Functionary

Functionary is a language model that can interpret and execute functions/plugins.

The model determines when to execute functions, whether in parallel or serially, and can understand their outputs. It only triggers functions as needed. Function definitions are given as JSON Schema Objects, similar to OpenAI GPT function calls.

Documentation and more examples: functionary.meetkai.com

Setup

To install the required dependencies, run:

pip install -r requirements.txt

Now you can start a blazing fast vLLM server. requirements

Small Model:

python3 server_vllm.py --model "meetkai/functionary-small-v2.4" --host 0.0.0.0 --max-model-len 8192

Medium model: (click to expand)

If you use multiple GPUs (medium models require: 4A6000 or 2A100 80GB to run), need to use: tensor-parallel-size

python3 server_vllm.py --model "meetkai/functionary-medium-v2.4" --max-model-len 8192 --tensor-parallel-size 2

Grammar Sampling

We also offer our own function-calling grammar sampling feature which constrains the LLM's generation to always follow the prompt template, and ensures 100% accuracy for function name. The parameters are generated using the efficient lm-format-enforcer, which ensures that the parameters follow the schema of the tool called. To enable grammar sampling, run the vLLM server with the command-line argument --enable-grammar-sampling:

python3 server_vllm.py --model "meetkai/functionary-medium-v2.4" --max-model-len 8192 --tensor-parallel-size 2 --enable-grammar-sampling

Docker

If you're having trouble with dependencies, and you have nvidia-container-toolkit, you can start your environment like this:

sudo docker run --gpus all -it --ipc=host --name functionary -v ${PWD}/functionary_workspace:/workspace -p 8000:8000 nvcr.io/nvidia/pytorch:23.10-py3

OpenAI Compatible Usage

from openai import OpenAI

client = OpenAI(base_url="https://localhost:8000/v1", api_key="functionary")

client.chat.completions.create(
    model="meetkai/functionary-small-v2.4",
    messages=[{"role": "user",
            "content": "What is the weather for Istanbul?"}
    ],
    tools=[{
            "type": "function",
            "function": {
                "name": "get_current_weather",
                "description": "Get the current weather",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "location": {
                            "type": "string",
                            "description": "The city and state, e.g. San Francisco, CA"
                        }
                    },
                    "required": ["location"]
                }
            }
        }],
    tool_choice="auto"
)

Raw Usage:

Details (click to expand)

import requests

data = {
    'model': 'meetkai/functionary-small-v2.4', # model name here is the value of argument "--model" in deploying: server_vllm.py or server.py
    'messages': [
        {
            "role": "user",
            "content": "What is the weather for Istanbul?"
        }
    ],
    'tools':[ # For functionary-7b-v2 we use "tools"; for functionary-7b-v1.4 we use "functions" = [{"name": "get_current_weather", "description":..., "parameters": ....}]
        {
            "type": "function",
            "function": {
                "name": "get_current_weather",
                "description": "Get the current weather",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "location": {
                            "type": "string",
                            "description": "The city and state, e.g. San Francisco, CA"
                        }
                    },
                    "required": ["location"]
                }
            }
        }
    ]
}

response = requests.post("https://127.0.0.1:8000/v1/chat/completions", json=data, headers={
    "Content-Type": "application/json",
    "Authorization": "Bearer xxxx"
})

# Print the response text
print(response.text)

Models Available

Model	Description	VRAM FP16
functionary-small-v2.4 / GGUF	8k context, code interpreter	24GB
functionary-medium-v2.4 / GGUF	8k context, code interpreter, better accuracy	90GB
functionary-small-v2.2 / GGUF	8k context	24GB
functionary-medium-v2.2 / GGUF	8k context	90GB
functionary-7b-v2.1 / GGUF	8k context	24GB
functionary-7b-v2 / GGUF	Parallel function call support.	24GB
functionary-7b-v1.4 / GGUF	4k context, better accuracy (deprecated)	24GB
functionary-7b-v1.1	4k context (deprecated)	24GB
functionary-7b-v0.1	2k context (deprecated) Not recommended, use 2.1 onwards	24GB

Compatibility information

v1 models are compatible with both OpenAI-python v0 and v1.
v2 models are designed for compatibility with OpenAI-python v1.

The difference between OpenAI-python v0 and v1 you may refer to the official documentation here

The Differences Between Related Projects

Feature/Project	Functionary	NexusRaven	Gorilla	Glaive	GPT-4-1106-preview
Single Function Call	✅	✅	✅	✅	✅
Parallel Function Calls	✅	✅	✅	❌	✅
Following Up on Missing Function Arguments	✅	❌	❌	❌	✅
Multi-turn	✅	❌	❌	✅	✅
Generate Model Responses Grounded in Tools Execution Results	✅	❌	❌	❌	✅
Chit-Chat	✅	❌	✅	✅	✅
Code Interpreter	✅	❌	❌	❌	✅

You can find more details of the features in here

Llama.cpp Inference

Make sure that the latest version of llama-cpp-python is successully installed in your system. Functionary v2 is fully integrated into llama-cpp-python. You can perform inference using Functionary's GGUF models either via normal chat completion or through llama-cpp-python's OpenAI-compatible server which behaves similarly to ours.

The following is the sample code using normal chat completion:

from llama_cpp import Llama
from llama_cpp.llama_tokenizer import LlamaHFTokenizer

# We should use HF AutoTokenizer instead of llama.cpp's tokenizer because we found that Llama.cpp's tokenizer doesn't give the same result as that from Huggingface. The reason might be in the training, we added new tokens to the tokenizer and Llama.cpp doesn't handle this successfully
llm = Llama.from_pretrained(
    repo_id="meetkai/functionary-small-v2.4-GGUF",
    filename="functionary-small-v2.4.Q4_0.gguf",
    chat_format="functionary-v2",
    tokenizer=LlamaHFTokenizer.from_pretrained("meetkai/functionary-small-v2.4-GGUF"),
    n_gpu_layers=-1
)

messages = [
    {"role": "user", "content": "what's the weather like in Hanoi?"}
]
tools = [ # For functionary-7b-v2 we use "tools"; for functionary-7b-v1.4 we use "functions" = [{"name": "get_current_weather", "description":..., "parameters": ....}]
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Get the current weather",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g., San Francisco, CA"
                    }
                },
                "required": ["location"]
            }
        }
    }
]

result = llm.create_chat_completion(
      messages = messages,
      tools=tools,
      tool_choice="auto",
)

print(result["choices"][0]["message"])

The output would be:

{'role': 'assistant', 'content': None, 'tool_calls': [{'type': 'function', 'function': {'name': 'get_current_weather', 'arguments': '{\n  "location": "Hanoi"\n}'}}]}

For more details, please refer to the Function Calling section in llama-cpp-python. To use our Functionary GGUF models using llama-cpp-python's OpenAI-compatible server, please refer to here for more details and documentation.

Note:

For Functionary in llama-cpp-python, the default system messages are added automatically during the API call. Therefore, there is no need to provide the default system messages in messages.
llama-cpp-python's OpenAI-compatible server does not support streaming for Functionary models yet.

Call Real Python Function

To call the real python function, get the result and extract the result to respond, you can use chatlab. The following example uses chatlab==0.16.0:

Please note that Chatlab currently doesn't support Parallel Function calls. This sample code is compatible only with Functionary Version 1.4 and may not work correctly with Functionary Version 2.0.

from chatlab import Conversation
import openai
import os
openai.api_key = "functionary" # We just need to set this something other than None
os.environ['OPENAI_API_KEY'] = "functionary" # chatlab requires us to set this too
openai.api_base = "https://localhost:8000/v1"

# now provide the function with description
def get_car_price(car_name: str):
    """this function is used to get the price of the car given the name
    :param car_name: name of the car to get the price
    """
    car_price = {
        "tang": {"price": "$20000"},
        "song": {"price": "$25000"} 
    }
    for key in car_price:
        if key in car_name.lower():
            return {"price": car_price[key]}
    return {"price": "unknown"}

chat = Conversation(model="meetkai/functionary-7b-v2")
chat.register(get_car_price)  # register this function
chat.submit("what is the price of the car named Tang?") # submit user prompt

# print the flow
for message in chat.messages:
    role = message["role"].upper()
    if "function_call" in message:
        func_name = message["function_call"]["name"]
        func_param = message["function_call"]["arguments"]
        print(f"{role}: call function: {func_name}, arguments:{func_param}")
    else:
        content = message["content"]
        print(f"{role}: {content}")

The output will look like this:

USER: what is the price of the car named Tang?
ASSISTANT: call function: get_car_price, arguments:{
  "car_name": "Tang"
}
FUNCTION: {'price': {'price': '$20000'}}
ASSISTANT: The price of the car named Tang is $20,000.

Use Cases

Here are a few examples of how you can use this function calling system:

Travel and Hospitality - Trip Planning

The function plan_trip(destination: string, duration: int, interests: list) can take user input such as "I want to plan a 7-day trip to Paris with a focus on art and culture" and generate an itinerary accordingly.

Details (click to expand)

client.chat.completions.create((
    model="meetkai/functionary-7b-v2",
    messages=[
        {"role": "user", "content": 'I want to plan a 7-day trip to Paris with a focus on art and culture'},
    ], 
    tools=[
        {
            "type": "function",
            "function": {
                "name": "plan_trip",
                "description": "Plan a trip based on user's interests",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "destination": {
                            "type": "string",
                            "description": "The destination of the trip",
                        },
                        "duration": {
                            "type": "integer",
                            "description": "The duration of the trip in days",
                        },
                        "interests": {
                            "type": "array",
                            "items": {"type": "string"},
                            "description": "The interests based on which the trip will be planned",
                        },
                    },
                    "required": ["destination", "duration", "interests"],
                }
            }
        }    
    ]
)

Response will have:

{"role": "assistant", "content": null, "tool_calls": [{"type": "function", "function": {"name": "plan_trip", "arguments": '{\n  "destination": "Paris",\n  "duration": 7,\n  "interests": ["art", "culture"]\n}'}}]}

Then you need to call plan_trip function with provided arguments. If you would like a commentary from the model, then you'll call the model again with the response from the function, the model will write necessary commentary.

Real Estate - Property Valuation

A function like estimate_property_value(property_details: dict) could allow users to input details about a property (such as location, size, number of rooms, etc.) and receive an estimated market value.

Details (click to expand)

client.chat.completions.create(
    model="meetkai/functionary-7b-v2",
    messages=[
        {
            "role": "user", 
            "content": 'What is the estimated value of a 3-bedroom house in San Francisco with 2000 sq ft area?'
        },
        {
            "role": "assistant", 
            "content": None, 
            "tool_calls": [
                {
                    "type": "function", 
                    "function": {
                        "name": "estimate_property_value", 
                        "arguments": '{\n  "property_details": {"location": "San Francisco", "size": 2000, "rooms": 3}\n}'
                    }
                }
            ]
        }
    ], 
    tools=[
        {
            "type": "function",
            "function": {
                "name": "estimate_property_value",
                "description": "Estimate the market value of a property",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "property_details": {
                            "type": "object",
                            "properties": {
                                "location": {
                                    "type": "string",
                                    "description": "The location of the property"
                                },
                                "size": {
                                    "type": "integer",
                                    "description": "The size of the property in square feet"
                                },
                                "rooms": {
                                    "type": "integer",
                                    "description": "The number of rooms in the property"
                                }
                            },
                            "required": ["location", "size", "rooms"]
                        }
                    },
                    "required": ["property_details"]
                }
            }
        }
    ],
    tool_choice="auto"
)

Response will have:

{"role": "assistant", "content": null, "tool_calls": [{"type": "function", "function": {"name": "plan_trip", "arguments": '{\n  "destination": "Paris",\n  "duration": 7,\n  "interests": ["art", "culture"]\n}'}}]}

Then you need to call plan_trip function with provided arguments. If you would like a commentary from the model, then you'll call the model again with the response from the function, the model will write necessary commentary.

Telecommunications - Customer Support

A function parse_customer_complaint(complaint: {issue: string, frequency: string, duration: string}) could help in extracting structured information from a complex, narrative customer complaint, identifying the core issue and potential solutions. The complaint object could include properties such as issue (the main problem), frequency (how often the issue occurs), and duration (how long the issue has been occurring).

Details (click to expand)

client.chat.completions.create(
    model="meetkai/functionary-7b-v2",
    messages=[
        {"role": "user", "content": 'My internet has been disconnecting frequently for the past week'},
    ], 
    tools=[
        {
            "type": "function",
            "function": {
            "name": "parse_customer_complaint",
            "description": "Parse a customer complaint and identify the core issue",
            "parameters": {
                "type": "object",
                "properties": {
                    "complaint": {
                        "type": "object",
                        "properties": {
                            "issue": {
                                "type": "string",
                                "description": "The main problem",
                            },
                            "frequency": {
                                "type": "string",
                                "description": "How often the issue occurs",
                            },
                            "duration": {
                                "type": "string",
                                "description": "How long the issue has been occurring",
                            },
                        },
                        "required": ["issue", "frequency", "duration"],
                    },
                },
                "required": ["complaint"],
            }
        }
     }
    ],
    tool_choice="auto"
)

Response will have:

{"role": "assistant", "content": null, "tool_calls": [{"type": "function", "function": {"name": "parse_customer_complaint", "arguments": '{\n  "complaint": {"issue": "internet disconnecting", "frequency": "frequently", "duration": "past week"}\n}'}}]}

Then you need to call parse_customer_complaint function with provided arguments. If you would like a commentary from the model, then you'll call the model again with the response from the function, the model will write necessary commentary.

How it Works?

We convert function definitions to a similar text to TypeScript definitions. Then we inject these definitions as system prompts. After that, we inject the default system prompt. Then we start the conversation messages.

The prompt example can be found here: V1 and V2

We don't change the logit probabilities to conform to a certain schema, but the model itself knows how to conform. This allows us to use existing tools and caching systems with ease.

Evaluation

Function Prediction Evaluation

Evaluation function call prediction in SGD dataset. The accuracy metric measures the overall correctness of predicted function calls, including function name prediction and arguments extraction.

Dataset	Model Name	Function Calling Accuracy (Name & Arguments)
SGD	MeetKai-functionary-small-v2.4	0.830
SGD	MeetKai-functionary-medium-v2.4	0.881
SGD	OpenAI-gpt-3.5-turbo-0125	0.716
SGD	OpenAI-gpt-4-turbo-0125	0.762

Training

See training README

Name		Name	Last commit message	Last commit date
Latest commit History 520 Commits
.github/workflows		.github/workflows
.vscode		.vscode
assets		assets
functionary		functionary
tests		tests
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
example_llama_cpp.py		example_llama_cpp.py
features_desc.md		features_desc.md
modal_server.py		modal_server.py
requirements.txt		requirements.txt
server_vllm.py		server_vllm.py

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Repository files navigation

Functionary

Setup

OpenAI Compatible Usage

Raw Usage:

Models Available

Compatibility information

The Differences Between Related Projects

Llama.cpp Inference

Call Real Python Function

Use Cases

Travel and Hospitality - Trip Planning

Real Estate - Property Valuation

Telecommunications - Customer Support

How it Works?

Evaluation

Function Prediction Evaluation

Training

Roadmap

About

Releases

Packages

Languages

License

mivanovitch/functionary

Folders and files

Latest commit

History

Repository files navigation

Functionary

Setup

OpenAI Compatible Usage

Raw Usage:

Models Available

Compatibility information

The Differences Between Related Projects

Llama.cpp Inference

Call Real Python Function

Use Cases

Travel and Hospitality - Trip Planning

Real Estate - Property Valuation

Telecommunications - Customer Support

How it Works?

Evaluation

Function Prediction Evaluation

Training

Roadmap

About

Resources

License

Stars

Watchers

Forks

Releases

Packages 0

Languages

Packages