mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-03 19:57:35 +00:00
docs!: adjust external provider docs
now that we consolidated the providerspec types and got rid of `AdapterSpec`, adjust external.md and external-provider-guide.md external_providers_guide.md specifically needed some updates around the proper fields required in a ProviderSpec beyond the changes in this PR. BREAKING CHANGE: external providers must update their `get_provider_spec` function to use `RemoteProviderSpec` properly Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern
parent
4dfbe46954
commit
da607957c0
2 changed files with 52 additions and 97 deletions
|
|
@ -152,7 +152,6 @@ __all__ = ["WeatherAPI", "available_providers"]
|
|||
from typing import Protocol
|
||||
|
||||
from llama_stack.providers.datatypes import (
|
||||
AdapterSpec,
|
||||
Api,
|
||||
ProviderSpec,
|
||||
RemoteProviderSpec,
|
||||
|
|
@ -166,13 +165,11 @@ def available_providers() -> list[ProviderSpec]:
|
|||
api=Api.weather,
|
||||
provider_type="remote::kaze",
|
||||
config_class="llama_stack_provider_kaze.KazeProviderConfig",
|
||||
adapter=AdapterSpec(
|
||||
adapter_type="kaze",
|
||||
module="llama_stack_provider_kaze",
|
||||
pip_packages=["llama_stack_provider_kaze"],
|
||||
config_class="llama_stack_provider_kaze.KazeProviderConfig",
|
||||
),
|
||||
),
|
||||
]
|
||||
|
||||
|
||||
|
|
@ -325,7 +322,6 @@ class WeatherKazeAdapter(WeatherProvider):
|
|||
|
||||
```yaml
|
||||
# ~/.llama/providers.d/remote/weather/kaze.yaml
|
||||
adapter:
|
||||
adapter_type: kaze
|
||||
pip_packages: ["llama_stack_provider_kaze"]
|
||||
config_class: llama_stack_provider_kaze.config.KazeProviderConfig
|
||||
|
|
|
|||
|
|
@ -11,38 +11,6 @@ an example entry in your build.yaml should look like:
|
|||
module: ramalama_stack
|
||||
```
|
||||
|
||||
Additionally you can configure the `external_providers_dir` in your Llama Stack configuration. This method is in the process of being deprecated in favor of the `module` method. If using this method, the external provider directory should contain your external provider specifications:
|
||||
|
||||
```yaml
|
||||
external_providers_dir: ~/.llama/providers.d/
|
||||
```
|
||||
|
||||
## Directory Structure
|
||||
|
||||
The external providers directory should follow this structure:
|
||||
|
||||
```
|
||||
providers.d/
|
||||
remote/
|
||||
inference/
|
||||
custom_ollama.yaml
|
||||
vllm.yaml
|
||||
vector_io/
|
||||
qdrant.yaml
|
||||
safety/
|
||||
llama-guard.yaml
|
||||
inline/
|
||||
inference/
|
||||
custom_ollama.yaml
|
||||
vllm.yaml
|
||||
vector_io/
|
||||
qdrant.yaml
|
||||
safety/
|
||||
llama-guard.yaml
|
||||
```
|
||||
|
||||
Each YAML file in these directories defines a provider specification for that particular API.
|
||||
|
||||
## Provider Types
|
||||
|
||||
Llama Stack supports two types of external providers:
|
||||
|
|
@ -50,13 +18,25 @@ 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
|
||||
|
||||
|
||||
### Provider Specification (Common between inline and remote providers)
|
||||
|
||||
- `provider_type`: The type of the provider to be installed (remote or inline). eg. `remote::ollama`
|
||||
- `api`: The API for this provider, eg. `inference`
|
||||
- `config_class`: The full path to the configuration class
|
||||
- `module`: The Python module containing the provider implementation
|
||||
- `optional_api_dependencies`: List of optional Llama Stack APIs that this provider can use
|
||||
- `api_dependencies`: List of Llama Stack APIs that this provider depends on
|
||||
- `provider_data_validator`: Optional validator for provider data.
|
||||
- `pip_packages`: List of Python packages required by the provider
|
||||
|
||||
### Remote Provider Specification
|
||||
|
||||
Remote providers are used when you need to communicate with external services. Here's an example for a custom Ollama provider:
|
||||
|
||||
```yaml
|
||||
adapter:
|
||||
adapter_type: custom_ollama
|
||||
provider_type: "remote::ollama"
|
||||
pip_packages:
|
||||
- ollama
|
||||
- aiohttp
|
||||
|
|
@ -66,14 +46,9 @@ api_dependencies: []
|
|||
optional_api_dependencies: []
|
||||
```
|
||||
|
||||
#### Adapter Configuration
|
||||
#### Remote Provider Configuration
|
||||
|
||||
The `adapter` section defines how to load and configure the provider:
|
||||
|
||||
- `adapter_type`: A unique identifier for this adapter
|
||||
- `pip_packages`: List of Python packages required by the provider
|
||||
- `config_class`: The full path to the configuration class
|
||||
- `module`: The Python module containing the provider implementation
|
||||
- `adapter_type`: A unique identifier for this adapter, eg. `ollama`
|
||||
|
||||
### Inline Provider Specification
|
||||
|
||||
|
|
@ -81,6 +56,7 @@ Inline providers run locally within the Llama Stack process. Here's an example f
|
|||
|
||||
```yaml
|
||||
module: llama_stack_vector_provider
|
||||
provider_type: inline::llama_stack_vector_provider
|
||||
config_class: llama_stack_vector_provider.config.VectorStoreConfig
|
||||
pip_packages:
|
||||
- faiss-cpu
|
||||
|
|
@ -95,12 +71,6 @@ container_image: custom-vector-store:latest # optional
|
|||
|
||||
#### Inline Provider Fields
|
||||
|
||||
- `module`: The Python module containing the provider implementation
|
||||
- `config_class`: The full path to the configuration class
|
||||
- `pip_packages`: List of Python packages required by the provider
|
||||
- `api_dependencies`: List of Llama Stack APIs that this provider depends on
|
||||
- `optional_api_dependencies`: List of optional Llama Stack APIs that this provider can use
|
||||
- `provider_data_validator`: Optional validator for provider data
|
||||
- `container_image`: Optional container image to use instead of pip packages
|
||||
|
||||
## Required Fields
|
||||
|
|
@ -113,20 +83,17 @@ All providers must contain a `get_provider_spec` function in their `provider` mo
|
|||
from llama_stack.providers.datatypes import (
|
||||
ProviderSpec,
|
||||
Api,
|
||||
AdapterSpec,
|
||||
remote_provider_spec,
|
||||
RemoteProviderSpec,
|
||||
)
|
||||
|
||||
|
||||
def get_provider_spec() -> ProviderSpec:
|
||||
return remote_provider_spec(
|
||||
return RemoteProviderSpec(
|
||||
api=Api.inference,
|
||||
adapter=AdapterSpec(
|
||||
adapter_type="ramalama",
|
||||
pip_packages=["ramalama>=0.8.5", "pymilvus"],
|
||||
config_class="ramalama_stack.config.RamalamaImplConfig",
|
||||
module="ramalama_stack",
|
||||
),
|
||||
)
|
||||
```
|
||||
|
||||
|
|
@ -197,18 +164,16 @@ information. Execute the test for the Provider type you are developing.
|
|||
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
|
||||
### How to create an external provider module
|
||||
|
||||
Here's a complete example of creating and using a custom Ollama provider:
|
||||
If you are creating a new external provider called `llama-stack-provider-ollama` here is how you would set up the package properly:
|
||||
|
||||
1. First, create the provider package:
|
||||
|
||||
|
|
@ -230,33 +195,28 @@ requires-python = ">=3.12"
|
|||
dependencies = ["llama-stack", "pydantic", "ollama", "aiohttp"]
|
||||
```
|
||||
|
||||
3. Create the provider specification:
|
||||
|
||||
```yaml
|
||||
# ~/.llama/providers.d/remote/inference/custom_ollama.yaml
|
||||
adapter:
|
||||
adapter_type: custom_ollama
|
||||
pip_packages: ["ollama", "aiohttp"]
|
||||
config_class: llama_stack_provider_ollama.config.OllamaImplConfig
|
||||
module: llama_stack_provider_ollama
|
||||
api_dependencies: []
|
||||
optional_api_dependencies: []
|
||||
```
|
||||
|
||||
4. Install the provider:
|
||||
3. Install the provider:
|
||||
|
||||
```bash
|
||||
uv pip install -e .
|
||||
```
|
||||
|
||||
5. Configure Llama Stack to use external providers:
|
||||
4. Edit `provider.py`
|
||||
|
||||
```yaml
|
||||
external_providers_dir: ~/.llama/providers.d/
|
||||
provider.py must be updated to contain `get_provider_spec`. This is used by llama stack to install the provider.
|
||||
|
||||
```python
|
||||
def get_provider_spec() -> ProviderSpec:
|
||||
return RemoteProviderSpec(
|
||||
api=Api.inference,
|
||||
adapter_type="llama-stack-provider-ollama",
|
||||
pip_packages=["ollama", "aiohttp"],
|
||||
config_class="llama_stack_provider_ollama.config.OllamaImplConfig",
|
||||
module="llama_stack_provider_ollama",
|
||||
)
|
||||
```
|
||||
|
||||
The provider will now be available in Llama Stack with the type `remote::custom_ollama`.
|
||||
|
||||
5. Implement the provider as outlined above with `get_provider_impl` or `get_adapter_impl`, etc.
|
||||
|
||||
### Example using `module`: ramalama-stack
|
||||
|
||||
|
|
@ -275,7 +235,6 @@ distribution_spec:
|
|||
module: ramalama_stack==0.3.0a0
|
||||
image_type: venv
|
||||
image_name: null
|
||||
external_providers_dir: null
|
||||
additional_pip_packages:
|
||||
- aiosqlite
|
||||
- sqlalchemy[asyncio]
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue