llama-stack-mirror/llama_stack/providers/remote/inference
Eric Huang 7027b537e0 feat: RFC: tools API rework
# What does this PR do?
This PR proposes updates to the tools API in Inference and Agent.

Goals:
1. Agent's tool specification should be consistent with Inference's tool spec, but with add-ons.
2. Formal types should be defined for built in tools. Currently Agent tools args are untyped, e.g. how does one know that `builtin::rag_tool` takes a `vector_db_ids` param or even how to know 'builtin::rag_tool' is even available (in code, outside of docs)?

Inference:
1. BuiltinTool is to be removed and replaced by a formal `type` parameter.
2. 'brave_search' is replaced by 'web_search' to be more generic. It will still be translated back to brave_search when the prompt is constructed to be consistent with model training.
3. I'm not sure what `photogen` is. Maybe it can be removed?

Agent:
1. Uses the same format as in Inference for builtin tools.
2. New tools types are added, i.e. knowledge_sesarch (currently rag_tool), and MCP tool.
3. Toolgroup as a concept will be removed since it's really only used for MCP.
4. Instead MCPTool is its own type and available tools provided by the server will be expanded by default. Users can specify a subset of tool names if desired.

Example snippet:
```

agent = Agent(
    client,
    model=model_id,
    instructions="You are a helpful assistant. Use the tools you have access to for providing relevant answers.",
    tools=[
        KnowledgeSearchTool(vector_store_id="1234"),
        KnowledgeSearchTool(vector_store_id="5678", name="paper_search", description="Search research papers"),
        KnowledgeSearchTool(vector_store_id="1357", name="wiki_search", description="Search wiki pages"),
        # no need to register toolgroup, just pass in the server uri
        # all available tools will be used
        MCPTool(server_uri="http://localhost:8000/sse"),
        # can specify a subset of available tools
        MCPTool(server_uri="http://localhost:8000/sse", tool_names=["list_directory"]),
        MCPTool(server_uri="http://localhost:8000/sse", tool_names=["list_directory"]),
        # custom tool
        my_custom_tool,
    ]
)
```

## Test Plan
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
2025-03-26 11:14:41 -07:00
..
anthropic feat(providers): Groq now uses LiteLLM openai-compat (#1303) 2025-02-27 13:16:50 -08:00
bedrock fix: solve ruff B008 warnings (#1444) 2025-03-06 16:48:35 -08:00
cerebras fix: solve ruff B008 warnings (#1444) 2025-03-06 16:48:35 -08:00
databricks test: add unit test to ensure all config types are instantiable (#1601) 2025-03-12 22:29:58 -07:00
fireworks fix: remove Llama-3.2-1B-Instruct for fireworks (#1558) 2025-03-11 11:19:29 -07:00
gemini feat(providers): Groq now uses LiteLLM openai-compat (#1303) 2025-02-27 13:16:50 -08:00
groq fix: register provider model name and HF alias in run.yaml (#1304) 2025-02-27 16:39:23 -08:00
nvidia feat: support nvidia hosted vision models (llama 3.2 11b/90b) (#1278) 2025-03-18 11:54:10 -07:00
ollama feat(logging): implement category-based logging (#1362) 2025-03-07 11:34:30 -08:00
openai feat(providers): Groq now uses LiteLLM openai-compat (#1303) 2025-02-27 13:16:50 -08:00
passthrough fix: passthrough impl response.content.text (#1665) 2025-03-17 13:42:08 -07:00
runpod test: add unit test to ensure all config types are instantiable (#1601) 2025-03-12 22:29:58 -07:00
sambanova fix: Updating ToolCall.arguments to allow for json strings that can be decoded on client side (#1685) 2025-03-19 10:36:19 -07:00
tgi fix: solve ruff B008 warnings (#1444) 2025-03-06 16:48:35 -08:00
together feat: Add open benchmark template codegen (#1579) 2025-03-12 11:12:08 -07:00
vllm feat: RFC: tools API rework 2025-03-26 11:14:41 -07:00
__init__.py impls -> inline, adapters -> remote (#381) 2024-11-06 14:54:05 -08:00