Dmitry Ng
064f09155c
- Raised the `go` directive from 1.24.1 to 1.26.5 to satisfy pgx/v5 and ollama's minimum Go version requirements and to pick up 15 patched standard library CVEs. - Updated `pgx/v5`, `otel`/`otel/sdk`/`otlptracehttp`, `x/net`, and the AWS `eventstream` protocol package to their latest requested versions. - Remediated govulncheck-flagged CVEs in `grpc`, `x/text`, `x/crypto`, `antchfx/xpath`, AWS SDK `bedrock*`/`s3` services, `etcd/server`, and `mongo-driver` v1/v2. - Fixed ollama's `MainGPU` API type change (`int` -> `*int`) in `llms/ollama/options.go` without breaking the public `WithRunnerMainGPU` signature.
OpenAI Function Call Streaming Example
Welcome to this exciting example of using OpenAI's function calling feature with streaming in Go! 🎉
What does this example do?
This example demonstrates how to use the LangChain Go library to interact with OpenAI's GPT-4 model, specifically showcasing function calling capabilities and streaming responses. Here's a breakdown of the main features:
-
OpenAI Model Initialization: The code sets up a connection to the GPT-4 Turbo model.
-
Function Definitions: Three functions are defined as tools that the AI can potentially use:
getCurrentWeather: Get current weather for a locationgetTomorrowWeather: Get predicted weather for a locationgetSuggestedPrompts: Generate related prompts based on user input
-
User Query: The example asks the AI about the weather in Boston.
-
Streaming Response: As the AI generates its response, the code streams and prints each chunk of the response in real-time.
-
Function Call Detection: If the AI decides to call a function, the code will detect and display this information.
How it works
- The program initializes the OpenAI model and sets up the context.
- It sends a user query about the weather in Boston.
- As the AI generates its response, each chunk is printed to the console.
- If the AI decides to call a function (like
getCurrentWeather), this will be detected and displayed.
Why is this cool?
- Real-time Interaction: You can see the AI's thought process as it generates the response chunk by chunk.
- Function Calling: This showcases how AI can be integrated with external tools or data sources.
- Flexible Tools: The example defines multiple tools, demonstrating how you can give the AI various capabilities.
Give it a try and watch as the AI decides whether to call a function or provide a direct response about the weather in Boston! ☀️🌦️