filmov
tv
Building Your Own Langchain Agents and Tools with LLMs: A Step-by-Step Tutorial
Показать описание
The video is about Developing Custom Langchain Agents and Tools using LLMs
The code used in this note book is at
The steps to create Custom Agents re
EASIEST ROUTE IS TO USE LLMCHAIN WITH ZEROSHOT
AGENT. PROMPTS MAKE ALL THE DIFFERENCE
PROMPT TEMPLATE WITH BELOW PARTS
TOOLS: LIST OF TOOLS THE AGENT WILL HAVE ACCESS TO, USED TO FORMAT THE PROMPT.
PREFIX: STRING TO PUT BEFORE THE LIST OF TOOLS.
SUFFIX: STRING TO PUT AFTER THE LIST OF TOOLS.
INPUT_VARIABLES: LIST OF INPUT VARIABLES THE FINAL PROMPT WILL EXPECT.
CREATE LLM CHAIN WITH PROMPT
USE ZERO SHOT AGENT ON THE LLMCHAIN
USING AGENTEXECUTOR.RUN METHOD TO EXECUTE
The steps to create the tools are
TOOLS ARE MADE OF PYTHON FUCTIONS + LLMS
NAME (STR), IS REQUIRED
DESCRIPTION (STR), IS OPTIONAL
FUNCTION, TO EXECUTE
RETURN_DIRECT (BOOL), DEFAULTS TO FALSE
TOOLS ARE CHAINED TOGETHER USING INITIALIZEAGENTS
PYTHON CLASSES CAN BECOME A TOOL BY INHERITING
BASETOOL CLASS
PYTHON FUNCTION CAN BECOME A TOOL BY USING THE
TOOL DECORATOR
The Colab notebook will provide excellent playground to practice these concepts. Use the same, and learn how to build your own tools. Do subscribe to the channel for updates on the videos.
The supporting playlists are
Python Data Engineering Playlist
Python Ecosystem of Libraries
ChatGPT and AI Playlist
AWS and Python AWS Wrangler
PS: Got a question or have a feedback on my content. Get in touch
By leaving a Comment in the video
@twitter Handle is @KQrios
The code used in this note book is at
The steps to create Custom Agents re
EASIEST ROUTE IS TO USE LLMCHAIN WITH ZEROSHOT
AGENT. PROMPTS MAKE ALL THE DIFFERENCE
PROMPT TEMPLATE WITH BELOW PARTS
TOOLS: LIST OF TOOLS THE AGENT WILL HAVE ACCESS TO, USED TO FORMAT THE PROMPT.
PREFIX: STRING TO PUT BEFORE THE LIST OF TOOLS.
SUFFIX: STRING TO PUT AFTER THE LIST OF TOOLS.
INPUT_VARIABLES: LIST OF INPUT VARIABLES THE FINAL PROMPT WILL EXPECT.
CREATE LLM CHAIN WITH PROMPT
USE ZERO SHOT AGENT ON THE LLMCHAIN
USING AGENTEXECUTOR.RUN METHOD TO EXECUTE
The steps to create the tools are
TOOLS ARE MADE OF PYTHON FUCTIONS + LLMS
NAME (STR), IS REQUIRED
DESCRIPTION (STR), IS OPTIONAL
FUNCTION, TO EXECUTE
RETURN_DIRECT (BOOL), DEFAULTS TO FALSE
TOOLS ARE CHAINED TOGETHER USING INITIALIZEAGENTS
PYTHON CLASSES CAN BECOME A TOOL BY INHERITING
BASETOOL CLASS
PYTHON FUNCTION CAN BECOME A TOOL BY USING THE
TOOL DECORATOR
The Colab notebook will provide excellent playground to practice these concepts. Use the same, and learn how to build your own tools. Do subscribe to the channel for updates on the videos.
The supporting playlists are
Python Data Engineering Playlist
Python Ecosystem of Libraries
ChatGPT and AI Playlist
AWS and Python AWS Wrangler
PS: Got a question or have a feedback on my content. Get in touch
By leaving a Comment in the video
@twitter Handle is @KQrios
Комментарии