https://github.com/CharlesSQ/conversational-agent-with-QA-tool

A custom chat agent implemented using Langchain, gpt-3.5 and Pinecone. Implements memory management for context, a custom prompt template, a custom output parser, and a QA tool.
https://github.com/CharlesSQ/conversational-agent-with-QA-tool

chatgpt langchain llm openai pinecone prompt-engineering

Last synced: 3 days ago
JSON representation

A custom chat agent implemented using Langchain, gpt-3.5 and Pinecone. Implements memory management for context, a custom prompt template, a custom output parser, and a QA tool.

• Host: GitHub
• URL: https://github.com/CharlesSQ/conversational-agent-with-QA-tool
• Owner: CharlesSQ
• Created: 2023-07-26T23:09:26.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-09-03T15:47:11.000Z (over 1 year ago)
• Last Synced: 2023-09-04T18:23:15.606Z (over 1 year ago)
• Topics: chatgpt, langchain, llm, openai, pinecone, prompt-engineering
• Language: Python
• Homepage:
• Size: 14.6 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome_ai_agents - Conversational-Agent-With-Qa-Tool - A custom chat agent implemented using Langchain, gpt-3.5 and Pinecone. Implements memory management for context, a custom prompt template… (Building / Tools)
• awesome_ai_agents - Conversational-Agent-With-Qa-Tool - A custom chat agent implemented using Langchain, gpt-3.5 and Pinecone. Implements memory management for context, a custom prompt template… (Building / Tools)

README

        
# Custom Chat Agent with Langchain and GPT-3.5

This repository contains code that demonstrates how to build a custom chat agent using Langchain, integrating GPT-3.5 from OpenAI. The agent can handle conversational context, provide various tools, and assist in answering questions, including math-related queries.

## Table of Contents

- [Introduction](#introduction)

- [Setup](#setup)

- [Usage](#usage)

- [Configuration](#configuration)

- [License](#license)

## Introduction

The project showcases the implementation of a custom chat agent that leverages Langchain, an open-source framework, to interact with users in a conversational manner. The agent uses a conversational business document search tool. This agent is powered by GPT-3.5 for natural language understanding and generation.

## Setup

1. Clone this repository to your local machine.

2. Install the required dependencies by running: `pip install -r requirements.txt`

3. Obtain the API keys from OpenAI and Pinecone.

4. You must create a `config.py` file that defines the following:

   ```python

   OPENAI_API_KEY = 'YOUR_OPENAI_API_KEY'

   PINECONE_API_KEY = 'YOUR_PINECONE_API_KEY'

   PINECONE_API_ENVIRONMENT = 'YOUR_PINECONE_ENVIRONMENT'

   ```

5. Get a previously created Pinecone index name, for document retrieval and set it in the `constants.py` file.

## Usage

To use the custom chat agent:

1. Run the provided Python script: `python main.py`

2. Enter your message as a user prompt.

3. The agent will process the input and respond with relevant information or tools.

## Configuration

The configuration of the chat agent can be customized by modifying the parameters in the `main.py` script. Key components include:

- Memory: Adjust the conversation memory buffer settings.

- Tools: Define and configure different tools the agent can use.

- Prompt Template: Modify the structure of the prompt used to interact with GPT-3.5.

- Output Parsing: Configure how the agent interprets and processes the model's responses.

## License

This project is licensed under the [MIT License](LICENSE).