README
¶
🎉 Join our new official Discord community! Connect with other LangChain Go developers and get help: Join Discord
🦜️🔗 LangChain Go
⚡ Building applications with LLMs through composability, with Go! ⚡
🤔 What is this?
This is the Go language implementation of LangChain.
📖 Documentation
🎉 Examples
See ./examples for example usage.
package main
import (
"context"
"fmt"
"log"
"github.com/tmc/langchaingo/llms"
"github.com/tmc/langchaingo/llms/openai"
)
func main() {
ctx := context.Background()
llm, err := openai.New()
if err != nil {
log.Fatal(err)
}
prompt := "What would be a good company name for a company that makes colorful socks?"
completion, err := llms.GenerateFromSinglePrompt(ctx, llm, prompt)
if err != nil {
log.Fatal(err)
}
fmt.Println(completion)
}
$ go run .
Socktastic
Resources
Here are some links to blog posts and articles on using Langchain Go:
- Using Gemini models in Go with LangChainGo - Jan 2024
- Using Ollama with LangChainGo - Nov 2023
- Creating a simple ChatGPT clone with Go - Aug 2023
- Creating a ChatGPT Clone that Runs on Your Laptop with Go - Aug 2023
Contributors
Documentation
¶
Overview ¶
Package langchaingo implements the Go language version of the langchain project.
Directories
¶
| Path | Synopsis |
|---|---|
|
Package agents contains the standard interface all agents must implement, implementations of this interface, and an agent executor.
|
Package agents contains the standard interface all agents must implement, implementations of this interface, and an agent executor. |
|
Package callbacks includes a standard interface for hooking into various stages of your LLM application.
|
Package callbacks includes a standard interface for hooking into various stages of your LLM application. |
|
Package chains contains a standard interface for chains, a number of built-in chains and functions for calling and running chains.
|
Package chains contains a standard interface for chains, a number of built-in chains and functions for calling and running chains. |
|
Package documentloaders includes a standard interface for loading documents from a source and implementations of this interface.
|
Package documentloaders includes a standard interface for loading documents from a source and implementations of this interface. |
|
Package embeddings contains helpers for creating vector embeddings from text using different providers.
|
Package embeddings contains helpers for creating vector embeddings from text using different providers. |
|
examples
|
|
|
deepseek-completion-example
command
|
|
|
maritaca-example
command
|
|
|
openai-embeddings-example
command
|
|
|
zep-memory-chain-example
command
|
|
|
Package exp contains experimental code that is subject to change or removal.
|
Package exp contains experimental code that is subject to change or removal. |
|
internal
|
|
|
Package jsonschema provides very simple functionality for representing a JSON schema as a (nested) struct.
|
Package jsonschema provides very simple functionality for representing a JSON schema as a (nested) struct. |
|
Package llms provides unified support for interacting with different Language Models (LLMs) from various providers.
|
Package llms provides unified support for interacting with different Language Models (LLMs) from various providers. |
|
cache
Package cache provides a generic wrapper that adds caching to a `llms.Model`.
|
Package cache provides a generic wrapper that adds caching to a `llms.Model`. |
|
ernie
Package ernie wrapper around the Baidu Large Language Model Platform APIs.
|
Package ernie wrapper around the Baidu Large Language Model Platform APIs. |
|
googleai
package googleai implements a langchaingo provider for Google AI LLMs.
|
package googleai implements a langchaingo provider for Google AI LLMs. |
|
googleai/internal/cmd
command
Code generator for vertex.go from googleai.go nolint
|
Code generator for vertex.go from googleai.go nolint |
|
googleai/palm
package palm implements a langchaingo provider for Google Vertex AI legacy PaLM models.
|
package palm implements a langchaingo provider for Google Vertex AI legacy PaLM models. |
|
googleai/vertex
package vertex implements a langchaingo provider for Google Vertex AI LLMs, including the new Gemini models.
|
package vertex implements a langchaingo provider for Google Vertex AI LLMs, including the new Gemini models. |
|
local/internal/localclient
Package localclient provides a client for local LLMs.
|
Package localclient provides a client for local LLMs. |
|
Package memory provides an interface for managing conversational data and a variety of implementations for storing and retrieving that data.
|
Package memory provides an interface for managing conversational data and a variety of implementations for storing and retrieving that data. |
|
sqlite3
Package sqlite3 adds support for chat message history using sqlite3.
|
Package sqlite3 adds support for chat message history using sqlite3. |
|
Package outputparser provides a set of output parsers to process structured or unstructured data from language models (LLMs).
|
Package outputparser provides a set of output parsers to process structured or unstructured data from language models (LLMs). |
|
Package prompts contains types, prompt templates, loading utilities, output parsers, example selectors, and other utilities for working with LLM prompts.
|
Package prompts contains types, prompt templates, loading utilities, output parsers, example selectors, and other utilities for working with LLM prompts. |
|
internal/fstring
Package fstring contains template format with f-string.
|
Package fstring contains template format with f-string. |
|
Package schema implements a shared core set of data types for use in langchaingo.
|
Package schema implements a shared core set of data types for use in langchaingo. |
|
Package textsplitter provides tools for splitting long texts into smaller chunks based on configurable rules and parameters.
|
Package textsplitter provides tools for splitting long texts into smaller chunks based on configurable rules and parameters. |
|
Package tools defines a standard interface for tools to be used by agents.
|
Package tools defines a standard interface for tools to be used by agents. |
|
duckduckgo
Package duckduckgo contains an implementation of the tool interface with the duckduckgo api client.
|
Package duckduckgo contains an implementation of the tool interface with the duckduckgo api client. |
|
metaphor
// Package metaphor contains an implementation of the tool interface with the metaphor search api client.
|
// Package metaphor contains an implementation of the tool interface with the metaphor search api client. |
|
perplexity
Package perplexity provides integration with Perplexity AI's API for AI agents.
|
Package perplexity provides integration with Perplexity AI's API for AI agents. |
|
scraper
Package scraper contains an implementation of the tool interface for a web scraping tool.
|
Package scraper contains an implementation of the tool interface for a web scraping tool. |
|
serpapi
Package serpapi contains an implementation of the tool interface with the serapi.
|
Package serpapi contains an implementation of the tool interface with the serapi. |
|
wikipedia
Package wikipedia contains an implementation of the tool interface with the wikipedia api.
|
Package wikipedia contains an implementation of the tool interface with the wikipedia api. |
|
zapier
Package zapier contains an implementation of the tool interface with the zapier NLA api client.
|
Package zapier contains an implementation of the tool interface with the zapier NLA api client. |
|
Package vectorstores contains the implementation of VectorStore, an interface for saving and querying documents as vector embeddings.
|
Package vectorstores contains the implementation of VectorStore, an interface for saving and querying documents as vector embeddings. |
|
azureaisearch
Package azureaisearch contains an implementation of the VectorStore interface that connects to Azure AI search.
|
Package azureaisearch contains an implementation of the VectorStore interface that connects to Azure AI search. |
|
chroma
Package chroma contains an implementation of the VectorStore interface that connects to an external Chroma database.
|
Package chroma contains an implementation of the VectorStore interface that connects to an external Chroma database. |
|
mongovector
Package mongovector implements a vector store using MongoDB as the backend.
|
Package mongovector implements a vector store using MongoDB as the backend. |
|
opensearch
Package opensearch contains an implementation of the VectorStore interface that connects to Opensearch.
|
Package opensearch contains an implementation of the VectorStore interface that connects to Opensearch. |
|
pgvector
Package pgvector contains an implementation of the VectorStore interface using pgvector.
|
Package pgvector contains an implementation of the VectorStore interface using pgvector. |
|
pinecone
Package pinecone contains an implementation of the VectorStore interface using pinecone.
|
Package pinecone contains an implementation of the VectorStore interface using pinecone. |
|
qdrant
Package qdrant contains an implementation of the VectorStore interface using Qdrant.
|
Package qdrant contains an implementation of the VectorStore interface using Qdrant. |
|
redisvector
Package redisvector contains an implementation of the VectorStore interface using redisvector.
|
Package redisvector contains an implementation of the VectorStore interface using redisvector. |
|
weaviate
Package weaviate contains an implementation of the VectorStore interface using weaviate.
|
Package weaviate contains an implementation of the VectorStore interface using weaviate. |
Click to show internal directories.
Click to hide internal directories.