Fix docker failing to start container

docs/source/providers/agents/index.md

@@ -4,12 +4,12 @@
 
 Agents API for creating and interacting with agentic systems.
 
-    Main functionalities provided by this API:
+Main functionalities provided by this API:
-    - Create agents with specific instructions and ability to use tools.
+- Create agents with specific instructions and ability to use tools.
-    - Interactions with agents are grouped into sessions ("threads"), and each interaction is called a "turn".
+- Interactions with agents are grouped into sessions ("threads"), and each interaction is called a "turn".
-    - Agents can be provided with various tools (see the ToolGroups and ToolRuntime APIs for more details).
+- Agents can be provided with various tools (see the ToolGroups and ToolRuntime APIs for more details).
-    - Agents can be provided with various shields (see the Safety API for more details).
+- Agents can be provided with various shields (see the Safety API for more details).
-    - Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details.
+- Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details.
 
 This section contains documentation for all available providers for the **agents** API.
 

docs/source/providers/inference/index.md

@@ -4,9 +4,9 @@
 
 Llama Stack Inference API for generating completions, chat completions, and embeddings.
 
-    This API provides the raw interface to the underlying models. Two kinds of models are supported:
+This API provides the raw interface to the underlying models. Two kinds of models are supported:
-    - LLM models: these models generate "raw" and "chat" (conversational) completions.
+- LLM models: these models generate "raw" and "chat" (conversational) completions.
-    - Embedding models: these models generate embeddings to be used for semantic search.
+- Embedding models: these models generate embeddings to be used for semantic search.
 
 This section contains documentation for all available providers for the **inference** API.
 

llama_stack/providers/registry/inference.py

@@ -116,7 +116,7 @@ def available_providers() -> list[ProviderSpec]:
             adapter=AdapterSpec(
                 adapter_type="fireworks",
                 pip_packages=[
-                    "fireworks-ai",
+                    "fireworks-ai==0.17.16",
                 ],
                 module="llama_stack.providers.remote.inference.fireworks",
                 config_class="llama_stack.providers.remote.inference.fireworks.FireworksImplConfig",

llama_stack/providers/remote/inference/vertexai/vertexai.py

@@ -6,7 +6,9 @@
 
 from typing import Any
 
-from llama_stack.apis.inference import ChatCompletionRequest
+from openai.types.chat import ChatCompletionContentPartImageParam, ChatCompletionContentPartTextParam
+
+from llama_stack.apis.inference import ChatCompletionRequest, RerankResponse
 from llama_stack.providers.utils.inference.litellm_openai_mixin import (
     LiteLLMOpenAIMixin,
 )
@@ -50,3 +52,12 @@ class VertexAIInferenceAdapter(LiteLLMOpenAIMixin):
         params.pop("api_key", None)
 
         return params
+
+    async def rerank(
+        self,
+        model: str,
+        query: str | ChatCompletionContentPartTextParam | ChatCompletionContentPartImageParam,
+        items: list[str | ChatCompletionContentPartTextParam | ChatCompletionContentPartImageParam],
+        max_num_results: int | None = None,
+    ) -> RerankResponse:
+        raise NotImplementedError("Reranking is not supported for Vertex AI")