### Clone and Start with Docker Compose

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

Clone the project repository and use Docker Compose to start the New API service. This is the recommended method for quick setup.

```bash
git clone https://github.com/QuantumNous/new-api.git
cd new-api

# Edit docker-compose.yml configuration
nano docker-compose.yml

# Start the service
docker-compose up -d
```

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

### Clone Project and Start with Docker Compose

Source: https://github.com/quantumnous/new-api/blob/main/README.ja.md

Clone the project repository and use docker-compose to start the services. Edit the docker-compose.yml file before starting.

```bash
# プロジェクトをクローン
git clone https://github.com/QuantumNous/new-api.git
cd new-api

# docker-compose.yml 設定を編集
nano docker-compose.yml

# サービスを起動
docker-compose up -d
```

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

### Clone and Start New API with Docker Compose

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

Clone the project repository, navigate into the directory, edit the docker-compose.yml file for configuration, and then start the services in detached mode.

```bash
git clone https://github.com/QuantumNous/new-api.git
cd new-api

nano docker-compose.yml

docker-compose up -d
```

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

### Clone and Configure Docker Compose

Source: https://github.com/quantumnous/new-api/blob/main/README.md

Clone the project repository and edit the docker-compose.yml file to configure your deployment. This is the recommended method for getting started.

```bash
git clone https://github.com/QuantumNous/new-api.git
cd new-api

# Edit docker-compose.yml configuration
nano docker-compose.yml
```

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

### Run New API with Docker (MySQL)

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

Deploy the New API using a Docker command, configured for MySQL. This includes setting the SQL_DSN environment variable for the database connection and mapping port 3000.

```bash
docker run --name new-api -d --restart always \
  -p 3000:3000 \
  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
  -e TZ=Asia/Shanghai \
  -v ./data:/data \
  calciumion/new-api:latest
```

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

### 启动 Docker Compose 服务

Source: https://github.com/quantumnous/new-api/blob/main/docs/installation/BT.md

在包含配置文件的目录下执行命令以启动容器。

```bash
cd /www/wwwroot/new-api
docker-compose up -d
```

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

### Run New API with Docker Commands (SQLite)

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

Pull the latest Docker image and run the New API container using SQLite as the database. Data is persisted to a local 'data' directory.

```bash
# Pull the latest image
docker pull calciumion/new-api:latest

# Run with SQLite (default)
docker run --name new-api -d --restart always \
  -p 3000:3000 \
  -e TZ=Asia/Shanghai \
  -v ./data:/data \
  calciumion/new-api:latest
```

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

### Run New API with Docker Commands (SQLite)

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

Pull the latest Docker image and run the New API container using SQLite as the default database. Ensure data persistence by mounting a volume.

```bash
# Pull the latest image
docker pull calciumion/new-api:latest

# Using SQLite (default)
docker run --name new-api -d --restart always \
  -p 3000:3000 \
  -e TZ=Asia/Shanghai \
  -v ./data:/data \
  calciumion/new-api:latest
```

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

### Run New API with Docker (SQLite)

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

Deploy the New API using a Docker command, specifically configured for SQLite. This command maps port 3000, sets the timezone, and mounts a local data directory.

```bash
docker run --name new-api -d --restart always \
  -p 3000:3000 \
  -e TZ=Asia/Shanghai \
  -v ./data:/data \
  calciumion/new-api:latest
```

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

### Run New API with Docker Commands (MySQL)

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

Pull the latest Docker image and run the New API container, configuring it to use a MySQL database. Ensure the SQL_DSN environment variable is correctly set.

```bash
# Pull the latest image
docker pull calciumion/new-api:latest

# Run with MySQL
docker run --name new-api -d --restart always \
  -p 3000:3000 \
  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
  -e TZ=Asia/Shanghai \
  -v ./data:/data \
  calciumion/new-api:latest
```

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

### Run New API with Docker Commands (MySQL)

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

Pull the latest Docker image and run the New API container, configuring it to use a MySQL database. Specify the database connection string via the SQL_DSN environment variable.

```bash
# Pull the latest image
docker pull calciumion/new-api:latest

# Using MySQL
docker run --name new-api -d --restart always \
  -p 3000:3000 \
  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
  -e TZ=Asia/Shanghai \
  -v ./data:/data \
  calciumion/new-api:latest
```

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

### Run New API with Docker (SQLite Default)

Source: https://github.com/quantumnous/new-api/blob/main/README.ja.md

Pull the latest Docker image and run the container, mapping ports and volumes. This configuration uses SQLite as the default database.

```bash
# 最新のイメージをプル
docker pull calciumion/new-api:latest

# SQLiteを使用（デフォルト）
docker run --name new-api -d --restart always \
  -p 3000:3000 \
  -e TZ=Asia/Shanghai \
  -v ./data:/data \
  calciumion/new-api:latest
```

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

### 更新 New API 版本

Source: https://github.com/quantumnous/new-api/blob/main/docs/installation/BT.md

通过拉取最新镜像并重启容器来更新服务。

```bash
# 拉取最新镜像
docker pull calciumion/new-api:latest

# 重启容器
docker-compose down && docker-compose up -d
```

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

### 配置数据持久化卷

Source: https://github.com/quantumnous/new-api/blob/main/docs/installation/BT.md

在 docker-compose.yml 中配置卷映射以实现数据持久化。

```yaml
volumes:
  - ./data:/data
```

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

### OpenAI Compatible Chat Completions

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

This endpoint provides compatibility with OpenAI's Chat Completions API, allowing users to interact with various AI models using a familiar interface.

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

### Description
Creates a chat completion choice based on the provided messages and model.

### Method
POST

### Endpoint
/v1/chat/completions

### Parameters
#### Request Body
- **model** (string) - Required - The model to use for generating the completion.
- **messages** (array) - Required - A list of messages comprising the conversation so far.
- **temperature** (number) - Optional - Controls randomness. Lower values make the output more focused and deterministic.
- **stream** (boolean) - Optional - Whether to stream back partial message deltas as they are generated.

### Request Example
```json
{
  "model": "gpt-3.5-turbo",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who won the world series in 2020?"}
  ]
}
```

### Response
#### Success Response (200)
- **id** (string) - Unique identifier for the completion.
- **object** (string) - Type of object, e.g., `chat.completion`.
- **created** (integer) - Unix timestamp of creation.
- **model** (string) - The model used for the completion.
- **choices** (array) - A list of completion choices.
  - **index** (integer) - Index of the choice.
  - **message** (object) - The generated message.
    - **role** (string) - Role of the message sender (e.g., `assistant`).
    - **content** (string) - The content of the message.
  - **finish_reason** (string) - The reason the model stopped generating tokens.
- **usage** (object) - Usage statistics for the completion.
  - **prompt_tokens** (integer) - Number of tokens in the prompt.
  - **completion_tokens** (integer) - Number of tokens in the completion.
  - **total_tokens** (integer) - Total tokens used.

#### Response Example
```json
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The Los Angeles Dodgers won the World Series in 2020."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 15,
    "total_tokens": 25
  }
}
```
```

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

### OpenAI Compatible Chat Completions

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

This endpoint provides compatibility with OpenAI's Chat Completions API, allowing users to interact with various AI models through a familiar interface.

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

### Description
Provides chat completions compatible with the OpenAI API.

### Method
POST

### Endpoint
/v1/chat/completions

### Parameters
#### Request Body
- **model** (string) - Required - The model to use for chat completions.
- **messages** (array) - Required - An array of message objects representing the conversation.
- **temperature** (number) - Optional - Controls randomness. Lower values make output more focused and deterministic.
- **stream** (boolean) - Optional - Whether to stream back partial message deltas as they become available.

### Request Example
```json
{
  "model": "gpt-3.5-turbo",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who won the world series in 2020?"}
  ],
  "temperature": 0.7,
  "stream": false
}
```

### Response
#### Success Response (200)
- **id** (string) - Unique identifier for the response.
- **object** (string) - Type of object, e.g., `chat.completion`.
- **created** (integer) - Unix timestamp of when the response was created.
- **model** (string) - The model used for the response.
- **choices** (array) - An array of completion choices.
  - **index** (integer) - Index of the choice.
  - **message** (object) - The message content.
    - **role** (string) - Role of the message sender (e.g., `assistant`).
    - **content** (string) - The content of the message.
  - **finish_reason** (string) - The reason the model stopped generating tokens.
- **usage** (object) - Usage statistics for the request.
  - **prompt_tokens** (integer) - Number of tokens in the prompt.
  - **completion_tokens** (integer) - Number of tokens in the completion.
  - **total_tokens** (integer) - Total number of tokens.

#### Response Example
```json
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The Los Angeles Dodgers won the World Series in 2020."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 15,
    "total_tokens": 25
  }
}
```
```

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

### 配置 Docker Compose 部署文件

Source: https://github.com/quantumnous/new-api/blob/main/docs/installation/BT.md

使用 docker-compose.yml 定义 New API 服务，需确保 SESSION_SECRET 已替换为自定义随机字符串。

```yaml
version: '3'
services:
  new-api:
    image: calciumion/new-api:latest
    container_name: new-api
    restart: always
    ports:
      - "3000:3000"
    volumes:
      - ./data:/data
    environment:
      - SESSION_SECRET=your_session_secret_here  # 请修改为随机字符串
      - TZ=Asia/Shanghai
```

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

### 生成随机密钥

Source: https://github.com/quantumnous/new-api/blob/main/docs/installation/BT.md

用于生成 SESSION_SECRET 环境变量所需的随机字符串。

```bash
# 生成 SESSION_SECRET
openssl rand -hex 16

# 或使用 Linux 命令
head -c 16 /dev/urandom | xxd -p
```

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

### OpenAI Realtime API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

This endpoint provides a realtime API session compatible with OpenAI, allowing for continuous data streams.

```APIDOC
## POST /v1/realtime/openai/createrealtimesession

### Description
Creates a realtime API session compatible with OpenAI.

### Method
POST

### Endpoint
/v1/realtime/openai/createrealtimesession

### Parameters
#### Request Body
- **model** (string) - Required - The model to use for the realtime session.
- **messages** (array) - Required - An array of message objects to initiate the session.

### Request Example
```json
{
  "model": "gpt-4",
  "messages": [
    {"role": "user", "content": "Start a realtime conversation."} 
  ]
}
```

### Response
#### Success Response (200)
- **session_id** (string) - The unique identifier for the realtime session.
- **status** (string) - The status of the session (e.g., `active`).

#### Response Example
```json
{
  "session_id": "rt-session-12345",
  "status": "active"
}
```
```

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

### Image Generation API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

This endpoint allows for image generation, compatible with OpenAI's image API.

```APIDOC
## POST /v1/images/openai/post-v1-images-generations

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

### Method
POST

### Endpoint
/v1/images/openai/post-v1-images-generations

### Parameters
#### Request Body
- **prompt** (string) - Required - A description of the desired image.
- **n** (integer) - Optional - The number of images to generate.
- **size** (string) - Optional - The size of the generated images (e.g., `1024x1024`).

### Request Example
```json
{
  "prompt": "A futuristic cityscape at sunset",
  "n": 1,
  "size": "1024x1024"
}
```

### Response
#### Success Response (200)
- **created** (integer) - Unix timestamp of creation.
- **data** (array) - An array of image objects.
  - **url** (string) - The URL of the generated image.

#### Response Example
```json
{
  "created": 1678886400,
  "data": [
    {"url": "https://example.com/image.png"}
  ]
}
```
```

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

### Image Generation API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

This endpoint allows for image generation using models compatible with OpenAI's image API.

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

### Description
Generates an image based on a text prompt.

### Method
POST

### Endpoint
/v1/images/generations

### Parameters
#### Request Body
- **prompt** (string) - Required - A text description of the desired image.
- **n** (integer) - Optional - The number of images to generate.
- **size** (string) - Optional - The size of the generated images (e.g., `1024x1024`).

### Response
#### Success Response (200)
- **created** (integer) - Unix timestamp of creation.
- **data** (array) - A list of generated image objects.
  - **url** (string) - The URL of the generated image.

### Response Example
```json
{
  "created": 1677652288,
  "data": [
    {
      "url": "https://example.com/image.png"
    }
  ]
}
```
```

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

### Audio Speech API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

This endpoint converts text to speech, compatible with OpenAI's audio API.

```APIDOC
## POST /v1/audio/openai/create-speech

### Description
Converts text to speech.

### Method
POST

### Endpoint
/v1/audio/openai/create-speech

### Parameters
#### Request Body
- **model** (string) - Required - The model to use for speech synthesis (e.g., `tts-1`).
- **input** (string) - Required - The text to synthesize.
- **voice** (string) - Optional - The voice to use (e.g., `alloy`, `echo`).

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

### Response
#### Success Response (200)
- **audio_content** (binary) - The synthesized speech as audio data.

#### Response Example
(Binary audio data)
```

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

### Audio Transcription API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

This endpoint handles audio transcription, compatible with OpenAI's audio API.

```APIDOC
## POST /v1/audio/openai/create-transcription

### Description
Transcribes audio into text.

### Method
POST

### Endpoint
/v1/audio/openai/create-transcription

### Parameters
#### Request Body
- **file** (file) - Required - The audio file to transcribe.
- **model** (string) - Required - The model to use for transcription (e.g., `whisper-1`).
- **language** (string) - Optional - The language of the audio (ISO-639-1 format).

### Request Example
```json
{
  "file": "@audio.mp3",
  "model": "whisper-1",
  "language": "en"
}
```

### Response
#### Success Response (200)
- **text** (string) - The transcribed text.

#### Response Example
```json
{
  "text": "This is a test transcription."
}
```
```

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

### OpenAI Responses API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

This endpoint allows users to interact with models that provide responses in the OpenAI Responses format.

```APIDOC
## POST /v1/chat/openai/createresponse

### Description
Generates a response using the OpenAI Responses format.

### Method
POST

### Endpoint
/v1/chat/openai/createresponse

### Parameters
#### Request Body
- **model** (string) - Required - The model to use.
- **messages** (array) - Required - A list of messages.

### Response
#### Success Response (200)
- **response** (object) - The generated response in OpenAI Responses format.

### Response Example
```json
{
  "response": {
    "id": "resp-123",
    "object": "text_completion",
    "created": 1677652288,
    "model": "some-model",
    "choices": [
      {
        "text": "This is a generated response.",
        "index": 0,
        "finish_reason": "stop"
      }
    ]
  }
}
```
```

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

### Audio Speech API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

This endpoint converts text into speech.

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

### Description
Converts text to speech.

### Method
POST

### Endpoint
/v1/audio/speech

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

### Response
#### Success Response (200)
- **audio_content** (binary) - The synthesized speech audio content.

### Response Example
(Binary audio data would be returned here)
```

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

### Rerank API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

This endpoint supports reranking functionalities using models like Cohere and Jina.

```APIDOC
## POST /v1/rerank/create-rerank

### Description
Performs reranking on a list of documents.

### Method
POST

### Endpoint
/v1/rerank/create-rerank

### Parameters
#### Request Body
- **model** (string) - Required - The rerank model to use (e.g., `cohere`, `jina`).
- **query** (string) - Required - The query to rank documents against.
- **documents** (array) - Required - A list of documents to rerank.
  - **id** (string) - Required - Document identifier.
  - **content** (string) - Required - Document content.

### Response
#### Success Response (200)
- **results** (array) - The reranked results.
  - **document** (object) - The reranked document.
    - **id** (string) - Document identifier.
    - **content** (string) - Document content.
  - **relevance_score** (number) - The relevance score.
  - **index** (integer) - The original index of the document.

### Response Example
```json
{
  "results": [
    {
      "document": {
        "id": "doc-1",
        "content": "This is the first document."
      },
      "relevance_score": 0.95,
      "index": 0
    },
    {
      "document": {
        "id": "doc-2",
        "content": "This is the second document."
      },
      "relevance_score": 0.85,
      "index": 1
    }
  ]
}
```
```

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

### OpenAI Responses API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

This endpoint handles responses in the OpenAI Responses format, which may differ from standard chat completions.

```APIDOC
## POST /v1/chat/openai/createresponse

### Description
Handles chat completions specifically formatted as OpenAI Responses.

### Method
POST

### Endpoint
/v1/chat/openai/createresponse

### Parameters
#### Request Body
- **model** (string) - Required - The model to use.
- **messages** (array) - Required - An array of message objects.
- **temperature** (number) - Optional - Controls randomness.

### Request Example
```json
{
  "model": "gpt-3.5-turbo",
  "messages": [
    {"role": "user", "content": "Tell me a joke."} 
  ],
  "temperature": 0.8
}
```

### Response
#### Success Response (200)
- **response** (string) - The generated response content.
- **finish_reason** (string) - The reason for stopping generation.

#### Response Example
```json
{
  "response": "Why don't scientists trust atoms? Because they make up everything!",
  "finish_reason": "stop"
}
```
```

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

### Audio Transcription API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

This endpoint provides audio transcription capabilities.

```APIDOC
## POST /v1/audio/transcriptions

### Description
Transcribes audio into text.

### Method
POST

### Endpoint
/v1/audio/transcriptions

### Parameters
#### Request Body
- **file** (file) - Required - The audio file to transcribe.
- **model** (string) - Required - The model to use for transcription.
- **language** (string) - Optional - The language of the audio (ISO-639-1 format).

### Response
#### Success Response (200)
- **text** (string) - The transcribed text.

### Response Example
```json
{
  "text": "This is the transcribed audio content."
}
```
```

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

### Google Gemini Chat API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

This endpoint allows interaction with Google Gemini models for chat functionalities.

```APIDOC
## POST /v1/chat/gemini/geminirelayv1beta

### Description
Relays chat requests to Google Gemini models.

### Method
POST

### Endpoint
/v1/chat/gemini/geminirelayv1beta

### Parameters
#### Request Body
- **model** (string) - Required - The Gemini model to use.
- **contents** (array) - Required - A list of content parts for the conversation.

### Response
#### Success Response (200)
- **candidates** (array) - A list of response candidates from the model.
  - **content** (object) - The content of the candidate response.
    - **parts** (array) - Parts of the content.
      - **text** (string) - The text content.
  - **finish_reason** (string) - The reason for finishing.

### Response Example
```json
{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "This is a response from Google Gemini."
          }
        ]
      },
      "finish_reason": "STOP"
    }
  ]
}
```
```

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

### Embeddings API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

This endpoint generates embeddings for text, compatible with OpenAI's embeddings API.

```APIDOC
## POST /v1/embeddings/createembedding

### Description
Creates embeddings for a given input text.

### Method
POST

### Endpoint
/v1/embeddings/createembedding

### Parameters
#### Request Body
- **model** (string) - Required - The model to use for generating embeddings.
- **input** (string or array) - Required - The input text or array of texts to get embeddings for.

### Request Example
```json
{
  "model": "text-embedding-ada-002",
  "input": "The quick brown fox jumps over the lazy dog."
}
```

### Response
#### Success Response (200)
- **data** (array) - An array of embedding objects.
  - **embedding** (array) - The embedding vector.
  - **index** (integer) - The index of the input text.
- **model** (string) - The model used.
- **usage** (object) - Usage statistics.
  - **prompt_tokens** (integer) - Number of tokens in the prompt.
  - **total_tokens** (integer) - Total number of tokens.

#### Response Example
```json
{
  "data": [
    {
      "embedding": [
        0.0023064255007047176,
        -0.009327214477539062,
        // ... more dimensions
      ],
      "index": 0
    }
  ],
  "model": "text-embedding-ada-002",
  "usage": {
    "prompt_tokens": 10,
    "total_tokens": 10
  }
}
```
```

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

### 配置渠道额外参数示例

Source: https://github.com/quantumnous/new-api/blob/main/docs/channel/other_setting.md

展示如何通过 JSON 对象启用强制格式化、思考内容转换并设置代理地址。

```json
{
    "force_format": true,
   "thinking_to_content": true,
    "proxy": "socks5://xxxxxxx"
}
```

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

### Rerank API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

This endpoint supports reranking of documents using models like Cohere and Jina.

```APIDOC
## POST /v1/rerank/create-rerank

### Description
Performs reranking of provided documents.

### Method
POST

### Endpoint
/v1/rerank/create-rerank

### Parameters
#### Request Body
- **model** (string) - Required - The rerank model to use (e.g., `cohere`, `jina`).
- **query** (string) - Required - The query to rank documents against.
- **documents** (array) - Required - An array of document objects.
  - **id** (string) - Required - Unique identifier for the document.
  - **content** (string) - Required - The content of the document.

### Request Example
```json
{
  "model": "cohere",
  "query": "best programming languages",
  "documents": [
    {"id": "doc1", "content": "Python is a popular language."}, 
    {"id": "doc2", "content": "Java is widely used in enterprise applications."}
  ]
}
```

### Response
#### Success Response (200)
- **results** (array) - An array of reranked results.
  - **document_id** (string) - The ID of the document.
  - **relevance_score** (number) - The relevance score of the document.

#### Response Example
```json
{
  "results": [
    {"document_id": "doc1", "relevance_score": 0.95},
    {"document_id": "doc2", "relevance_score": 0.80}
  ]
}
```
```

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

### Google Gemini Chat API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

This endpoint provides chat functionality for Google Gemini models.

```APIDOC
## POST /v1/chat/gemini/geminirelayv1beta

### Description
Relays chat requests to Google Gemini models.

### Method
POST

### Endpoint
/v1/chat/gemini/geminirelayv1beta

### Parameters
#### Request Body
- **model** (string) - Required - The Gemini model to use.
- **contents** (array) - Required - An array of content objects representing the conversation.

### Request Example
```json
{
  "model": "gemini-1.5-flash",
  "contents": [
    {"role": "user", "parts": [{"text": "What is the capital of France?"}]}
  ]
}
```

### Response
#### Success Response (200)
- **candidates** (array) - An array of candidate responses.
  - **content** (object) - The content of the candidate response.
    - **parts** (array) - An array of parts in the content.
      - **text** (string) - The text of the part.

#### Response Example
```json
{
  "candidates": [
    {
      "content": {
        "parts": [
          {"text": "The capital of France is Paris."}
        ]
      }
    }
  ]
}
```
```

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

### Claude Messages API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

This endpoint allows interaction with models using the Claude Messages API format.

```APIDOC
## POST /v1/chat/messages

### Description
Creates a message completion using the Claude Messages API format.

### Method
POST

### Endpoint
/v1/chat/messages

### Parameters
#### Request Body
- **model** (string) - Required - The model to use.
- **messages** (array) - Required - A list of messages.

### Response
#### Success Response (200)
- **id** (string) - Unique identifier for the message.
- **type** (string) - Type of message, e.g., `message_delta`.
- **role** (string) - Role of the sender.
- **content** (array) - Content of the message.
- **stop_reason** (string) - The reason the model stopped generating.

### Response Example
```json
{
  "id": "msg-123",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "This is a response from Claude."
    }
  ],
  "stop_reason": "end_turn"
}
```
```

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

### Claude Messages API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_CN.md

This endpoint allows interaction with models using the Claude Messages API format.

```APIDOC
## POST /v1/chat/claude/createmessage

### Description
Sends messages to Claude models.

### Method
POST

### Endpoint
/v1/chat/claude/createmessage

### Parameters
#### Request Body
- **model** (string) - Required - The Claude model to use.
- **messages** (array) - Required - An array of message objects.
- **max_tokens** (integer) - Optional - The maximum number of tokens to generate.

### Request Example
```json
{
  "model": "claude-3-sonnet-20240229",
  "messages": [
    {"role": "user", "content": "Explain the concept of recursion."} 
  ],
  "max_tokens": 100
}
```

### Response
#### Success Response (200)
- **content** (string) - The response content from the Claude model.
- **stop_reason** (string) - The reason the model stopped generating.

#### Response Example
```json
{
  "content": "Recursion is a method where the solution to a problem depends on smaller instances of the same problem.",
  "stop_reason": "end_turn"
}
```
```

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

### Embeddings API

Source: https://github.com/quantumnous/new-api/blob/main/README.zh_TW.md

This endpoint generates embeddings for text.

```APIDOC
## POST /v1/embeddings

### Description
Creates an embedding vector for a given text.

### Method
POST

### Endpoint
/v1/embeddings

### Parameters
#### Request Body
- **model** (string) - Required - The model to use for generating embeddings.
- **input** (string or array) - Required - The text or list of texts to generate embeddings for.

### Response
#### Success Response (200)
- **data** (array) - A list of embedding objects.
  - **embedding** (array) - The embedding vector.
  - **index** (integer) - The index of the input text.
- **model** (string) - The model used.
- **usage** (object) - Usage statistics.
  - **prompt_tokens** (integer) - Number of tokens in the prompt.
  - **total_tokens** (integer) - Total tokens used.

### Response Example
```json
{
  "data": [
    {
      "embedding": [
        0.0023,
        -0.0074,
        0.0031,
        // ... more dimensions
      ],
      "index": 0
    }
  ],
  "model": "text-embedding-ada-002",
  "usage": {
    "prompt_tokens": 5,
    "total_tokens": 5
  }
}
```
```

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