### Call Video Generation API

Source: https://context7.com/kangyiwen/dmxapi/llms.txt

Provides an example of generating video content from a text prompt using the video generations endpoint.

```bash
curl https://api.dmxapi.com/v1/videos/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_DMXAPI_KEY" \
  -d '{
    "model": "video-gen-1",
    "prompt": "日落时分，海浪轻轻拍打沙滩，金色阳光洒在海面上",
    "duration": 5,
    "resolution": "1080p"
  }'
```

--------------------------------

### Implement RAG with LangChain

Source: https://context7.com/kangyiwen/dmxapi/llms.txt

Shows how to build a Retrieval-Augmented Generation (RAG) pipeline using LangChain, FAISS, and DMXAPI as the LLM and embedding provider.

```python
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains import RetrievalQA
from langchain.text_splitter import RecursiveCharacterTextSplitter

llm = ChatOpenAI(
    model="gpt-4",
    openai_api_key="YOUR_DMXAPI_KEY",
    openai_api_base="https://api.dmxapi.com/v1",
    temperature=0
)

embeddings = OpenAIEmbeddings(
    openai_api_key="YOUR_DMXAPI_KEY",
    openai_api_base="https://api.dmxapi.com/v1"
)

documents = ["您的文档内容..."]
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
texts = text_splitter.create_documents(documents)
vectorstore = FAISS.from_documents(texts, embeddings)

qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=vectorstore.as_retriever(search_kwargs={"k": 3})
)
```

--------------------------------

### Integrate DMXAPI with Python SDK

Source: https://context7.com/kangyiwen/dmxapi/llms.txt

Demonstrates using the official OpenAI Python SDK to interact with DMXAPI by configuring the base_url.

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_DMXAPI_KEY",
    base_url="https://api.dmxapi.com/v1"
)

def chat_with_model(user_message, model="gpt-4"):
    try:
        response = client.chat.completions.create(
            model=model,
            messages=[
                {"role": "system", "content": "你是一个专业的AI助手。"},
                {"role": "user", "content": user_message}
            ],
            temperature=0.7,
            max_tokens=2000
        )
        return response.choices[0].message.content
    except Exception as e:
        print(f"API调用错误: {e}")
        return None
```

--------------------------------

### Call Image Generation API

Source: https://context7.com/kangyiwen/dmxapi/llms.txt

Shows how to generate images using models like DALL-E 3 by sending a prompt to the images generations endpoint.

```bash
curl https://api.dmxapi.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_DMXAPI_KEY" \
  -d '{
    "model": "dall-e-3",
    "prompt": "一只可爱的卡通熊猫在竹林中吃竹子，水彩画风格",
    "n": 1,
    "size": "1024x1024",
    "quality": "standard"
  }'
```

--------------------------------

### POST /v1/videos/generations

Source: https://context7.com/kangyiwen/dmxapi/llms.txt

Generate video content from text descriptions.

```APIDOC
## POST /v1/videos/generations

### Description
Generate a video based on a text prompt.

### Method
POST

### Endpoint
https://api.dmxapi.com/v1/videos/generations

### Parameters
#### Request Body
- **model** (string) - Required - The video generation model.
- **prompt** (string) - Required - Description of the video.
- **duration** (integer) - Optional - Length in seconds.

### Request Example
{
  "model": "video-gen-1",
  "prompt": "Sunset at the beach",
  "duration": 5
}

### Response
#### Success Response (200)
- **id** (string) - Job ID for the video generation task.
- **status** (string) - Current status of the request.
```

--------------------------------

### POST /v1/audio/speech

Source: https://context7.com/kangyiwen/dmxapi/llms.txt

Convert text into natural-sounding speech using TTS models.

```APIDOC
## POST /v1/audio/speech

### Description
Synthesize speech from text input.

### Method
POST

### Endpoint
https://api.dmxapi.com/v1/audio/speech

### Parameters
#### Request Body
- **model** (string) - Required - The TTS model to use.
- **input** (string) - Required - The text to convert to speech.
- **voice** (string) - Required - The voice profile to use.

### Request Example
{
  "model": "tts-1",
  "input": "Hello world",
  "voice": "alloy"
}

### Response
#### Success Response (200)
- Returns a binary MP3 audio stream.
```

--------------------------------

### Call LLM Text Generation API

Source: https://context7.com/kangyiwen/dmxapi/llms.txt

Demonstrates how to perform text generation using the OpenAI-compatible chat completions endpoint via curl. It requires an API key and supports various models like gpt-4.

```bash
curl https://api.dmxapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_DMXAPI_KEY" \
  -d '{
    "model": "gpt-4",
    "messages": [
      {"role": "system", "content": "你是一个有帮助的助手。"},
      {"role": "user", "content": "请用简短的话介绍人工智能的发展历史。"}
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'
```

--------------------------------

### POST /v1/chat/completions

Source: https://context7.com/kangyiwen/dmxapi/llms.txt

Generate text responses using various LLMs like GPT-4 or Claude via a unified chat interface.

```APIDOC
## POST /v1/chat/completions

### Description
Generate text completions or engage in multi-turn conversations with supported LLMs.

### Method
POST

### Endpoint
https://api.dmxapi.com/v1/chat/completions

### Parameters
#### Request Body
- **model** (string) - Required - The ID of the model to use (e.g., "gpt-4").
- **messages** (array) - Required - A list of messages comprising the conversation.
- **temperature** (float) - Optional - Sampling temperature (0-2).
- **max_tokens** (integer) - Optional - Maximum tokens to generate.

### Request Example
{
  "model": "gpt-4",
  "messages": [{"role": "user", "content": "Explain AI history."}]
}

### Response
#### Success Response (200)
- **id** (string) - Unique identifier for the completion.
- **choices** (array) - List of generated message choices.

#### Response Example
{
  "id": "chatcmpl-xxx",
  "choices": [{"message": {"role": "assistant", "content": "..."}}]
}
```

--------------------------------

### POST /v1/images/generations

Source: https://context7.com/kangyiwen/dmxapi/llms.txt

Generate high-quality images from text prompts using models like DALL-E or Stable Diffusion.

```APIDOC
## POST /v1/images/generations

### Description
Create images based on a text prompt.

### Method
POST

### Endpoint
https://api.dmxapi.com/v1/images/generations

### Parameters
#### Request Body
- **model** (string) - Required - The model to use (e.g., "dall-e-3").
- **prompt** (string) - Required - Text description of the image.
- **size** (string) - Optional - Image dimensions (e.g., "1024x1024").

### Request Example
{
  "model": "dall-e-3",
  "prompt": "A cute cartoon panda",
  "size": "1024x1024"
}

### Response
#### Success Response (200)
- **data** (array) - List of generated image URLs.

#### Response Example
{
  "data": [{"url": "https://api.dmxapi.com/files/img-xxx.png"}]
}
```

--------------------------------

### Call TTS Speech Synthesis API

Source: https://context7.com/kangyiwen/dmxapi/llms.txt

Demonstrates converting text to speech using the audio speech endpoint, saving the output directly to an MP3 file.

```bash
curl https://api.dmxapi.com/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_DMXAPI_KEY" \
  -d '{
    "model": "tts-1",
    "input": "欢迎使用 DMXAPI，全球领先的大模型 API 聚合服务。",
    "voice": "alloy",
    "response_format": "mp3",
    "speed": 1.0
  }' \
  --output speech.mp3
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.