littlelittlecloud / agentchat Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
I tried the FunctionDefinition example here: https://github.com/LittleLittleCloud/AgentChat/blob/main/src/AgentChat.OpenAI/README.md#facilitate-chat-functioncall-for-gpt-series-model
On build, I get a few errors:
7>AgentFunctions.generated.cs(11,10): Error CS1001 : Identifier expected
7>AgentFunctions.generated.cs(31,20): Error CS0103 : The name 'GetCurrentWeather' does not exist in the current context
The generated source looks like this:
//----------------------
// <auto-generated>
// This code was generated by a tool.
// </auto-generated>
//----------------------
using Azure.AI.OpenAI;
using System.Text.Json;
using System.Threading.Tasks;
using System;
namespace // ERROR: Identifier expected
{
public partial class AgentFunctions
{
private class GetCurrentWeatherSchema
{
public string city {get; set;}
public string date {get; set;}
}
public string GetCurrentWeatherWrapper(string arguments)
{
var schema = JsonSerializer.Deserialize<GetCurrentWeatherSchema>(
arguments,
new JsonSerializerOptions
{
PropertyNamingPolicy = JsonNamingPolicy.CamelCase,
});
return GetCurrentWeather(schema.city, schema.date); // ERROR: Cannot resolve symbol 'GetCurrentWeather'
}
public FunctionDefinition GetCurrentWeatherFunction
{
get => new FunctionDefinition
{
Name = @"GetCurrentWeather",
Description = """
Get the current weather in a given location.
""",
Parameters = BinaryData.FromObjectAsJson(new
{
Type = "object",
Properties = new
{
city = new
{
Type = @"string",
Description = @"The city to get the weather for",
},
date = new
{
Type = @"string",
Description = @"The date to get the weather for",
},
},
Required = new []
{
"city",
"date",
},
},
new JsonSerializerOptions
{
PropertyNamingPolicy = JsonNamingPolicy.CamelCase,
})
};
}
}
}
AgentChatVersion: 0.4.2-6852152687
.NET 6.0
Not super familiar with source generators, so might be doing something wrong.
Hi there,
AgentChat for dotnet seems quite promising for multi-agent chats, especially for role-playing scenarios. Incorporating LLamaSharp for local large language model (LLM) inference could provide added flexibility and efficiency.
Is it possible to support LLamaSharp to run local LLM inference with AgentChat?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.