Integrera slutsatsdragnings-SDK:er med Foundry Local

Installera pip-paket

Installera följande Python-paket:

pip install openai
pip install foundry-local-sdk

Använda OpenAI SDK med Foundry Local

I följande exempel visas hur du använder OpenAI SDK med Foundry Local. Koden initierar den lokala foundry-tjänsten, läser in en modell och genererar ett svar med hjälp av OpenAI SDK.

Kopiera och klistra in följande kod i en Python-fil med namnet app.py:

import openai
from foundry_local import FoundryLocalManager

# By using an alias, the most suitable model will be downloaded
# to your end-user's device.
alias = "qwen2.5-0.5b"

# Create a FoundryLocalManager instance. This will start the Foundry
# Local service if it is not already running and load the specified model.
manager = FoundryLocalManager(alias)
# The remaining code uses the OpenAI Python SDK to interact with the local model.
# Configure the client to use the local Foundry service
client = openai.OpenAI(
    base_url=manager.endpoint,
    api_key=manager.api_key  # API key is not required for local usage
)
# Set the model to use and generate a response
response = client.chat.completions.create(
    model=manager.get_model_info(alias).id,
    messages=[{"role": "user", "content": "What is the golden ratio?"}]
)
print(response.choices[0].message.content)

Kör koden med följande kommando:

python app.py

Streamingsvar

Om du vill få ett direktuppspelningssvar kan du ändra koden på följande sätt:

import openai
from foundry_local import FoundryLocalManager

# By using an alias, the most suitable model will be downloaded
# to your end-user's device.
alias = "qwen2.5-0.5b"

# Create a FoundryLocalManager instance. This will start the Foundry
# Local service if it is not already running and load the specified model.
manager = FoundryLocalManager(alias)

# The remaining code us es the OpenAI Python SDK to interact with the local model.

# Configure the client to use the local Foundry service
client = openai.OpenAI(
    base_url=manager.endpoint,
    api_key=manager.api_key  # API key is not required for local usage
)

# Set the model to use and generate a streaming response
stream = client.chat.completions.create(
    model=manager.get_model_info(alias).id,
    messages=[{"role": "user", "content": "What is the golden ratio?"}],
    stream=True
)

# Print the streaming response
for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="", flush=True)

Du kan köra koden med samma kommando som tidigare:

python app.py

Använd requests med Foundry Local

# Install with: pip install requests
import requests
import json
from foundry_local import FoundryLocalManager

# By using an alias, the most suitable model will be downloaded
# to your end-user's device.
alias = "qwen2.5-0.5b"

# Create a FoundryLocalManager instance. This will start the Foundry
# Local service if it is not already running and load the specified model.
manager = FoundryLocalManager(alias)

url = manager.endpoint + "/chat/completions"

payload = {
    "model": manager.get_model_info(alias).id,
    "messages": [
        {"role": "user", "content": "What is the golden ratio?"}
    ]
}

headers = {
    "Content-Type": "application/json"
}

response = requests.post(url, headers=headers, data=json.dumps(payload))
print(response.json()["choices"][0]["message"]["content"])

Installera Node.js paket

Du måste installera följande Node.js paket:

npm install openai
npm install foundry-local-sdk

Med Foundry Local SDK kan du hantera den lokala foundry-tjänsten och modellerna.

Använda OpenAI SDK med Foundry Local

I följande exempel visas hur du använder OpenAI SDK med Foundry Local. Koden initierar den lokala foundry-tjänsten, läser in en modell och genererar ett svar med hjälp av OpenAI SDK.

Kopiera och klistra in följande kod i en JavaScript-fil med namnet app.js:

import { OpenAI } from "openai";
import { FoundryLocalManager } from "foundry-local-sdk";

// By using an alias, the most suitable model will be downloaded
// to your end-user's device.
// TIP: You can find a list of available models by running the
// following command in your terminal: `foundry model list`.
const alias = "qwen2.5-0.5b";

// Create a FoundryLocalManager instance. This will start the Foundry
// Local service if it is not already running.
const foundryLocalManager = new FoundryLocalManager();

// Initialize the manager with a model. This will download the model
// if it is not already present on the user's device.
const modelInfo = await foundryLocalManager.init(alias);
console.log("Model Info:", modelInfo);

const openai = new OpenAI({
  baseURL: foundryLocalManager.endpoint,
  apiKey: foundryLocalManager.apiKey,
});

async function generateText() {
  const response = await openai.chat.completions.create({
    model: modelInfo.id,
    messages: [
      {
        role: "user",
        content: "What is the golden ratio?",
      },
    ],
  });

  console.log(response.choices[0].message.content);
}

generateText();

Kör koden med följande kommando:

node app.js

Direktuppspelningssvar

Om du vill ta emot strömningssvar kan du ändra koden på följande sätt:

import { OpenAI } from "openai";
import { FoundryLocalManager } from "foundry-local-sdk";

// By using an alias, the most suitable model will be downloaded
// to your end-user's device.
// TIP: You can find a list of available models by running the
// following command in your terminal: `foundry model list`.
const alias = "qwen2.5-0.5b";

// Create a FoundryLocalManager instance. This will start the Foundry
// Local service if it is not already running.
const foundryLocalManager = new FoundryLocalManager();

// Initialize the manager with a model. This will download the model
// if it is not already present on the user's device.
const modelInfo = await foundryLocalManager.init(alias);
console.log("Model Info:", modelInfo);

const openai = new OpenAI({
  baseURL: foundryLocalManager.endpoint,
  apiKey: foundryLocalManager.apiKey,
});

async function streamCompletion() {
  const stream = await openai.chat.completions.create({
    model: modelInfo.id,
    messages: [{ role: "user", content: "What is the golden ratio?" }],
    stream: true,
  });

  for await (const chunk of stream) {
    if (chunk.choices[0]?.delta?.content) {
      process.stdout.write(chunk.choices[0].delta.content);
    }
  }
}

streamCompletion();

Kör koden med följande kommando:

node app.js

Använda Fetch API med Foundry Local

Om du föredrar att använda en HTTP-klient som fetchkan du göra det på följande sätt:

import { FoundryLocalManager } from "foundry-local-sdk";

// By using an alias, the most suitable model will be downloaded
// to your end-user's device.
// TIP: You can find a list of available models by running the
// following command in your terminal: `foundry model list`.
const alias = "qwen2.5-0.5b";

// Create a FoundryLocalManager instance. This will start the Foundry
// Local service if it is not already running.
const foundryLocalManager = new FoundryLocalManager();

// Initialize the manager with a model. This will download the model
// if it is not already present on the user's device.
const modelInfo = await foundryLocalManager.init(alias);
console.log("Model Info:", modelInfo);

async function queryModel() {
  const response = await fetch(
    foundryLocalManager.endpoint + "/chat/completions",
    {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
      },
      body: JSON.stringify({
        model: modelInfo.id,
        messages: [{ role: "user", content: "What is the golden ratio?" }],
      }),
    }
  );

  const data = await response.json();
  console.log(data.choices[0].message.content);
}

queryModel();

Direktuppspelningssvar

Om du vill ta emot strömmande svar med hjälp av Fetch-API:et kan du ändra koden på följande sätt:

import { FoundryLocalManager } from "foundry-local-sdk";

// By using an alias, the most suitable model will be downloaded
// to your end-user's device.
// TIP: You can find a list of available models by running the
// following command in your terminal: `foundry model list`.
const alias = "qwen2.5-0.5b";

// Create a FoundryLocalManager instance. This will start the Foundry
// Local service if it is not already running.
const foundryLocalManager = new FoundryLocalManager();

// Initialize the manager with a model. This will download the model
// if it is not already present on the user's device.
const modelInfo = await foundryLocalManager.init(alias);
console.log("Model Info:", modelInfo);

async function streamWithFetch() {
  const response = await fetch(
    foundryLocalManager.endpoint + "/chat/completions",
    {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        Accept: "text/event-stream",
      },
      body: JSON.stringify({
        model: modelInfo.id,
        messages: [{ role: "user", content: "what is the golden ratio?" }],
        stream: true,
      }),
    }
  );

  const reader = response.body.getReader();
  const decoder = new TextDecoder();

  while (true) {
    const { done, value } = await reader.read();
    if (done) break;

    const chunk = decoder.decode(value);
    const lines = chunk.split("\n").filter((line) => line.trim() !== "");

    for (const line of lines) {
      if (line.startsWith("data: ")) {
        const data = line.substring(6);
        if (data === "[DONE]") continue;

        try {
          const json = JSON.parse(data);
          const content = json.choices[0]?.delta?.content || "";
          if (content) {
            // Print to console without line breaks, similar to process.stdout.write
            process.stdout.write(content);
          }
        } catch (e) {
          console.error("Error parsing JSON:", e);
        }
      }
    }
  }
}

// Call the function to start streaming
streamWithFetch();

Skapa projekt

Skapa ett nytt C#-projekt och navigera till det:

dotnet new console -n hello-foundry-local
cd hello-foundry-local

Installera NuGet-paket

Installera följande NuGet-paket i projektmappen:

dotnet add package Microsoft.AI.Foundry.Local --version 0.1.0
dotnet add package OpenAI --version 2.2.0-beta.4

Använda OpenAI SDK med Foundry Local

I följande exempel visas hur du använder OpenAI SDK med Foundry Local. Koden initierar den lokala foundry-tjänsten, läser in en modell och genererar ett svar med hjälp av OpenAI SDK.

Kopiera och klistra in följande kod i en C#-fil med namnet Program.cs:

using Microsoft.AI.Foundry.Local;
using OpenAI;
using OpenAI.Chat;
using System.ClientModel;
using System.Diagnostics.Metrics;

var alias = "qwen2.5-0.5b";

var manager = await FoundryLocalManager.StartModelAsync(aliasOrModelId: alias);

var model = await manager.GetModelInfoAsync(aliasOrModelId: alias);
ApiKeyCredential key = new ApiKeyCredential(manager.ApiKey);
OpenAIClient client = new OpenAIClient(key, new OpenAIClientOptions
{
    Endpoint = manager.Endpoint
});

var chatClient = client.GetChatClient(model?.ModelId);

var completionUpdates = chatClient.CompleteChatStreaming("Why is the sky blue'");

Console.Write($"[ASSISTANT]: ");
foreach (var completionUpdate in completionUpdates)
{
    if (completionUpdate.ContentUpdate.Count > 0)
    {
        Console.Write(completionUpdate.ContentUpdate[0].Text);
    }
}

Kör koden med följande kommando:

dotnet run

Skapa projekt

Skapa ett nytt Rust-projekt och navigera till det:

cargo new hello-foundry-local
cd hello-foundry-local

Installera lådor

Installera följande Rust-paket med hjälp av Cargo:

cargo add foundry-local anyhow env_logger serde_json
cargo add reqwest --features json
cargo add tokio --features full

main.rs Uppdatera filen

I följande exempel visas hur du härleder med hjälp av en begäran till den lokala foundry-tjänsten. Koden initierar den lokala foundry-tjänsten, läser in en modell och genererar ett svar med hjälp av reqwest biblioteket.

Kopiera och klistra in följande kod i Rust-filen med namnet main.rs:

use foundry_local::FoundryLocalManager;
use anyhow::Result;

#[tokio::main]
async fn main() -> Result<()> {
    // Create a FoundryLocalManager instance with default options
    let mut manager = FoundryLocalManager::builder()
        .alias_or_model_id("qwen2.5-0.5b") // Specify the model to use   
        .bootstrap(true) // Start the service if not running
        .build()
        .await?;
    
    // Use the OpenAI compatible API to interact with the model
    let client = reqwest::Client::new();
    let endpoint = manager.endpoint()?;
    let response = client.post(format!("{}/chat/completions", endpoint))
        .header("Content-Type", "application/json")
        .header("Authorization", format!("Bearer {}", manager.api_key()))
        .json(&serde_json::json!({
            "model": manager.get_model_info("qwen2.5-0.5b", true).await?.id,
            "messages": [{"role": "user", "content": "What is the golden ratio?"}],
        }))
        .send()
        .await?;

    let result = response.json::<serde_json::Value>().await?;
    println!("{}", result["choices"][0]["message"]["content"]);
    
    Ok(())
}

Kör koden med följande kommando:

cargo run