mirror of https://github.com/vxcontrol/langchaingo.git synced 2026-08-27 20:10:20 -04:00

Files

T

Dmitry Ng 1fc129969f feat(llms): add provider-neutral structured output via WithStructuredOutput

Add a single WithStructuredOutput(StructuredOutputConfig) call option
carrying a raw JSON Schema (Draft 2020-12), so one contract yields the
same guarantee — a normal-final response is a single JSON value matching
the schema — on OpenAI, Anthropic, Bedrock (Converse and legacy), Google
AI, Vertex, and Ollama. Each provider maps it to its native mechanism;
the result is validated locally against the original schema in the new
llms/structuredoutput package. Also fixes a latent Converse gap where the
response stop reason was never surfaced on ContentChoice.StopReason.

2026-07-17 04:39:05 +03:00

go.mod

feat(llms): add provider-neutral structured output via WithStructuredOutput

2026-07-17 04:39:05 +03:00

go.sum

feat(llms): add provider-neutral structured output via WithStructuredOutput

2026-07-17 04:39:05 +03:00

perplexity_completion_example.go

feat: integrate streaming functionality across LLMs and callbacks

2025-06-23 18:52:06 +03:00

README.md

Add perplexity completion example (#977 )

2024-09-12 17:14:28 -07:00

README.md

Perplexity Completion Example with LangChain Go

Hello there! 👋 This example demonstrates how to use the Perplexity API with LangChain Go to generate creative text completions. Let's break down what this exciting little program does!

What This Example Does

Environment Setup:
- The program starts by loading environment variables from a .env file. This is where you'll store your Perplexity API key.
Perplexity LLM Configuration:
- It sets up a Large Language Model (LLM) client using Perplexity's API, which is compatible with the OpenAI interface.
- The model used is "llama-3.1-sonar-large-128k-online", a powerful language model hosted by Perplexity.
Text Generation:
- The example prompts the model to "What is a prime number?"
Streaming Output:
- As the model generates text, it streams the output directly to the console, allowing you to see the response being created in real-time!

Cool Features

Real-time Streaming: Watch as the AI crafts the response word by word!
Customizable: You can easily modify the prompt or adjust generation parameters.
Perplexity Integration: Showcases how to use Perplexity's powerful models with LangChain Go.

Running the Example

Make sure you have a Perplexity API key and set it in your .env file as PERPLEXITY_API_KEY=your_api_key_here.
Run the program and watch as it generates a creative response about prime numbers right before your eyes!

You can read more about the perplexity API here: Perplexity API Documentation.

Enjoy exploring the creative possibilities with Perplexity and LangChain Go! 🚀🐹