Example curl requests for OpenAI's function calling API using a local Ollama docker container with the llama3.1 model.
Step 1:
Ask the LLM a question and provide the function it can call to gather the required information.
In this case, we want to know the current weather and provide the get_current_weather function definition.
Note: If you use a local Ollama instance, you can remove the "Authorization"-header.
Request:
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "llama3.1",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How is the current weather in Graz?"
}
],
"parallel_tool_calls": false,
"tools": [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and country, eg. San Francisco, USA"
},
"format": { "type": "string", "enum": ["celsius", "fahrenheit"] }
},
"required": ["location", "format"]
}
}
}
]
}'Response:
Llama3.1 responds by requesting the result of the get_current_weather function:
{
"id": "chatcmpl-202",
"object": "chat.completion",
"created": 1723311089,
"model": "llama3.1",
"system_fingerprint": "fp_ollama",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_fu6au6uj",
"type": "function",
"function": {
"name": "get_current_weather",
"arguments": "{\"format\":\"fahrenheit\",\"location\":\"Graz, Austria\"}"
}
}
]
},
"finish_reason": "tool_calls"
}
],
"usage": {
"prompt_tokens": 184,
"completion_tokens": 28,
"total_tokens": 212
}
}Step 2:
We can now call our local function get_current_weather and return the result (Graz 30 °C) to the LLM by responding like this:
Request:
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "llama3.1",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "How is the current weather?"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_fu6au6uj",
"type": "function",
"function": {
"name": "get_current_weather",
"arguments": "{\"format\":\"fahrenheit\",\"location\":\"Graz, Austria\"}"
}
}
]
},
{
"role": "tool",
"content": "{\"city\":\"Graz\",\"weather\":\"30°C\"}",
"tool_call_id": "call_fu6au6uj"
}
],
"parallel_tool_calls": false,
"tools": [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and country, eg. San Francisco, USA"
},
"format": { "type": "string", "enum": ["celsius", "fahrenheit"] }
},
"required": ["location", "format"]
}
}
}
]
}'Response:
The LLM now returns the answer with the result of the get_current_weather function:
{
"id": "chatcmpl-371",
"object": "chat.completion",
"created": 1723315198,
"model": "llama3.1",
"system_fingerprint": "fp_ollama",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "The current temperature in Graz is 30°C (86°F), which assumes it's clear and sunny today."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 81,
"completion_tokens": 23,
"total_tokens": 104
}
}You can also try this yourself by only executing the request in step 2, since it contains the whole chat history.
Useful resources: