mirror of https://github.com/vxcontrol/langchaingo.git synced 2026-08-28 04:19:56 -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

openai_function_call_example.go

feat: setup repository for fork

2025-06-22 02:27:21 +03:00

README.md

examples: Add example readmes (#916 )

2024-06-20 23:47:52 -04:00

README.md

OpenAI Function Call Example

Welcome to this cheerful example of using OpenAI's function calling capabilities with the LangChain Go library! 🎉

What does this example do?

This example demonstrates how to use OpenAI's GPT-3.5-turbo model to generate responses and make function calls based on user input. It's like having a smart assistant that can not only answer questions but also fetch real-time information for you! 🤖💬

Here's a breakdown of what happens in this exciting journey:

We set up an OpenAI language model using the LangChain Go library.
We ask the model about the weather in Boston and Chicago.
The model recognizes that it needs to fetch weather information and makes a function call to getCurrentWeather.
We simulate getting the weather data (it's always sunny in this example! ☀️).
We provide the weather information back to the model.
Finally, we ask the model to compare the weather in both cities.

Key Features

🌟 Uses OpenAI's GPT-3.5-turbo model
🛠️ Demonstrates function calling capabilities
🌤️ Simulates weather data retrieval
🔄 Shows how to manage conversation context and message history

How it Works

Initial Query: We ask about the weather in Boston and Chicago.
Function Recognition: The model recognizes it needs to call the getCurrentWeather function.
Data Retrieval: We simulate fetching weather data for both cities.
Context Update: We update the conversation context with the weather information.
Comparison: We ask the model to compare the weather, and it provides a human-like response.

Fun Fact

In this example, Boston is always 72 and sunny, while Chicago is 65 and windy. Looks like Boston is winning the weather game today! 🏆

So, grab your virtual sunglasses and enjoy exploring this example of AI-powered weather inquiries! ☀️🕶️