| Name | tool-calling-llm JSON |
| Version |
0.1.2
JSON |
| download |
| home_page | None |
| Summary | Convert any LangChain Chat Model into a Tool Calling LLM |
| upload_time | 2024-09-19 19:12:13 |
| maintainer | None |
| docs_url | None |
| author | Karim Lalani |
| requires_python | <4.0,>=3.9 |
| license | None |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
Tool Calling LLM
================
Tool Calling LLM is a python mixin that lets you add tool calling capabilities effortlessly to [LangChain](https://langchain.com)'s Chat Models that don't yet support tool/function calling natively. Simply create a new chat model class with ToolCallingLLM and your favorite chat model to get started.
With ToolCallingLLM you also get access to the following functions:
1. `.bind_tools()` allows you to bind tool definitions with a llm.
2. `.with_structured_output()` allows you to return structured data from your model. This is now being provided by LangChain's `BaseChatModel` class.
At this time, ToolCallingLLM has been tested to work with ChatOllama, ChatNVIDIA, and ChatLiteLLM with Ollama provider.
The [OllamaFunctions](https://python.langchain.com/v0.2/docs/integrations/chat/ollama_functions/) was the original inspiration for this effort. The code for ToolCallingLLM was abstracted out of `OllamaFunctions` to allow it to be reused with other non tool calling Chat Models.
Installation
------------
```bash
pip install --upgrade tool_calling_llm
```
Usage
-----
Creating a Tool Calling LLM is as simple as creating a new sub class of the original ChatModel you wish to add tool calling features to.
Below sample code demonstrates how you might enhance `ChatOllama` chat model from `langchain-ollama` package with tool calling capabilities.
```python
from tool_calling_llm import ToolCallingLLM
from langchain_ollama import ChatOllama
from langchain_community.tools import DuckDuckGoSearchRun
class OllamaWithTools(ToolCallingLLM, ChatOllama):
def __init__(self, **kwargs):
super().__init__(**kwargs)
@property
def _llm_type(self):
return "ollama_with_tools"
llm = OllamaWithTools(model="llama3.1",format="json")
tools = [DuckDuckGoSearchRun()]
llm_tools = llm.bind_tools(tools=tools)
llm_tools.invoke("Who won the silver medal in shooting in the Paris Olympics in 2024?")
```
This yields output as follows:
```
AIMessage(content='', id='run-9c3c7a78-97af-4d06-835e-aa81174fd7e8-0', tool_calls=[{'name': 'duckduckgo_search', 'args': {'query': 'Paris Olympics 2024 shooting silver medal winner'}, 'id': 'call_67b06088e208482497f6f8314e0f1a0e', 'type': 'tool_call'}])
```
For more comprehensive examples, refer to [ToolCallingLLM-Tutorial.ipynb](ToolCallingLLM-Tutorial.ipynb) jupyter notebook.
Raw data
{
"_id": null,
"home_page": null,
"name": "tool-calling-llm",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": null,
"author": "Karim Lalani",
"author_email": "jimmy00784@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/2a/be/0e7d3f4d75c49cfe672f408b5ca8e0bb24a4415570cd14c46e968958b5fb/tool_calling_llm-0.1.2.tar.gz",
"platform": null,
"description": "Tool Calling LLM\n================\n\nTool Calling LLM is a python mixin that lets you add tool calling capabilities effortlessly to [LangChain](https://langchain.com)'s Chat Models that don't yet support tool/function calling natively. Simply create a new chat model class with ToolCallingLLM and your favorite chat model to get started.\n\nWith ToolCallingLLM you also get access to the following functions:\n1. `.bind_tools()` allows you to bind tool definitions with a llm.\n2. `.with_structured_output()` allows you to return structured data from your model. This is now being provided by LangChain's `BaseChatModel` class.\n\nAt this time, ToolCallingLLM has been tested to work with ChatOllama, ChatNVIDIA, and ChatLiteLLM with Ollama provider.\n\nThe [OllamaFunctions](https://python.langchain.com/v0.2/docs/integrations/chat/ollama_functions/) was the original inspiration for this effort. The code for ToolCallingLLM was abstracted out of `OllamaFunctions` to allow it to be reused with other non tool calling Chat Models.\n\nInstallation\n------------\n\n```bash\npip install --upgrade tool_calling_llm\n```\n\nUsage\n-----\n\nCreating a Tool Calling LLM is as simple as creating a new sub class of the original ChatModel you wish to add tool calling features to. \n\nBelow sample code demonstrates how you might enhance `ChatOllama` chat model from `langchain-ollama` package with tool calling capabilities.\n\n```python\nfrom tool_calling_llm import ToolCallingLLM\nfrom langchain_ollama import ChatOllama\nfrom langchain_community.tools import DuckDuckGoSearchRun\n\n\nclass OllamaWithTools(ToolCallingLLM, ChatOllama):\n def __init__(self, **kwargs):\n super().__init__(**kwargs)\n\n @property\n def _llm_type(self):\n return \"ollama_with_tools\"\n\n\nllm = OllamaWithTools(model=\"llama3.1\",format=\"json\")\ntools = [DuckDuckGoSearchRun()]\nllm_tools = llm.bind_tools(tools=tools)\n\nllm_tools.invoke(\"Who won the silver medal in shooting in the Paris Olympics in 2024?\")\n```\n\nThis yields output as follows:\n```\nAIMessage(content='', id='run-9c3c7a78-97af-4d06-835e-aa81174fd7e8-0', tool_calls=[{'name': 'duckduckgo_search', 'args': {'query': 'Paris Olympics 2024 shooting silver medal winner'}, 'id': 'call_67b06088e208482497f6f8314e0f1a0e', 'type': 'tool_call'}])\n```\nFor more comprehensive examples, refer to [ToolCallingLLM-Tutorial.ipynb](ToolCallingLLM-Tutorial.ipynb) jupyter notebook.\n\n",
"bugtrack_url": null,
"license": null,
"summary": "Convert any LangChain Chat Model into a Tool Calling LLM",
"version": "0.1.2",
"project_urls": {
"Homepage": "https://github.com/lalanikarim/tool_calling_llm",
"Issues": "https://github.com/lalanikarim/tool_calling_llm/issues"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "75bb21d50be4cb02e64e2700bc2dbe26a0646bf74534f0b11c858d5bbc2fefad",
"md5": "39e507b2d862eed7a62c4b432488a008",
"sha256": "bc0aa3a1f9f522a0ca9d131e8241be6861233d5ebfb649a04ccf2a00f2ade50c"
},
"downloads": -1,
"filename": "tool_calling_llm-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "39e507b2d862eed7a62c4b432488a008",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 7460,
"upload_time": "2024-09-19T19:12:11",
"upload_time_iso_8601": "2024-09-19T19:12:11.465200Z",
"url": "https://files.pythonhosted.org/packages/75/bb/21d50be4cb02e64e2700bc2dbe26a0646bf74534f0b11c858d5bbc2fefad/tool_calling_llm-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "2abe0e7d3f4d75c49cfe672f408b5ca8e0bb24a4415570cd14c46e968958b5fb",
"md5": "cf55aaf5b7dce14c802a0d901ff3f509",
"sha256": "b558d0229b6cee840ca3b123673067c2c5fa9323590ed1dcbb5e2c06432c5d8a"
},
"downloads": -1,
"filename": "tool_calling_llm-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "cf55aaf5b7dce14c802a0d901ff3f509",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 6666,
"upload_time": "2024-09-19T19:12:13",
"upload_time_iso_8601": "2024-09-19T19:12:13.080536Z",
"url": "https://files.pythonhosted.org/packages/2a/be/0e7d3f4d75c49cfe672f408b5ca8e0bb24a4415570cd14c46e968958b5fb/tool_calling_llm-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-19 19:12:13",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "lalanikarim",
"github_project": "tool_calling_llm",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "tool-calling-llm"
}
