附加 ( Additional )

📄️ 分析文档 (Analyze Document)

LangChain

📄️ ConstitutionalChain 自我批判链

LangChain

📄️ 抽取

抽取链使用OpenAI的"functions"参数来指定从文档中抽取实体的模式。这样可以确保模型输出我们想要的实体和属性模式，并具有适当的类型。

📄️ FLARE

This notebook is an implementation of Forward-Looking Active REtrieval augmented generation (FLARE).

📄️ Graph DB QA chain

This notebook shows how to use LLMs to provide a natural language interface to a graph database you can query with the Cypher query language.

📄️ NebulaGraphQAChain

本笔记本展示了如何使用语言模型为NebulaGraph数据库提供自然语言接口。

📄️ Graph QA

This notebook goes over how to do question answering over a graph data structure.

📄️ 虚拟文档嵌入

这个笔记本介绍了如何使用虚拟文档嵌入（HyDE），如这篇论文所述。

📄️ Bash chain

This notebook showcases using LLMs and a bash process to perform simple filesystem commands.

📄️ 自检链

这个笔记本展示了如何使用LLMCheckerChain。

📄️ 数学链

本笔记本展示了使用LLMs和Python REPL解决复杂的数学问题。

📄️ HTTP request chain

使用request库从URL获取HTML结果，然后使用LLM解析结果

📄️ Summarization checker chain

This notebook shows some examples of LLMSummarizationCheckerChain in use with different types of texts. It has a few distinct differences from the LLMCheckerChain, in that it doesn't have any assumptions to the format of the input text (or summary).

📄️ 审查 Moderation

LangChain

📄️ 动态从多个提示中选择 multi_prompt_router

LangChain

📄️ 动态选择多个检索器 multi_retrieval_qa_router

LangChain

📄️ 使用OpenAI函数进行检索问答

OpenAI函数允许对响应输出进行结构化。在问答问题时，除了获取最终答案外，还可以获取支持证据、引用等，这通常很有用。

📄️ OpenAPI chain

This notebook shows an example of using an OpenAPI chain to call an endpoint in natural language, and get back a response in natural language.

📄️ Program-aided language model (PAL) chain

Implements Program-Aided Language Models, as in https://arxiv.org/pdf/2211.10435.pdf.

📄️ Question-Answering Citations

This notebook shows how to use OpenAI functions ability to extract citations from text.

📄️ 文档问答 qa_with_sources

LangChain

📄️ 标记

标记链使用OpenAI的functions参数来指定用于标记文档的模式。这帮助我们确保模型输出我们想要的准确标记及其适当的类型。

📄️ Vector store-augmented text generation

This notebook walks through how to use LangChain for text generation over a vector index. This is useful if we want to generate text that is able to draw from a large body of custom text, for example, generating blog posts that have an understanding of previous blog posts written, or product tutorials that can refer to product documentation.