merge

CONTRIBUTING.md

@@ -22,6 +22,7 @@ pip install -r requirements.txt
 pip install sphinx-autobuild
 
 # This will start a local server (usually at http://127.0.0.1:8000) that automatically rebuilds and refreshes when you make changes to the documentation.
+make html
 sphinx-autobuild source build/html
 ```
 

docs/source/getting_started/distributions/remote_hosted_distro/index.md

@@ -1,15 +1,42 @@
 # Remote-Hosted Distribution
 
-Remote Hosted distributions are distributions connecting to remote hosted services through Llama Stack server. Inference is done through remote providers. These are useful if you have an API key for a remote inference provider like Fireworks, Together, etc.
+Remote-Hosted distributions are available endpoints serving Llama Stack API that you can directly connect to.
 
-| **Distribution** 	|           **Llama Stack Docker**           	| Start This Distribution 	|    **Inference**   	|     **Agents**     	|     **Memory**     	|     **Safety**     	|    **Telemetry**   	|
+| Distribution | Endpoint | Inference | Agents | Memory | Safety | Telemetry |
-|:----------------:	|:------------------------------------------:	|:-----------------------:	|:------------------:	|:------------------:	|:------------------:	|:------------------:	|:------------------:	|
+|-------------|----------|-----------|---------|---------|---------|------------|
-|        Together       	|         [llamastack/distribution-together](https://hub.docker.com/repository/docker/llamastack/distribution-together/general)        	|       [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/remote_hosted_distro/together.html)       	| remote::together 	| meta-reference | remote::weaviate | meta-reference 	| meta-reference  	|
+| Together | [https://llama-stack.together.ai](https://llama-stack.together.ai) | remote::together | meta-reference | remote::weaviate | meta-reference | meta-reference |
-|        Fireworks       	|         [llamastack/distribution-fireworks](https://hub.docker.com/repository/docker/llamastack/distribution-fireworks/general)        	|       [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/remote_hosted_distro/fireworks.html)       	| remote::fireworks 	| meta-reference | remote::weaviate | meta-reference 	| meta-reference  	|
+| Fireworks | [https://llamastack-preview.fireworks.ai](https://llamastack-preview.fireworks.ai) | remote::fireworks | meta-reference | remote::weaviate | meta-reference | meta-reference |
 
-```{toctree}
+## Connecting to Remote-Hosted Distributions
-:maxdepth: 1
 
-fireworks
+You can use `llama-stack-client` to interact with these endpoints. For example, to list the available models served by the Fireworks endpoint:
-together
+
+```bash
+$ pip install llama-stack-client
+$ llama-stack-client configure --endpoint https://llamastack-preview.fireworks.ai
+$ llama-stack-client models list
 ```
+
+You will see outputs:
+```
+$ llama-stack-client models list
++------------------------------+------------------------------+---------------+------------+
+| identifier                   | llama_model                  | provider_id   | metadata   |
++==============================+==============================+===============+============+
+| Llama3.1-8B-Instruct         | Llama3.1-8B-Instruct         | fireworks0    | {}         |
++------------------------------+------------------------------+---------------+------------+
+| Llama3.1-70B-Instruct        | Llama3.1-70B-Instruct        | fireworks0    | {}         |
++------------------------------+------------------------------+---------------+------------+
+| Llama3.1-405B-Instruct       | Llama3.1-405B-Instruct       | fireworks0    | {}         |
++------------------------------+------------------------------+---------------+------------+
+| Llama3.2-1B-Instruct         | Llama3.2-1B-Instruct         | fireworks0    | {}         |
++------------------------------+------------------------------+---------------+------------+
+| Llama3.2-3B-Instruct         | Llama3.2-3B-Instruct         | fireworks0    | {}         |
++------------------------------+------------------------------+---------------+------------+
+| Llama3.2-11B-Vision-Instruct | Llama3.2-11B-Vision-Instruct | fireworks0    | {}         |
++------------------------------+------------------------------+---------------+------------+
+| Llama3.2-90B-Vision-Instruct | Llama3.2-90B-Vision-Instruct | fireworks0    | {}         |
++------------------------------+------------------------------+---------------+------------+
+```
+
+Checkout the [llama-stack-client-python](https://github.com/meta-llama/llama-stack-client-python/blob/main/docs/cli_reference.md) repo for more details on how to use the `llama-stack-client` CLI. Checkout [llama-stack-app](https://github.com/meta-llama/llama-stack-apps/tree/main) for examples applications built on top of Llama Stack.

docs/source/getting_started/distributions/self_hosted_distro/index.md

@@ -8,6 +8,10 @@ We offer deployable distributions where you can host your own Llama Stack server
 |  Meta Reference Quantized  	| [llamastack/distribution-meta-reference-quantized-gpu](https://hub.docker.com/repository/docker/llamastack/distribution-meta-reference-quantized-gpu/general) 	|       [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/meta-reference-quantized-gpu.html)       	| meta-reference-quantized 	| meta-reference 	| meta-reference; remote::pgvector; remote::chromadb	| meta-reference 	| meta-reference	|
 |      Ollama      	|       [llamastack/distribution-ollama](https://hub.docker.com/repository/docker/llamastack/distribution-ollama/general)       	|       [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/ollama.html)       	| remote::ollama	| meta-reference 	| remote::pgvector; remote::chromadb 	|  meta-reference 	| meta-reference 	|
 |        TGI       	|         [llamastack/distribution-tgi](https://hub.docker.com/repository/docker/llamastack/distribution-tgi/general)        	|       [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/tgi.html)       	| remote::tgi	| meta-reference 	| meta-reference; remote::pgvector; remote::chromadb 	| meta-reference 	| meta-reference 	|
+|        Together       	|         [llamastack/distribution-together](https://hub.docker.com/repository/docker/llamastack/distribution-together/general)        	|       [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/together.html)       	| remote::together 	| meta-reference | remote::weaviate | meta-reference 	| meta-reference  	|
+|        Fireworks       	|         [llamastack/distribution-fireworks](https://hub.docker.com/repository/docker/llamastack/distribution-fireworks/general)        	|       [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/fireworks.html)       	| remote::fireworks 	| meta-reference | remote::weaviate | meta-reference 	| meta-reference  	|
+|        Bedrock       	|         [llamastack/distribution-bedrock](https://hub.docker.com/repository/docker/llamastack/distribution-bedrock/general)        	|       [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/bedrock.html)       	| remote::bedrock 	| meta-reference | remote::weaviate | meta-reference 	| meta-reference  	|
+
 
 ```{toctree}
 :maxdepth: 1
@@ -17,4 +21,7 @@ meta-reference-quantized-gpu
 ollama
 tgi
 dell-tgi
+together
+fireworks
+bedrock
 ```

llama_stack/providers/tests/eval/fixtures.py

@@ -52,11 +52,4 @@ async def eval_stack(request):
         provider_data,
     )
 
-    return (
+    return impls
-        impls[Api.eval],
-        impls[Api.eval_tasks],
-        impls[Api.scoring],
-        impls[Api.scoring_functions],
-        impls[Api.datasetio],
-        impls[Api.datasets],
-    )

llama_stack/providers/tests/eval/provider_config_example.yaml

@@ -1,22 +0,0 @@
-providers:
-  datasetio:
-  - provider_id: test-meta
-    provider_type: meta-reference
-    config: {}
-  scoring:
-    - provider_id: test-meta
-      provider_type: meta-reference
-      config: {}
-  eval:
-    - provider_id: test-meta
-      provider_type: meta-reference
-      config: {}
-  inference:
-    - provider_id: test-tgi
-      provider_type: remote::tgi
-      config:
-        url: http://127.0.0.1:5009
-    - provider_id: test-tgi-2
-      provider_type: remote::tgi
-      config:
-        url: http://127.0.0.1:5010

llama_stack/providers/tests/eval/test_eval.py

@@ -30,19 +30,23 @@ class Testeval:
     async def test_eval_tasks_list(self, eval_stack):
         # NOTE: this needs you to ensure that you are starting from a clean state
         # but so far we don't have an unregister API unfortunately, so be careful
-        _, eval_tasks_impl, _, _, _, _ = eval_stack
+        eval_tasks_impl = eval_stack[Api.eval_tasks]
         response = await eval_tasks_impl.list_eval_tasks()
         assert isinstance(response, list)
 
     @pytest.mark.asyncio
     async def test_eval_evaluate_rows(self, eval_stack):
-        eval_impl, eval_tasks_impl, _, _, datasetio_impl, datasets_impl = eval_stack
+        eval_impl, eval_tasks_impl, datasetio_impl, datasets_impl = (
+            eval_stack[Api.eval],
+            eval_stack[Api.eval_tasks],
+            eval_stack[Api.datasetio],
+            eval_stack[Api.datasets],
+        )
         await register_dataset(
             datasets_impl, for_generation=True, dataset_id="test_dataset_for_eval"
         )
-
         response = await datasets_impl.list_datasets()
-        assert len(response) >= 1
+        assert len(response) == 1
         rows = await datasetio_impl.get_rows_paginated(
             dataset_id="test_dataset_for_eval",
             rows_in_page=3,
@@ -79,7 +83,11 @@ class Testeval:
 
     @pytest.mark.asyncio
     async def test_eval_run_eval(self, eval_stack):
-        eval_impl, eval_tasks_impl, _, _, datasetio_impl, datasets_impl = eval_stack
+        eval_impl, eval_tasks_impl, datasets_impl = (
+            eval_stack[Api.eval],
+            eval_stack[Api.eval_tasks],
+            eval_stack[Api.datasets],
+        )
         await register_dataset(
             datasets_impl, for_generation=True, dataset_id="test_dataset_for_eval"
         )