https://github.com/onepointconsulting/elasticsearch-agent

ElasticSearch agent based on ElasticSearch, LangChain and ChatGPT 4
https://github.com/onepointconsulting/elasticsearch-agent

Last synced: about 1 month ago
JSON representation

ElasticSearch agent based on ElasticSearch, LangChain and ChatGPT 4

• Host: GitHub
• URL: https://github.com/onepointconsulting/elasticsearch-agent
• Owner: onepointconsulting
• Created: 2023-10-10T17:38:31.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2023-10-17T17:43:35.000Z (8 months ago)
• Last Synced: 2024-04-28T02:07:15.111Z (2 months ago)
• Language: Python
• Size: 185 KB
• Stars: 25
• Watchers: 1
• Forks: 10
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Lists

• awesome-langchain - Elasticsearch Agent - agent?style=social) (Tools / Agents)
• awesome-agents - Elasticsearch Agent - agent?style=social) (Langchain Agents)
• awesome-langchain-zh - Elasticsearch Agent - agent?style=social): 一个基于 elasticsearch,langchain,gpt4的gpt 代理 (工具 / 代理)

README

        
# Elasticsearch Langchain Agent

This project uses ElasticSearch together with LangChain and ChatGPT 4 to build an agent with which you can ask intelligent questions on

top of an ElasticSearch cluster.

## Setup

We suggest to use [Conda](https://docs.conda.io/en/latest/) to manage the virtual environment and then install poetry.

```

conda activate base

conda remove -n elastic_search_playground --all

conda create -n elastic_search_playground python=3.11

conda activate elastic_search_playground

pip install poetry

``````

## Installation

```

poetry install

```

## Configuration

The configuration should be saved in a `.env` file.

```

OPENAI_API_KEY=

OPENAI_MODEL=gpt-4-0613

# OPENAI_MODEL=gpt-3.5-turbo-16k-0613

REQUEST_TIMEOUT=300

LANGCHAIN_CACHE=false

CHATGPT_STREAMING=false

LLM_VERBOSE=true

# Elastic Search related

ELASTIC_SERVER=https://127.0.0.1:9200

ELASTIC_USER=elastic

ELASTIC_PASSWORD=

ELASTIC_VERIFY_CERTIFICATES=false

ELASTIC_INDEX_DATA_FROM=0

ELASTIC_INDEX_DATA_SIZE=5

ELASTIC_INDEX_DATA_MAX_SIZE=50

LANGCHAIN_VERBOSE=true

AGGS_LIMIT=200

TOKEN_LIMIT=6000

MAX_SEARCH_RETRIES = 100

```

Please note that the agent works best with ChatGPT 4.