provider package is installed in your Python environment if using `external_providers_dir`.
+
+## Examples
+
+### Example using `external_providers_dir`: Custom Ollama Provider
 
 Here's a complete example of creating and using a custom Ollama provider:
 
@@ -241,7 +258,7 @@ external_providers_dir: ~/.llama/providers.d/
 The provider will now be available in Llama Stack with the type `remote::custom_ollama`.
 
 
-## Example using `module`: ramalama-stack
+### Example using `module`: ramalama-stack
 
 [ramalama-stack](https://github.com/containers/ramalama-stack) is a recognized external provider that supports installation via module.
 
@@ -266,35 +283,4 @@ additional_pip_packages:
 
 No other steps are required other than `llama stack build` and `llama stack run`. The build process will use `module` to install all of the provider dependencies, retrieve the spec, etc.
 
-The provider will now be available in Llama Stack with the type `remote::ramalama`.
-
-## Best Practices
-
-1. **Package Naming**: Use the prefix `llama-stack-provider-` for your provider packages to make them easily identifiable.
-
-2. **Version Management**: Keep your provider package versioned and compatible with the Llama Stack version you're using.
-
-3. **Dependencies**: Only include the minimum required dependencies in your provider package.
-
-4. **Documentation**: Include clear documentation in your provider package about:
-   - Installation requirements
-   - Configuration options
-   - Usage examples
-   - Any limitations or known issues
-
-5. **Testing**: Include tests in your provider package to ensure it works correctly with Llama Stack.
-You can refer to the [integration tests
-guide](https://github.com/meta-llama/llama-stack/blob/main/tests/integration/README.md) for more
-information. Execute the test for the Provider type you are developing.
-
-## Troubleshooting
-
-If your external provider isn't being loaded:
-
-1. Check that `module` points to a published pip package with a top level `provider` module including `get_provider_spec`.
-1. Check that the `external_providers_dir` path is correct and accessible.
-2. Verify that the YAML files are properly formatted.
-3. Ensure all required Python packages are installed.
-4. Check the Llama Stack server logs for any error messages - turn on debug logging to get more
-   information using `LLAMA_STACK_LOGGING=all=debug`.
-5. Verify that the provider package is installed in your Python environment if using `external_providers_dir`.
+The provider will now be available in Llama Stack with the type `remote::ramalama`.

docs/source/providers/external/external-providers-list.md

@@ -0,0 +1,10 @@
+# Known External Providers
+
+Here's a list of known external providers that you can use with Llama Stack:
+
+| Name | Description | API | Type | Repository |
+|------|-------------|-----|------|------------|
+| KubeFlow Training | Train models with KubeFlow | Post Training | Remote | [llama-stack-provider-kft](https://github.com/opendatahub-io/llama-stack-provider-kft) |
+| KubeFlow Pipelines | Train models with KubeFlow Pipelines | Post Training | Inline **and** Remote | [llama-stack-provider-kfp-trainer](https://github.com/opendatahub-io/llama-stack-provider-kfp-trainer) |
+| RamaLama | Inference models with RamaLama | Inference | Remote | [ramalama-stack](https://github.com/containers/ramalama-stack) |
+| TrustyAI LM-Eval | Evaluate models with TrustyAI LM-Eval | Eval | Remote | [llama-stack-provider-lmeval](https://github.com/trustyai-explainability/llama-stack-provider-lmeval) |

docs/source/providers/external/index.md

@@ -0,0 +1,13 @@
+# External Providers
+
+Llama Stack supports external providers that live outside of the main codebase. This allows you to:
+- Create and maintain your own providers independently
+- Share providers with others without contributing to the main codebase
+- Keep provider-specific code separate from the core Llama Stack code
+
+```{toctree}
+:maxdepth: 1
+
+external-providers-list
+external-providers-guide
+```

docs/source/providers/index.md

@@ -15,7 +15,7 @@ Importantly, Llama Stack always strives to provide at least one fully inline pro
 ```{toctree}
 :maxdepth: 1
 
-external
+external/index
 openai
 inference/index
 agents/index

llama_stack/apis/post_training/post_training.py

@@ -193,18 +193,10 @@ class DPOLossType(Enum):
 class DPOAlignmentConfig(BaseModel):
     """Configuration for Direct Preference Optimization (DPO) alignment.
 
-    :param reward_scale: Scaling factor for the reward signal
-    :param reward_clip: Maximum absolute value for reward clipping
-    :param epsilon: Small value added for numerical stability
-    :param gamma: Discount factor for future rewards
     :param beta: Temperature parameter for the DPO loss
     :param loss_type: The type of loss function to use for DPO
     """
 
-    reward_scale: float
-    reward_clip: float
-    epsilon: float
-    gamma: float
     beta: float
     loss_type: DPOLossType = DPOLossType.sigmoid
 

llama_stack/core/routing_tables/vector_dbs.py

@@ -84,8 +84,6 @@ class VectorDBsRoutingTable(CommonRoutingTableImpl, VectorDBs):
 
     async def unregister_vector_db(self, vector_db_id: str) -> None:
         existing_vector_db = await self.get_vector_db(vector_db_id)
-        if existing_vector_db is None:
-            raise VectorStoreNotFoundError(vector_db_id)
         await self.unregister_object(existing_vector_db)
 
     async def openai_retrieve_vector_store(

scripts/gen-ci-docs.py

@@ -36,7 +36,7 @@ def generate_ci_docs():
     # Header section to preserve
     header = """# Llama Stack CI
 
-Llama Stack uses GitHub Actions for Continous Integration (CI). Below is a table detailing what CI the project includes and the purpose.
+Llama Stack uses GitHub Actions for Continuous Integration (CI). Below is a table detailing what CI the project includes and the purpose.
 
 | Name | File | Purpose |
 | ---- | ---- | ------- |

tests/integration/post_training/test_post_training.py

@@ -195,10 +195,6 @@ class TestPostTraining:
         algorithm_config = DPOAlignmentConfig(
             beta=0.1,
             loss_type=DPOLossType.sigmoid,  # Default loss type
-            reward_scale=1.0,  # Scaling factor for reward signal (neutral scaling)
-            reward_clip=5.0,  # Maximum absolute value for reward clipping (prevents extreme values)
-            epsilon=1e-8,  # Small value for numerical stability
-            gamma=1.0,
         )
         data_config = DataConfig(
             dataset_id=dataset.identifier,