mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-03 19:57:35 +00:00
ac7c35fbe6
# What does this PR do? Fireworks doesn't allow repsonse_format with tool use. The default response format is 'text' anyway, so we can safely omit. ## Test Plan Below script failed without the change, runs after. ``` #!/usr/bin/env python3 """ Script to test Responses API with kubernetes-mcp-server. This script: 1. Connects to the llama stack server 2. Uses the Responses API with MCP tools 3. Asks for the list of Kubernetes namespaces using the kubernetes-mcp-server """ import json from openai import OpenAI # Connect to the llama stack server base_url = "http://localhost:8321/v1" client = OpenAI(base_url=base_url, api_key="fake") # Define the MCP tool pointing to the kubernetes-mcp-server # The kubernetes-mcp-server is running on port 3000 with SSE endpoint at /sse mcp_server_url = "http://localhost:3000/sse" tools = [ { "type": "mcp", "server_label": "k8s", "server_url": mcp_server_url, } ] # Create a response request asking for k8s namespaces print("Sending request to list Kubernetes namespaces...") print(f"Using MCP server at: {mcp_server_url}") print("Available tools will be listed automatically by the MCP server.") print() response = client.responses.create( # model="meta-llama/Llama-3.2-3B-Instruct", # Using the vllm model model="fireworks/accounts/fireworks/models/llama4-scout-instruct-basic", # model="openai/gpt-4o", input="what are all the Kubernetes namespaces? Use tool call to `namespaces_list`. make sure to adhere to the tool calling format UNDER ALL CIRCUMSTANCES.", tools=tools, stream=False, ) print("\n" + "=" * 80) print("RESPONSE OUTPUT:") print("=" * 80) # Print the output for i, output in enumerate(response.output): print(f"\n[Output {i + 1}] Type: {output.type}") if output.type == "mcp_list_tools": print(f" Server: {output.server_label}") print(f" Tools available: {[t.name for t in output.tools]}") elif output.type == "mcp_call": print(f" Tool called: {output.name}") print(f" Arguments: {output.arguments}") print(f" Result: {output.output}") if output.error: print(f" Error: {output.error}") elif output.type == "message": print(f" Role: {output.role}") print(f" Content: {output.content}") print("\n" + "=" * 80) print("FINAL RESPONSE TEXT:") print("=" * 80) print(response.output_text) ```
39 lines
1,013 B
JSON
39 lines
1,013 B
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:11434/api/ps",
|
|
"headers": {},
|
|
"body": {},
|
|
"endpoint": "/api/ps",
|
|
"model": ""
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "ollama._types.ProcessResponse",
|
|
"__data__": {
|
|
"models": [
|
|
{
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"name": "llama3.2:3b-instruct-fp16",
|
|
"digest": "195a8c01d91ec3cb1e0aad4624a51f2602c51fa7d96110f8ab5a20c84081804d",
|
|
"expires_at": "2025-09-30T14:29:52.682809-07:00",
|
|
"size": 8581748736,
|
|
"size_vram": 8581748736,
|
|
"details": {
|
|
"parent_model": "",
|
|
"format": "gguf",
|
|
"family": "llama",
|
|
"families": [
|
|
"llama"
|
|
],
|
|
"parameter_size": "3.2B",
|
|
"quantization_level": "F16"
|
|
},
|
|
"context_length": null
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|