项目文件夹

文件
T
Asim Aslam 081e375f29 Add AI provider integration guide and new providers support (#2900)
* docs: add AI provider integration guide and Supported AI Providers section

Add a step-by-step guide for AI infrastructure companies to implement
ai.Model and contribute a provider to go-micro. Covers the full
lifecycle: skeleton, tool call handling, tests, registration, and PR
checklist.

Add a "Supported AI Providers" section to the project README that lists
current providers (Anthropic, OpenAI) in a table and links to the
integration guide with a call-to-action for new providers and sponsors.

Streamline the "Adding a New Provider" section in ai/README.md to point
to the new guide instead of duplicating a full code listing.

* fix: remove nonexistent Discord link from README

* fix(website): set content container width to 800px on desktop

Move the 800px max-width from .markdown-body up to .content so
the entire content pane (not just the inner body) is sized
correctly. The container now fills up to 800px beside the sidebar.

* feat(ai): wire Atlas Cloud into server and auto-detection

Import atlascloud provider in the micro server so it is available
when running micro run / micro server. Add atlascloud to
AutoDetectProvider so --ai_base_url with an atlascloud domain
selects the right provider automatically.

* feat(ai): add Google Gemini provider

Add ai/gemini implementing ai.Model for Google's Gemini API. Uses
the native generateContent endpoint with system_instruction,
contents/parts, and functionDeclarations — not an OpenAI shim.
Default model gemini-2.5-flash, auth via x-goog-api-key header.

Wire into micro server imports and AutoDetectProvider (matches
googleapis.com and google in base URL).

Update README.md and ai/README.md with provider listing.

* feat(ai): add Groq, Mistral, and Together AI providers

Add three new OpenAI-compatible providers:

- ai/groq: ultra-fast inference, default model llama-3.3-70b-versatile
- ai/mistral: Mistral AI, default model mistral-large-latest
- ai/together: Together AI, default model Llama-3.3-70B-Instruct-Turbo

All three are wired into the micro server imports and
AutoDetectProvider. README and ai/README updated with the full
provider table.

* feat(ai): add ai/tools helper and 'micro chat' interactive agent

Extract the registry-discovery + RPC-execution loop from the web
agent playground into a reusable ai/tools package:

- tools.New(reg) creates a Set bound to a registry
- Set.Discover() walks the registry and returns []ai.Tool with
  LLM-safe (underscored) names, remembering the mapping back to
  the original dotted form
- Set.Handler(client) returns an ai.ToolHandler that resolves
  the safe name and issues the RPC

Add cmd/micro/chat — an interactive 'micro chat' REPL that uses
ai/tools to let users talk to their services through any
registered AI provider. Supports --prompt for single-shot use,
auto-detects the provider from --base_url, and falls back to the
provider's conventional env var (ANTHROPIC_API_KEY, etc).

Update README with the new command and the programmatic example.

* feat(examples): add gRPC interop example

Add examples/grpc-interop showing that any standard gRPC client can
call a go-micro service — no go-micro SDK required on the client
side. Includes:

- proto/greeter.proto with generated Go, gRPC, and micro stubs
- server/ using go-micro gRPC transport
- client/ using stock google.golang.org/grpc (no go-micro imports)
- README with Python example and explanation of how routing works

Addresses the confusion from issue #2818 where users didn't know
that go-micro gRPC services are callable by any gRPC client.

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-05-24 18:17:04 +01:00

142 行
4.0 KiB
Go

// Package ai provides abstraction for AI model providers
package ai
import (
"context"
"strings"
)
// Model provides an interface for interacting with AI model providers
type Model interface {
// Init initializes the model with options
Init(...Option) error
// Options returns the model options
Options() Options
// Generate generates a response from the model
Generate(ctx context.Context, req *Request, opts ...GenerateOption) (*Response, error)
// Stream generates a streaming response (for future implementation)
Stream(ctx context.Context, req *Request, opts ...GenerateOption) (Stream, error)
// String returns the name of the provider
String() string
}
// Tool represents a tool/function that can be called by the model
type Tool struct {
Name string // LLM-safe name (e.g., "greeter_Greeter_Hello")
OriginalName string // Original name (e.g., "greeter.Greeter.Hello")
Description string
Properties map[string]any // JSON schema for tool parameters
}
// Request represents a request to generate content from a model
type Request struct {
// Prompt is the user's message/prompt
Prompt string
// SystemPrompt is the system instruction for the model
SystemPrompt string
// Tools available for the model to use
Tools []Tool
// Messages for continuing a conversation (optional)
Messages []Message
}
// Message represents a conversation message
type Message struct {
Role string // "user", "assistant", "system", "tool"
Content any // Can be string or structured content
}
// Response represents the response from a model
type Response struct {
// Reply is the text response from the model
Reply string
// ToolCalls are tool calls requested by the model
ToolCalls []ToolCall
// Answer is the final answer after tool execution (if tools were used)
Answer string
}
// ToolCall represents a request to call a tool
type ToolCall struct {
ID string // Tool call ID (for correlation)
Name string // Tool name
Input map[string]any // Tool input arguments
}
// ToolResult represents the result of a tool execution
type ToolResult struct {
ID string // Tool call ID (for correlation)
Content string // Tool execution result (JSON string)
}
// Stream is the interface for streaming responses (future implementation)
type Stream interface {
// Recv receives the next chunk of the response
Recv() (*Response, error)
// Close closes the stream
Close() error
}
// ToolHandler is a function that handles tool calls
type ToolHandler func(name string, input map[string]any) (result any, content string)
// NewFunc creates a new Model instance
type NewFunc func(...Option) Model
var providers = make(map[string]NewFunc)
// Register registers a model provider
func Register(name string, fn NewFunc) {
providers[name] = fn
}
// New creates a new Model instance based on the provider name
func New(provider string, opts ...Option) Model {
if fn, ok := providers[provider]; ok {
return fn(opts...)
}
// Default to first registered provider
if len(providers) > 0 {
for _, fn := range providers {
return fn(opts...)
}
}
return nil
}
// AutoDetectProvider attempts to detect the provider from the base URL
func AutoDetectProvider(baseURL string) string {
if baseURL == "" {
return "openai"
}
switch {
case strings.Contains(baseURL, "anthropic"):
return "anthropic"
case strings.Contains(baseURL, "atlascloud"):
return "atlascloud"
case strings.Contains(baseURL, "googleapis.com"), strings.Contains(baseURL, "google"):
return "gemini"
case strings.Contains(baseURL, "groq"):
return "groq"
case strings.Contains(baseURL, "mistral"):
return "mistral"
case strings.Contains(baseURL, "together"):
return "together"
default:
return "openai"
}
}
// DefaultModel is a default model instance
var DefaultModel Model
// Generate generates a response using the default model
func Generate(ctx context.Context, req *Request, opts ...GenerateOption) (*Response, error) {
if DefaultModel == nil {
return nil, nil
}
return DefaultModel.Generate(ctx, req, opts...)
}