智能体开发,实现自定义知识库,基于 LangChain,qwen 7b, ollama, chatopera | LLMs

Agent built with LangChain, and Chatopera Cloud

By themselves, language models can't take actions - they just output text. A big use case for LangChain is creating agents. Agents are systems that use LLMs as reasoning engines to determine which actions to take and the inputs necessary to perform the action. After executing actions, the results can be fed back into the LLM to determine whether more actions are needed, or whether it is okay to finish. This is often achieved via tool-calling.

本教程示例程序:https://github.com/hailiang-wang/llm-get-started/tree/master/005_agent_langchain

Config custom knowledge base with Chatopera Cloud Services, https://bot.chatopera.com/

Leverge chat routes with LLMs - e.g. mistral-nemo, myaniu/qwen2.5-1m:7b, myaniu/qwen2.5-1m:14b.

RAG & Agent

Start

First, install ollama, next, run ollama pull mistral-nemo:latest, checkout mistral-nemo.

Next, install pip deps.

复制代码
pip install -r requirements.txt

Then, config env file.

复制代码
cp sample.env .env # Modify key-values in .env

At last, run

复制代码
./start.sh

Other tool calling enabled models

复制代码
myaniu/qwen2.5-1m:7b
myaniu/qwen2.5-1m:14b
相关推荐
AI大模型10 小时前
LangGraph官方文档笔记(6)——时间旅行
程序员·langchain·llm
是小王同学啊~1 天前
(LangChain)RAG系统链路向量检索器之Retrievers(五)
python·算法·langchain
AIGC包拥它1 天前
提示技术系列——链式提示
人工智能·python·langchain·prompt
AI大模型1 天前
LangGraph官方文档笔记(4)——提示聊天机器人
程序员·langchain·llm
OpenAppAI2 天前
Few-shot Prompting(少样本提示)概念指南
langchain·few-shot·prompts
余衫马11 天前
LangChain 文本分割器深度解析:从原理到落地应用(上)
langchain·文本分割器
大千AI助手13 天前
LangChain执行引擎揭秘:RunnableConfig配置全解析
人工智能·langchain·config
精灵vector13 天前
Agent的记忆详细实现机制
python·langchain·llm
少林码僧14 天前
14.2 《3小时从零搭建企业级LLaMA3语言助手:GitHub配置+私有化模型集成全实战》
人工智能·机器学习·语言模型·langchain
何双新14 天前
第3讲、LangChain性能优化:上下文缓存与流式响应实战指南
缓存·性能优化·langchain