Alibaba Cloud Model Studio:Long context (Qwen-Long)

Python

import os
from pathlib import Path
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),  # If not configured, replace with your API key.
    # The following URL is for the China (Beijing) region. Replace {WorkspaceId} with your Workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)

file_object = client.files.create(file=Path("Model_Studio_Phone_Product_Introduction.docx"), purpose="file-extract")
print(file_object.id)

Java

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.files.*;

import java.nio.file.Path;
import java.nio.file.Paths;

public class Main {
    public static void main(String[] args) {
        // Create a client and use the API key from the environment variable.
        OpenAIClient client = OpenAIOkHttpClient.builder()
                // If you have not configured the environment variable, replace the following line with: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // The following URL is for the China (Beijing) region. Replace {WorkspaceId} with your Workspace ID. URLs vary by region.
                .baseUrl("https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1")
                .build();
        // Set the file path. Modify the path and filename as needed.
        Path filePath = Paths.get("src/main/java/org/example/Model_Studio_Phone_Product_Introduction.docx");
        // Create file upload parameters.
        FileCreateParams fileParams = FileCreateParams.builder()
                .file(filePath)
                .purpose(FilePurpose.of("file-extract"))
                .build();

        // Upload the file and print the file-id.
        FileObject fileObject = client.files().create(fileParams);
        System.out.println(fileObject.id());
    }
}

curl

# The following URL is for the China (Beijing) region. Replace {WorkspaceId} with your Workspace ID. URLs vary by region.
curl --location --request POST 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/files' \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
  --form 'file=@"Alibaba Cloud Model Studio Phone Series Product Introduction.docx"' \
  --form 'purpose="file-extract"'

Python

import os
from openai import OpenAI, BadRequestError

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),  # If not configured, replace with your API key.
    # Endpoint for the China (Beijing) region. Replace {WorkspaceId} with your Workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)
try:
    # Initialize messages list.
    completion = client.chat.completions.create(
        model="qwen-long",
        messages=[
            # sys1: Role definition.
            {'role': 'system', 'content': 'You are a helpful assistant.'},
            # sys2: Document content (plain text or file-id).
            # Replace '{FILE_ID}' with the file-id used in your conversation.
            {'role': 'system', 'content': f'fileid://{FILE_ID}'},
            # When the request includes a second system message, the user message content is limited to 9,000 tokens.
            {'role': 'user', 'content': 'What is this article about?'}
        ],
        # All examples use streaming output to show the model's response process. For non-streaming examples, see https://www.alibabacloud.com/help/en/model-studio/text-generation
        stream=True,
        stream_options={"include_usage": True}
    )

    full_content = ""
    for chunk in completion:
        if chunk.choices and chunk.choices[0].delta.content:
            # Concatenate the output content.
            full_content += chunk.choices[0].delta.content
            print(chunk.model_dump())
        
        # Get token usage.
        if chunk.usage:
            print(f"Total tokens: {chunk.usage.total_tokens}")

    print(full_content)

except BadRequestError as e:
    print(f"Error: {e}")
    print("See documentation: https://www.alibabacloud.com/help/en/model-studio/error-code")

Java

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.core.http.StreamResponse;
import com.openai.models.chat.completions.*;

public class Main {
    public static void main(String[] args) {
        // Create a client and use the API key from the environment variable.
        OpenAIClient client = OpenAIOkHttpClient.builder()
                // If you have not configured the environment variable, replace the following line with: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // Endpoint for the China (Beijing) region. Replace {WorkspaceId} with your Workspace ID. URLs vary by region.
                .baseUrl("https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1")
                .build();

        // Create a chat request.
        ChatCompletionCreateParams chatParams = ChatCompletionCreateParams.builder()
                //sys1: Role definition.
                .addSystemMessage("You are a helpful assistant.")
                //sys2: Document content (plain text or file-id).
                //Replace '{FILE_ID}' with the file-id used in your conversation.
                .addSystemMessage("fileid://{FILE_ID}")
                //When the request includes a second system message, the user message content is limited to 9,000 tokens.
                .addUserMessage("What is this article about?")
                .model("qwen-long")
                .build();

        StringBuilder fullResponse = new StringBuilder();

        // All examples use streaming output to show the model's response process. For non-streaming examples, see https://www.alibabacloud.com/help/en/model-studio/text-generation
        try (StreamResponse<ChatCompletionChunk> streamResponse = client.chat().completions().createStreaming(chatParams)) {
            streamResponse.stream().forEach(chunk -> {
                // Print and concatenate the content of each chunk.
                System.out.println(chunk);
                String content = chunk.choices().get(0).delta().content().orElse("");
                if (!content.isEmpty()) {
                    fullResponse.append(content);
                }
            });
            System.out.println(fullResponse);
        } catch (Exception e) {
            System.err.println("Error: " + e.getMessage());
            System.err.println("See documentation: https://www.alibabacloud.com/help/en/model-studio/error-code");
        }
    }
}

curl

# Endpoint for the China (Beijing) region. Replace {WorkspaceId} with your Workspace ID. URLs vary by region.
curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
    "model": "qwen-long",
    "messages": [
        {"role": "system","content": "You are a helpful assistant."},
        {"role": "system","content": "fileid://file-fe-xxx"},
        {"role": "user","content": "What is this article about?"}
    ],
    "stream": true,
    "stream_options": {
        "include_usage": true
    }
}'

Pass multiple documents

import os
from openai import OpenAI, BadRequestError

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),  # If not configured, replace with your API key.
    # Endpoint for the China (Beijing) region. Replace {WorkspaceId} with your Workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)
try:
    # Initialize messages list.
    completion = client.chat.completions.create(
        model="qwen-long",
        messages=[
            {'role': 'system', 'content': 'You are a helpful assistant.'},
            # Replace '{FILE_ID1}' and '{FILE_ID2}' with the file-ids used in your conversation.
            {'role': 'system', 'content': f"fileid://{FILE_ID1},fileid://{FILE_ID2}"},
            {'role': 'user', 'content': 'What are these articles about?'}
        ],
        # All examples use streaming output to show the model's response process. For non-streaming examples, see https://www.alibabacloud.com/help/en/model-studio/text-generation
        stream=True,
        stream_options={"include_usage": True}
    )
    
    full_content = ""
    for chunk in completion:
        if chunk.choices and chunk.choices[0].delta.content:
            # Concatenate the output content.
            full_content += chunk.choices[0].delta.content
            print(chunk.model_dump())
    
    print(full_content)

except BadRequestError as e:
    print(f"Error: {e}")
    print("See documentation: https://www.alibabacloud.com/help/en/model-studio/error-code")

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.core.http.StreamResponse;
import com.openai.models.chat.completions.*;

public class Main {
    public static void main(String[] args) {
        // Create a client and use the API key from the environment variable.
        OpenAIClient client = OpenAIOkHttpClient.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // Endpoint for the China (Beijing) region. Replace {WorkspaceId} with your Workspace ID. URLs vary by region.
                .baseUrl("https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1")
                .build();

        // Create a chat request.
        ChatCompletionCreateParams chatParams = ChatCompletionCreateParams.builder()
                .addSystemMessage("You are a helpful assistant.")
                //Replace '{FILE_ID1}' and '{FILE_ID2}' with the file-ids used in your conversation.
                .addSystemMessage("fileid://{FILE_ID1},fileid://{FILE_ID2}")
                .addUserMessage("What are these two articles about?")
                .model("qwen-long")
                .build();

        StringBuilder fullResponse = new StringBuilder();

        // All examples use streaming output to show the model's response process. For non-streaming examples, see https://www.alibabacloud.com/help/en/model-studio/text-generation
        try (StreamResponse<ChatCompletionChunk> streamResponse = client.chat().completions().createStreaming(chatParams)) {
            streamResponse.stream().forEach(chunk -> {
                // The content of each chunk.
                System.out.println(chunk);
                String content = chunk.choices().get(0).delta().content().orElse("");
                if (!content.isEmpty()) {
                    fullResponse.append(content);
                }
            });
            System.out.println("\nFull response content:");
            System.out.println(fullResponse);
        } catch (Exception e) {
            System.err.println("Error: " + e.getMessage());
            System.err.println("See documentation: https://www.alibabacloud.com/help/en/model-studio/error-code");
        }
    }
}

# Endpoint for the China (Beijing) region. Replace {WorkspaceId} with your Workspace ID. URLs vary by region.
curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
    "model": "qwen-long",
    "messages": [
        {"role": "system","content": "You are a helpful assistant."},
        {"role": "system","content": "fileid://file-fe-xxx1"},
        {"role": "system","content": "fileid://file-fe-xxx2"},
        {"role": "user","content": "What are these two articles about?"}
    ],
    "stream": true,
    "stream_options": {
        "include_usage": true
    }
}'

Append documents

import os
from openai import OpenAI, BadRequestError

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),  # If not configured, replace with your API key.
    # Endpoint for the China (Beijing) region. Replace {WorkspaceId} with your Workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)
# Initialize the messages list.
messages = [
    {'role': 'system', 'content': 'You are a helpful assistant.'},
    # Replace '{FILE_ID1}' with the file-id used in your conversation.
    {'role': 'system', 'content': f'fileid://{FILE_ID1}'},
    {'role': 'user', 'content': 'What is this article about?'}
]

try:
    # First-round response
    completion_1 = client.chat.completions.create(
        model="qwen-long",
        messages=messages,
        stream=False
    )
    # Print first-round response.
    # To stream: set stream=True, concatenate segments, and pass to assistant_message content.
    print(f"First-round response: {completion_1.choices[0].message.model_dump()}")
except BadRequestError as e:
    print(f"Error: {e}")
    print("See documentation: https://www.alibabacloud.com/help/en/model-studio/error-code")

# Construct the assistant_message.
assistant_message = {
    "role": "assistant",
    "content": completion_1.choices[0].message.content}

# Add assistant_message to messages.
messages.append(assistant_message)

# Add the file-id of the appended document to messages.
# Replace '{FILE_ID2}' with the file-id used in your conversation.
system_message = {'role': 'system', 'content': f'fileid://{FILE_ID2}'}
messages.append(system_message)

# Add the user's question.
messages.append({'role': 'user', 'content': 'What are the similarities and differences between the methods discussed in these two articles?'})

# Response after appending the document.
completion_2 = client.chat.completions.create(
    model="qwen-long",
    messages=messages,
    # All code examples use streaming output to clearly and intuitively show the model output process. For non-streaming output examples, see https://www.alibabacloud.com/help/en/model-studio/text-generation
    stream=True,
    stream_options={
        "include_usage": True
    }
)

# Stream and print the response after appending the document.
print("Response after appending the document:")
for chunk in completion_2:
    print(chunk.model_dump())

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.core.http.StreamResponse;

import java.util.ArrayList;
import java.util.List;

public class Main {
    public static void main(String[] args) {
        OpenAIClient client = OpenAIOkHttpClient.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // Endpoint for the China (Beijing) region. Replace {WorkspaceId} with your Workspace ID. URLs vary by region.
                .baseUrl("https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1")
                .build();
        // Initialize messages list.
        List<ChatCompletionMessageParam> messages = new ArrayList<>();
        
        // Add information for role setting.
        ChatCompletionSystemMessageParam roleSet = ChatCompletionSystemMessageParam.builder()
                .content("You are a helpful assistant.")
                .build();
        messages.add(ChatCompletionMessageParam.ofSystem(roleSet));
        
        // Replace '{FILE_ID1}' with the file-id used in your conversation.
        ChatCompletionSystemMessageParam systemMsg1 = ChatCompletionSystemMessageParam.builder()
                .content("fileid://{FILE_ID1}")
                .build();
        messages.add(ChatCompletionMessageParam.ofSystem(systemMsg1));

        // User question message (USER role).
        ChatCompletionUserMessageParam userMsg1 = ChatCompletionUserMessageParam.builder()
                .content("Please summarize the article content.")
                .build();
        messages.add(ChatCompletionMessageParam.ofUser(userMsg1));

        // Construct the first-round request and handle exceptions.
        ChatCompletion completion1;
        try {
            completion1 = client.chat().completions().create(
                    ChatCompletionCreateParams.builder()
                            .model("qwen-long")
                            .messages(messages)
                            .build()
            );
        } catch (Exception e) {
            System.err.println("Request error. See error code page:");
            System.err.println("https://www.alibabacloud.com/help/en/model-studio/error-code");
            System.err.println("Error details: " + e.getMessage());
            e.printStackTrace(); 
            return; 
        }

        // First-round response.
        String firstResponse = completion1 != null ? completion1.choices().get(0).message().content().orElse("") : "";
        System.out.println("First-round response: " + firstResponse);

        // Construct AssistantMessage.
        ChatCompletionAssistantMessageParam assistantMsg = ChatCompletionAssistantMessageParam.builder()
                .content(firstResponse)
                .build();
        messages.add(ChatCompletionMessageParam.ofAssistant(assistantMsg));

        // Replace '{FILE_ID2}' with the file-id used in your conversation.
        ChatCompletionSystemMessageParam systemMsg2 = ChatCompletionSystemMessageParam.builder()
                .content("fileid://{FILE_ID2}")
                .build();
        messages.add(ChatCompletionMessageParam.ofSystem(systemMsg2));

        // Second-round user question (USER role).
        ChatCompletionUserMessageParam userMsg2 = ChatCompletionUserMessageParam.builder()
                .content("Please compare the structural differences between the two articles.")
                .build();
        messages.add(ChatCompletionMessageParam.ofUser(userMsg2));

        // All examples use streaming output to show the model's response process. For non-streaming examples, see https://www.alibabacloud.com/help/en/model-studio/text-generation
        StringBuilder fullResponse = new StringBuilder();
        try (StreamResponse<ChatCompletionChunk> streamResponse = client.chat().completions().createStreaming(
                ChatCompletionCreateParams.builder()
                        .model("qwen-long")
                        .messages(messages)
                        .build())) {

            streamResponse.stream().forEach(chunk -> {
                String content = chunk.choices().get(0).delta().content().orElse("");
                if (!content.isEmpty()) {
                    fullResponse.append(content);
                }
            });
            System.out.println("\nFinal response:");
            System.out.println(fullResponse.toString().trim());
        } catch (Exception e) {
            System.err.println("Error: " + e.getMessage());
            System.err.println("See documentation: https://www.alibabacloud.com/help/en/model-studio/error-code");
        }
    }
}

# Endpoint for the China (Beijing) region. Replace {WorkspaceId} with your Workspace ID. URLs vary by region.
curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
    "model": "qwen-long",
    "messages": [
        {"role": "system","content": "You are a helpful assistant."},
        {"role": "system","content": "fileid://file-fe-xxx1"},
        {"role": "user","content": "What is this article about?"},
        {"role": "system","content": "fileid://file-fe-xxx2"},
        {"role": "user","content": "What are the similarities and differences between the methods discussed in these two articles?"}
    ],
    "stream": true,
    "stream_options": {
        "include_usage": true
    }
}'