github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-10 21:35:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update template index (#12809)

Browse Source
This commit is contained in:
Lance Martin 2023-11-02 17:51:40 -07:00 committed by GitHub
parent 5c0e9ac578
commit 2683c2fc53
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 22 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
templates/docs/INDEX.md
View File

@ -15,7 +15,7 @@ These are some of the more popular templates to get started with.
## 📥 Advanced Retrieval
These templates cover advanced retrieval techniques.
These templates cover advanced retrieval techniques, which can be used for chat and QA over databases or documents.
- [Reranking](../rag-pinecone-rerank): This retrieval technique uses Cohere's reranking endpoint to rerank documents from an initial retrieval step.
- [Anthropic Iterative Search](../anthropic-iterative-search): This retrieval technique uses iterative prompting to determine what to retrieve and whether the retriever documents are good enough.
@ -25,7 +25,7 @@ These templates cover advanced retrieval techniques.
## 🔍Advanced Retrieval - Query Transformation
A selection of advanced retrieval methods that involve transforming the original user query.
A selection of advanced retrieval methods that involve transforming the original user query, which can improve retrieval quality.
- [Hypothetical Document Embeddings](../hyde): A retrieval technique that generates a hypothetical document for a given query, and then uses the embedding of that document to do semantic search. [Paper](https://arxiv.org/abs/2212.10496).
- [Rewrite-Retrieve-Read](../rewrite-retrieve-read): A retrieval technique that rewrites a given query before passing it to a search engine. [Paper](https://arxiv.org/abs/2305.14283).
@ -36,7 +36,7 @@ A selection of advanced retrieval methods that involve transforming the original
## 🧠Advanced Retrieval - Query Construction
A selection of advanced retrieval methods that involve constructing a query in a separate DSL from natural language.
A selection of advanced retrieval methods that involve constructing a query in a separate DSL from natural language, which enable natural languge chat over various structured databases.
- [Elastic Query Generator](../elastic-query-generator): Generate elastic search queries from natural language.
- [Neo4j Cypher Generation](../neo4j-cypher): Generate cypher statements from natural language. Available with a ["full text" option](../neo4j-cypher-ft) as well.
@ -44,7 +44,7 @@ A selection of advanced retrieval methods that involve constructing a query in a
## 🦙 OSS Models
These templates use OSS models.
These templates use OSS models, which enable privacy for sensitive data.
- [Local Retrieval Augmented Generation](../rag-chroma-private): Build a chatbot over your data. Uses only local tooling: Ollama, GPT4all, Chroma.
- [SQL Question Answering (Replicate)](../sql-llama2): Question answering over a SQL database, using Llama2 hosted on [Replicate](https://replicate.com/).
@ -53,11 +53,28 @@ These templates use OSS models.
## ⛏️ Extraction
Extract data in a structured format
These templates extract data in a structured format based upon a user-specified schema.
- [Extraction Using OpenAI Functions](../extraction-openai-functions): Extract information from text using OpenAI Function Calling.
- [Extraction Using Anthropic Functions](../extraction-anthropic-functions): Extract information from text using a LangChain wrapper around the Anthropic endpoints intended to simulate function calling.
- [Extract BioTech Plate Data](../plate-chain): Extract microplate data from messy Excel spreadsheets into a more normalized format.
## ⛏️Summarization and tagging
These templates summarize or categorize documents and text.
- [Summarization using Anthropic](../summarize-anthropic): Uses Anthropic's Claude2 to summarize long documents.
## 🤖 Agents
These templates build chatbots that can take actions, helping to automate tasks.
- [OpenAI Functions Agent](../openai-functions-agent): Build a chatbot that can take actions. Uses OpenAI function calling and Tavily.
- [XML Agent](../xml-agent): Build a chatbot that can take actions. Uses Anthropic and You.com.
## :rotating_light: Safety and evaluation
These templates enable moderation or evaluation of LLM outputs.
- [Guardrails Output Parser](../guardrails-output-parser): Use guardrails-ai to validate LLM output.
- [Chatbot Feedback](../chat-bot-feedback): Use LangSmith to evaluate chatbot responses.