DataEyesAI
home
home
  1. ​​Quick Start
  • ​​Quick Start
    • Overview
    • Authorization
    • Online Debugging
    • Integration Guide
  • API Reference​​
    • Error Codes
    • HTTP Notes
  • Search / Reader Product
    • Web Reader API​​
      • Web Reader API
      • Web Reader API(HK)
    • Web Search API​​
      • Modal Card API
        • Weather
          • All City ID
          • Weather Query API
      • Web Search API
      • Video Search api
      • Trending Search API
    • Document OCR Parsing API
      • fiel upload
      • URL Parsing
  • AI Models API
    • Base Url
    • Configuration Guide for Various Plugins
    • System interface
      • Query account information
    • List models
      • Models
    • OpenAI format (supports major original models)
      • Chat (Response)
        • Create Network Search
        • Create Model Response GPT-5 Enable Thinking
        • Create Function Call
        • Create Model Response
        • Create Model Response (Streaming Return)
        • Create Model Response (Control Thinking Length)
      • ChatGPT Interface
        • Audio
          • Audio to text gpt-4o-transcribe
          • GPT-4o-audio
          • Audio to text whisper-1
          • Audio to text gpt-4o-transcribe
          • Create voice gpt-4o-mini-tts
        • Chat
          • Create chat-based image recognition (non-streaming)
          • Create chat-based image recognition (streaming)
          • Create chat-based image recognition (streaming) best64
          • Official N test
          • Create structured output
          • Control the effort level of the inference model
          • Create chat function call
          • deepseek-ocr recognition
          • Create chat completion (non-stream)
        • Completions
          • ChatGPT automatic completion
          • Create completion
      • Image
        • Edit image
        • Create chat completion (streaming)
        • Create chat completion (qwen-mt-turbo)
        • Create chat completion with deepseek v3.1 level of reasoning (streaming)
      • Audio
        • Speech recognition
        • Speech synthesis
        • Official Function Calling invocation
        • Create chat-generated images (non-streaming)
      • Embedding
        • Text embeddings
    • Anthropic format
      • Chat
      • Chat(prompt cache)
      • Streaming response
      • Chat (deep reasoning)
      • Tool invocation (function call)
      • Analyze image
    • Google Gemini interface
      • Native format
        • Text-to-image + control over aspect ratio + clarity
        • Generate image
        • Text generation
        • Text generation - stream
        • Text generation + reasoning - stream
        • Image generation
        • Formatted output
        • Function call
        • Document understanding
        • URL context [native format]
        • Code execution
        • Video understanding
        • URL context
        • Video understanding - url [native format]
        • Imagen 4
        • Audio understanding
        • Embeddings
        • Chat
        • Edit image
      • Image-to-image Base64 request method
        • Multi-image fusion slice generation with gemini-3-pro-image-preview, controlling aspect ratio and clarity
        • Image editing
        • Single image gemini-3-pro-image-preview, controlling aspect ratio and clarity.
        • Image generation( gemini-2.5-flash-image)
        • Image generation gemini-2.5-flash-image, controlling aspect ratio.
        • Image understanding
      • Image-to-image URL request returns URL request format OpenAI
        • Single image generation with gemini-3-pro-image-preview, controlling aspect ratio and clarity.
        • Multi-image fusion slice generation with gemini-3-pro-image-preview, controlling aspect ratio and clarity.
        • Image understanding
    • NanoBanana
      • OpenAI request
        • Edit image
        • OpenAI image format
      • Gemini request
        • Generate image
        • Edit image
    • Midjourney format
      • Task query interface
      • Upload image
      • Get seed (Seed)
      • Submit Imagine task
      • Query tasks based on ID list
      • FaceSwap
      • Execute Action operation
      • /mj/submit/blend
      • Submit Describe task
      • Submit Modal
      • Refresh link
      • Edit image
      • Query task status by task ID
      • Get the seed of the task image
    • Doubao - Video Generation
      • Text-to-video example
      • Image-to-video example
      • Query a single task
    • Doubao - Painting
      • doubao-seededit-3-0-i2i-250628
      • doubao-seedream-4-0-250828 - text-to-image
      • doubao-seedream-4-0-250828 - image-to-image
      • doubao-seedream-4-0-250828 - multi-image generation
    • Rerank Reordering Model
      • Rerank
    • Text-to-Music Suno
      • Task Submission
        • Generate Song (Inspiration Mode)
        • Generate Song (Custom Mode)
        • Generate Song (Continuation Mode)
        • Generate Song (Singer Style)
        • Generate Song (Secondary Creation from Uploaded Song)
        • Generate Song (Song Stitching)
        • Generate Lyrics
        • Song Stitching
      • Query Interface
        • Batch Retrieve Tasks
        • Query Single Task
    • Video Model
      • Veo-Video Generation
        • OpenAI Video Format (Recommended)
          • OpenAI Creates Video with Images
          • OpenAI Query Task
          • OpenAI Download Video
      • Sora-Video Generation
        • OpenAI Official Video Format (Recommended)
          • sora-2/sora-2-pro
            • OpenAI Query Task
            • OpenAI Download Video
            • OpenAI Creates Video with Images
            • OpenAI Creates Video (with Character)
            • OpenAI Edit Video
        • Chat Format
          • Create Video
          • Create video + image
          • Continuously modify and generate video
      • Kling -Video Generation
        • Text-to-video
        • Image-to-video
        • Query task (free)
      • Wan -Video Generation
        • Create video with image Wan
        • Query video
      • MiniMax -Video Generation
        • Text-to-video generation task
        • Image-to-video task
        • Query video generation task status
        • Video download
      • Vidu -Video Generation
        • Generates video
        • Query
  • ​​FAQ​​
    • Data Updates
  • Change Log​​
home
home
  1. ​​Quick Start

Integration Guide

Integration Guide#

Step 1: Authentication
After purchasing the product and obtaining access permissions and keys, you can view your Authorization in the console.
Step 2: Using the API
Refer to the API documentation and fill in the corresponding request parameters based on your usage scenario to call the specific API.
Step 3: Actual Development
Please safeguard your Authorization and minimize its exposure in page source code or other easily accessible paths.

Integrating in Dify#

Shuyan Intelligence has already been listed on the Dify plugin marketplace. You can find our product there and install it directly.
After setting up the plugin's Authorization information, proceed with the following configurations.

AI Search Prompt#

system

Role#

You are an AI search assistant meticulously crafted by Shuyan Intelligence, capable of precise searches in the digital world and providing answers to user queries in a neutral, objective, and journalistic tone.

Skills#

Skill 1: Accurately Respond to User Queries
1.
When a user asks a question, first provide a brief and direct answer to the core question in a standalone paragraph, followed by several independent paragraphs that analyze various aspects and details of the question, ensuring the answer is complete and logically structured.
2.
The provided answers should be moderately to extensively detailed, rich in information and tightly connected, but avoid repeating the user's question.
3.
Structure the content clearly, explicitly expressing internal classifications and logical relationships, and provide detailed content in markdown format.
Skill 2: Appropriately Use Citation Numbers to Reference Contextual Information
1.
You will receive a set of contexts related to the question, each starting with a reference number, e.g., [[citation:x]], where x is a number. Use the context to answer with references.
Skill 3: Avoid Blindly Repeating Context; Provide Extended Insights and Explanations
1.
Analyze, synthesize, and evaluate contextual information to offer deeper insights and explanations.
2.
Incorporate your professional knowledge and experience to provide richer and more profound answers.
3.
Always maintain sensitivity to user queries and a commitment to information accuracy.

Restrictions#

1.
Do not inform users to open links or visit websites for answers unless explicitly requested by the user.
2.
Answers must be based on contextual information and reference relevant content, but there is no need to mention the context in the response.
3.
Use unordered lists, ordered lists, and other formats only when necessary.
4.
Provide detailed analysis of the question, summarize key points, and highlight main information in standalone paragraphs only when necessary.
user
Here is the context:
{{context}}
Here is the user's question:
{{query}}
Previous
Online Debugging
Next
Error Codes