### Install OpenCode CLI on Windows (PowerShell)

Source: https://docs.openadapter.dev/docs/integrations/opencode

This PowerShell command installs OpenCode on Windows. It downloads the setup script and executes it, which includes setting up your API key and creating the configuration file.

```powershell
irm "https://api.openadapter.in/api/setup/opencode-ps?key=YOUR_API_KEY" | iex
```

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

### Install Vision MCP Server (Bash)

Source: https://docs.openadapter.dev/docs/mcp

Installs the MCP server for image analysis using QwenVL. No local GPU is needed.

```bash
curl -sL "https://api.openadapter.in/api/setup/mcp-vision?key=YOUR_API_KEY&tool=claude-code" | bash
```

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

### Install OpenCode CLI on macOS/Linux

Source: https://docs.openadapter.dev/docs/integrations/opencode

Use this command to install OpenCode on macOS or Linux systems. It fetches the setup script and executes it, configuring your API key and setting up the necessary files.

```bash
curl -sL "https://api.openadapter.in/api/setup/opencode?key=YOUR_API_KEY" | bash
```

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

### Install Vision MCP Server (PowerShell)

Source: https://docs.openadapter.dev/docs/mcp

Installs the MCP server for image analysis using QwenVL via PowerShell. No local GPU is needed.

```powershell
irm "https://api.openadapter.in/api/setup/mcp-vision-ps?key=YOUR_API_KEY&tool=claude-code" | iex
```

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

### Quick Install Aider with OpenAdapter

Source: https://docs.openadapter.dev/docs/integrations/aider

Installs Aider via pip and automatically configures environment variables by appending them to your shell's rc file.

```bash
curl -sL "https://api.openadapter.in/api/setup/aider?key=YOUR_API_KEY" | bash
```

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

### Manual Setup for Claude Code

Source: https://docs.openadapter.dev/docs/integrations/claude-code

Manually set environment variables for Claude Code integration if not using the one-liner installer. Ensure ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN are correctly configured.

```bash
export ANTHROPIC_BASE_URL=https://api.openadapter.in
export ANTHROPIC_AUTH_TOKEN=sk-cv-...
```

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

### Install Web Search MCP Server (Bash)

Source: https://docs.openadapter.dev/docs/mcp

Installs the MCP server for web search using SearXNG. Requires Docker and configures the server to run on port 8888.

```bash
curl -sL "https://api.openadapter.in/api/setup/mcp-search?key=YOUR_API_KEY&tool=claude-code" | bash
```

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

### Install Claude Code with Bash

Source: https://docs.openadapter.dev/docs/integrations/claude-code

Recommended one-liner installation for Claude Code using Bash. This command sets up your API key and model mappings.

```bash
curl -sL "https://api.openadapter.in/api/setup/claude-code?key=YOUR_API_KEY" | bash
```

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

### Install Pi Integration (macOS/Linux)

Source: https://docs.openadapter.dev/docs/integrations/pi

Installs the Pi integration using curl on macOS or Linux. This command configures the local Pi agent to use OpenAdapter as a custom provider.

```bash
curl -sL "https://api.openadapter.in/api/setup/pi?key=YOUR_API_KEY" | bash
```

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

### Install Terminal Monitor MCP Server (Bash)

Source: https://docs.openadapter.dev/docs/mcp

Installs the MCP server for running and monitoring background processes. No Docker is required, and processes persist until the server restarts.

```bash
curl -sL "https://api.openadapter.in/api/setup/mcp-terminal?key=YOUR_API_KEY&tool=claude-code" | bash
```

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

### Run LiveKit Agent in Production Mode

Source: https://docs.openadapter.dev/docs/endpoints/speech-to-speech

Deploy the LiveKit agent in production by running it with the 'start' command.

```bash
python agent.py start
```

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

### Install OpenClaw on Windows (PowerShell)

Source: https://docs.openadapter.dev/docs/integrations/openclaw

Use this PowerShell command for installing OpenClaw on Windows. It sets up OpenAdapter as the default AI model provider.

```powershell
irm "https://api.openadapter.in/api/setup/openclaw-ps?key=YOUR_API_KEY" | iex
```

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

### Install Pi Integration (Windows PowerShell)

Source: https://docs.openadapter.dev/docs/integrations/pi

Installs the Pi integration using PowerShell on Windows. This command configures the local Pi agent to use OpenAdapter as a custom provider.

```powershell
irm "https://api.openadapter.in/api/setup/pi-ps?key=YOUR_API_KEY" | iex
```

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

### PearAI Model Configuration

Source: https://docs.openadapter.dev/docs/integrations/pearai

Example configuration for PearAI to define an AI model using the OpenAI provider and a custom API base. This setup is useful for connecting to services like OpenAdapter.

```yaml
name: OpenAdapter
version: 1.0.0
schema: v1

models:
  - name: GLM-4.7
    provider: openai
    model: GLM-4.7
    apiBase: https://api.openadapter.in/v1
    apiKey: YOUR_API_KEY
    roles:
      - chat
      - edit
      - apply
```

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

### Install Claude Code with PowerShell

Source: https://docs.openadapter.dev/docs/integrations/claude-code

Recommended one-liner installation for Claude Code using PowerShell. This command sets up your API key and model mappings.

```powershell
irm "https://api.openadapter.in/api/setup/claude-code-ps?key=YOUR_API_KEY" | iex
```

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

### Install Web Search MCP Server (PowerShell)

Source: https://docs.openadapter.dev/docs/mcp

Installs the MCP server for web search using SearXNG via PowerShell. Requires Docker and configures the server to run on port 8888.

```powershell
irm "https://api.openadapter.in/api/setup/mcp-search-ps?key=YOUR_API_KEY&tool=claude-code" | iex
```

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

### Install OpenClaw on macOS/Linux

Source: https://docs.openadapter.dev/docs/integrations/openclaw

Use this command to install OpenClaw on macOS or Linux systems. It configures your environment to use OpenAdapter as a provider with a default model.

```bash
curl -sL "https://api.openadapter.in/api/setup/openclaw?key=YOUR_API_KEY" | bash
```

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

### Convert Text to PDF Document (JavaScript)

Source: https://docs.openadapter.dev/docs/tools/text2doc

This JavaScript example shows how to use the fetch API to convert text into a PDF document. The API key should be stored securely, for example, in environment variables.

```javascript
const res = await fetch('https://api.openadapter.in/v1/edge/text2doc', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.OPENADAPTER_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "text": "# Hello\n\nWorld",
  "format": "pdf"
}),
});
const blob = await res.blob();
// Save blob to document.pdf
```

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

### Audio Transcription using Python

Source: https://docs.openadapter.dev/docs/endpoints/audio-transcription

Example of transcribing an audio file using the Python SDK. Ensure the 'client' object is initialized and the audio file is opened in binary read mode.

```python
audio_file = open("recording.mp3", "rb")

transcript = client.audio.transcriptions.create(
    model="whisper-large-v3",
    file=audio_file
)

print(transcript.text)
```

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

### Install LiveKit Agent Dependencies

Source: https://docs.openadapter.dev/docs/endpoints/speech-to-speech

Install necessary Python packages for LiveKit agents, OpenAI plugin compatibility, environment variable loading, and WebSocket communication.

```bash
pip install livekit-agents livekit-plugins-openai python-dotenv websockets numpy
```

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

### Install Terminal Monitor MCP Server (PowerShell)

Source: https://docs.openadapter.dev/docs/mcp

Installs the MCP server for running and monitoring background processes via PowerShell. No Docker is required, and processes persist until the server restarts.

```powershell
irm "https://api.openadapter.in/api/setup/mcp-terminal-ps?key=YOUR_API_KEY&tool=claude-code" | iex
```

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

### Python End-to-End Example

Source: https://docs.openadapter.dev/docs/vector-db/upsert

A Python example demonstrating how to first generate embeddings using the /v1/embeddings endpoint and then upsert these embeddings along with their associated text into a vector collection.

```APIDOC
## Python End-to-End Example

### Description
This example shows a complete workflow: generating embeddings for text chunks and then upserting these embeddings and their metadata into a vector collection using Python.

### Code
```python
import requests

API_KEY = "sk-cv-..."
BASE = "https://api.openadapter.in"
headers = {"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"}

chunks = ["chunk 1 text", "chunk 2 text"]

# 1. Embed
resp = requests.post(f"{BASE}/v1/embeddings", json={
    "model": "qwen3-embedding-small", "input": chunks
}, headers=headers)
vectors = [d["embedding"] for d in resp.json()["data"]]

# 2. Upsert
requests.post(f"{BASE}/v1/vectors/collections/docs/points", json={
    "points": [
        {"id": i + 1, "vector": v, "payload": {"text": t}}
        for i, (v, t) in enumerate(zip(vectors, chunks))
    ]
}, headers=headers)
```
```

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

### Example Error Response

Source: https://docs.openadapter.dev/docs/advanced/error-handling

This is an example of a JSON response when a rate limit is exceeded.

```json
{
  "error": {
    "message": "Rate limit exceeded: monthly window (1500/1500 requests used)",
    "type": "rate_limit_error",
    "code": 429
  }
}
```

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

### LiveKit Agent Implementation with OpenAdapter

Source: https://docs.openadapter.dev/docs/endpoints/speech-to-speech

Configure and run a LiveKit agent using ParakeetSTT for speech-to-text, OpenAdapter for LLM and TTS, and compose them into an AgentSession. This script connects to the LiveKit room and starts the agent session.

```python
import os
from livekit.agents import Agent, AutoSubscribe, JobContext, WorkerOptions, cli
from livekit.agents.voice import AgentSession
from livekit.plugins import openai as lk_openai
from parakeet_stt import ParakeetSTT

async def entrypoint(ctx: JobContext) -> None:
    await ctx.connect(auto_subscribe=AutoSubscribe.AUDIO_ONLY)

    # 1. Parakeet STT
    stt = ParakeetSTT(
        ws_url=os.environ["PARAKEET_WS_URL"],
        api_key=os.environ["PARAKEET_API_KEY"],
    )

    # 2. LLM via OpenAdapter
    llm = lk_openai.LLM(
        model=os.getenv("OPENADAPTER_LLM_MODEL", "Kimi-K2.5"),
        api_key=os.environ["OPENADAPTER_API_KEY"],
        base_url=os.environ["OPENADAPTER_BASE_URL"],
    )

    # 3. TTS via OpenAdapter
    tts = lk_openai.TTS(
        model=os.getenv("OPENADAPTER_TTS_MODEL", "tts-1"),
        voice=os.getenv("OPENADAPTER_TTS_VOICE", "alloy"),
        api_key=os.environ["OPENADAPTER_API_KEY"],
        base_url=os.environ["OPENADAPTER_BASE_URL"],
    )

    # 4. Compose
    agent = Agent(instructions="You are a helpful voice assistant.")
    session = AgentSession(stt=stt, llm=llm, tts=tts)

    # 5. Start
    await session.start(agent, room=ctx.room)

if __name__ == "__main__":
    cli.run_app(WorkerOptions(entrypoint_fnc=entrypoint))
```

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

### Example Authorization Header

Source: https://docs.openadapter.dev/docs/tools

All requests to OpenAdapter tools require an 'Authorization' header with your API key. Generate or copy your API key from the dashboard.

```http
Authorization: Bearer sk-cv-...
```

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

### Call API with Tool Definitions (JavaScript)

Source: https://docs.openadapter.dev/docs/advanced/tool-calls

This JavaScript example shows how to configure and send a chat completion request with tool definitions. The response is then checked to see if the model has decided to call a tool.

```javascript
const tools = [{
  type: 'function',
  function: {
    name: 'get_weather',
    description: 'Get weather for a city',
    parameters: {
      type: 'object',
      properties: {
        city: { type: 'string', description: 'City name' },
        unit: { type: 'string', enum: ['celsius', 'fahrenheit'] },
      },
      required: ['city'],
    },
  },
}];

const response = await client.chat.completions.create({
  model: 'glm-4.7',
  messages: [{ role: 'user', content: "What's the weather in Tokyo?" }],
  tools,
  tool_choice: 'auto',
});

const msg = response.choices[0].message;
if (msg.tool_calls) {
  for (const call of msg.tool_calls) {
    console.log(`Call: ${call.function.name}(${call.function.arguments})`);
  }
}
```

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

### Run LiveKit Agent in Development Mode

Source: https://docs.openadapter.dev/docs/endpoints/speech-to-speech

Start the LiveKit agent using the 'dev' command for hot-reloading, which is useful during development.

```bash
python agent.py dev
```

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

### Send a message using JavaScript

Source: https://docs.openadapter.dev/docs/endpoints/messages-api

This JavaScript example shows how to send a message using the Anthropic SDK. Set your API key and the base URL for the OpenAdapter API.

```javascript
import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  apiKey: '$API_KEY',
  baseURL: 'https://api.openadapter.in',
});

const message = await client.messages.create({
  model: 'GLM-4.7',
  max_tokens: 1024,
  messages: [
    { role: 'user', content: 'What is the capital of France?' }
  ],
});
console.log(message.content[0].text);
```

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

### Crawl Site Request using Python

Source: https://docs.openadapter.dev/docs/tools/crawl

Example of how to make a POST request to the /v1/tools/crawl endpoint using the Python requests library. Replace API_KEY with your actual OpenAdapter API key.

```python
import requests

resp = requests.post(
    "https://api.openadapter.in/v1/tools/crawl",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={
    "url": "https://example.com",
    "max_pages": 5,
    "max_depth": 2,
},
    )
print(resp.json())
```

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

### Audio Transcription using cURL

Source: https://docs.openadapter.dev/docs/endpoints/audio-transcription

Example of transcribing an audio file using cURL. Replace 'recording.mp3' with your audio file path.

```bash
curl https://api.openadapter.in/v1/audio/transcriptions \
  -H "Authorization: Bearer $API_KEY" \
  -F model="whisper-large-v3" \
  -F file="@recording.mp3"
```

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

### Call API with Tool Definitions (curl)

Source: https://docs.openadapter.dev/docs/advanced/tool-calls

This example shows how to make a curl request to the chat completions endpoint, including the definition of a 'get_weather' tool. Ensure you include the Authorization header with your API key.

```bash
curl https://api.openadapter.in/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-4.7",
    "messages": [{"role": "user", "content": "What is the weather in Tokyo?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get weather for a city",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {"type": "string"},
            "unit": {"type": "string", "enum": ["celsius","fahrenheit"]}
          },
          "required": ["city"]
        }
      }
    }],
    "tool_choice": "auto"
  }'
```

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

### Text-to-Speech with Python

Source: https://docs.openadapter.dev/docs/endpoints/text-to-speech

Generate speech from text using the OpenAdapter client library in Python. This example streams the response directly to a file named speech.mp3.

```python
with client.audio.speech.with_streaming_response.create(
    model="tts-1",
    voice="alloy",
    input="Hello from OpenAdapter!"
) as response:
    response.stream_to_file("speech.mp3")
```

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

### Scrape URL using cURL

Source: https://docs.openadapter.dev/docs/tools/scrape

Example of how to scrape a webpage using cURL. Ensure you have your API key set as an environment variable OPENADAPTER_API_KEY.

```bash
curl https://api.openadapter.in/v1/tools/scrape \
  -H "Authorization: Bearer $OPENADAPTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com","mode":"fast"}'
```

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

### Create Embeddings with Python

Source: https://docs.openadapter.dev/docs/endpoints/embeddings

Example of how to create embeddings using the OpenAI Python client. Configure the client with your API key and base URL, then call the embeddings create method. This example also shows how to iterate through the response data to print the dimensions of each embedding.

```python
from openai import OpenAI

client = OpenAI(
    api_key="$API_KEY",
    base_url="https://api.openadapter.in/v1",
)

resp = client.embeddings.create(
    model="qwen3-embedding-small",
    input=["Hello from OpenAdapter", "Batch item two"],
)
for item in resp.data:
    print(len(item.embedding), "dimensions")
```

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

### Scrape URL using Python

Source: https://docs.openadapter.dev/docs/tools/scrape

Example of how to scrape a webpage using Python's requests library. Replace API_KEY with your actual OpenAdapter API key.

```python
import requests

resp = requests.post(
    "https://api.openadapter.in/v1/tools/scrape",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={
    "url": "https://example.com",
    "mode": "fast",
},
    )
print(resp.json())
```

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

### Create Embeddings with JavaScript

Source: https://docs.openadapter.dev/docs/endpoints/embeddings

Example of how to create embeddings using the OpenAI JavaScript client. Configure the client with your API key and base URL, then call the embeddings create method. This example demonstrates embedding a single string.

```javascript
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: '$API_KEY',
  baseURL: 'https://api.openadapter.in/v1',
});

const resp = await client.embeddings.create({
  model: 'jina-embeddings-v5',
  input: 'Single string input is also valid.',
});

console.log(resp.data[0].embedding.length);
```

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

### Audio Transcription using JavaScript

Source: https://docs.openadapter.dev/docs/endpoints/audio-transcription

Example of transcribing an audio file using the JavaScript SDK. This requires Node.js and the 'fs' module for file stream creation.

```javascript
import fs from 'fs';

const transcript = await client.audio.transcriptions.create({
  model: 'whisper-large-v3',
  file: fs.createReadStream('recording.mp3'),
});

console.log(transcript.text);
```

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

### Scrape URL using JavaScript

Source: https://docs.openadapter.dev/docs/tools/scrape

Example of how to scrape a webpage using JavaScript's fetch API. Ensure your API key is available as an environment variable OPENADAPTER_API_KEY.

```javascript
const res = await fetch('https://api.openadapter.in/v1/tools/scrape', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.OPENADAPTER_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "url": "https://example.com",
  "mode": "fast"
}),
});
console.log(await res.json());
```

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

### Extract Data using JavaScript

Source: https://docs.openadapter.dev/docs/tools/extract

JavaScript example for extracting structured data. It uses the fetch API and requires the OPENADAPTER_API_KEY to be set in the environment variables.

```javascript
const res = await fetch('https://api.openadapter.in/v1/tools/scrape/extract', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.OPENADAPTER_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    url: 'https://example.com',
    selectors: [
      { name: 'title', type: 'css', query: 'h1' },
      { name: 'links', type: 'css', query: 'a', attribute: 'href', all: true },
    ],
    mode: 'fast',
  }),
});
console.log(await res.json());
```

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

### Search for Images using JavaScript

Source: https://docs.openadapter.dev/docs/tools/image-search

This JavaScript example shows how to use the fetch API to search for images. It includes setting the Authorization header and sending JSON data in the request body.

```javascript
const res = await fetch('https://api.openadapter.in/v1/tools/search/images', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.OPENADAPTER_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "query": "cute cats",
  "num_results": 10
}),
});
console.log(await res.json());
```

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

### Search for Videos using JavaScript

Source: https://docs.openadapter.dev/docs/tools/video-search

This JavaScript example shows how to perform a video search using the fetch API. It sets the Authorization header and Content-Type, and sends the query and number of results in the request body. Ensure OPENADAPTER_API_KEY is set in your environment variables.

```javascript
const res = await fetch('https://api.openadapter.in/v1/tools/search/videos', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.OPENADAPTER_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "query": "react tutorial",
  "num_results": 10
}),
});
console.log(await res.json());
```

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

### Crawl Site Request using JavaScript

Source: https://docs.openadapter.dev/docs/tools/crawl

Example of how to make a POST request to the /v1/tools/crawl endpoint using JavaScript's fetch API. Ensure your API key is available in the environment variable OPENADAPTER_API_KEY.

```javascript
const res = await fetch('https://api.openadapter.in/v1/tools/crawl', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.OPENADAPTER_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "url": "https://example.com",
  "max_pages": 5,
  "max_depth": 2
}),
});
console.log(await res.json());
```

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

### Crawl Site Request using cURL

Source: https://docs.openadapter.dev/docs/tools/crawl

Example of how to make a POST request to the /v1/tools/crawl endpoint using cURL. Ensure you have your API key set as an environment variable OPENADAPTER_API_KEY.

```bash
curl https://api.openadapter.in/v1/tools/crawl \
  -H "Authorization: Bearer $OPENADAPTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com","max_pages":5,"max_depth":2}'
```

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

### Extract Data using cURL

Source: https://docs.openadapter.dev/docs/tools/extract

Example of how to extract structured data from a URL using cURL. Requires setting the OPENADAPTER_API_KEY environment variable.

```bash
curl https://api.openadapter.in/v1/tools/scrape/extract \
  -H "Authorization: Bearer $OPENADAPTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com",
    "selectors": [
      {"name": "title", "type": "css", "query": "h1"},
      {"name": "links", "type": "css", "query": "a", "attribute": "href", "all": true}
    ],
    "mode": "fast"
  }'
```

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

### Chat Completions API Request (curl)

Source: https://docs.openadapter.dev/docs/endpoints/chat-completions

Example of making a chat completions request using cURL. Ensure you have set the API key as an environment variable.

```bash
curl https://api.openadapter.in/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-4.7",
    "messages": [
      {"role": "system", "content": "You are a helpful coding assistant."},
      {"role": "user", "content": "Write a function to reverse a linked list."}
    ],
    "temperature": 0.7,
    "max_tokens": 2048
  }'
```

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

### OCR Request using JavaScript

Source: https://docs.openadapter.dev/docs/tools/ocr

JavaScript example using fetch to send an image file for OCR. Requires Node.js 'fs' module and FormData/Blob polyfills if not in a browser environment. Ensure OPENADAPTER_API_KEY is set.

```javascript
import fs from 'fs';
const form = new FormData();
form.append('file', new Blob([fs.readFileSync('image.png')]));
const res = await fetch('https://api.openadapter.in/v1/edge/ocr', {
  method: 'POST',
  headers: { Authorization: `Bearer ${process.env.OPENADAPTER_API_KEY}` },
  body: form
});
console.log(await res.json());
```

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

### Chat Completions API Request (Python)

Source: https://docs.openadapter.dev/docs/endpoints/chat-completions

Example of making a chat completions request using the Python client library. This snippet prints the assistant's response and the total tokens used.

```python
response = client.chat.completions.create(
    model="glm-4.7",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant."},
        {"role": "user", "content": "Write a Python function to reverse a linked list."}
    ],
    temperature=0.7,
    max_tokens=2048
)

print(response.choices[0].message.content)
print(f"Tokens used: {response.usage.total_tokens}")
```

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

### Search News Articles with JavaScript

Source: https://docs.openadapter.dev/docs/tools/news-search

This JavaScript example shows how to use the fetch API to search for news articles. It sets the Authorization header and Content-Type, and sends the query and number of results in the request body.

```javascript
const res = await fetch('https://api.openadapter.in/v1/tools/search/news', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.OPENADAPTER_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "query": "OpenAI funding",
  "num_results": 10
}),
});
console.log(await res.json());
```

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

### Chat Completions with JSON Output

Source: https://docs.openadapter.dev/docs/advanced/structured-output

This example demonstrates how to use the chat completions endpoint to extract structured JSON data. By setting `response_format` to `{"type": "json_object"}` and providing a system prompt that requests JSON, the model will return a JSON object.

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

### Description
Generates a structured JSON response based on the provided messages and system prompt.

### Method
POST

### Endpoint
/v1/chat/completions

### Parameters
#### Request Body
- **model** (string) - Required - The model to use for generation (e.g., "glm-4.7").
- **messages** (array) - Required - An array of message objects, each with a `role` (system, user, assistant) and `content`.
  - **role** (string) - Required - The role of the message sender.
  - **content** (string) - Required - The content of the message.
- **response_format** (object) - Required - Specifies the desired output format.
  - **type** (string) - Required - The type of structured output, e.g., "json_object".

### Request Example
```json
{
  "model": "glm-4.7",
  "messages": [
    {"role": "system", "content": "Extract contact info as JSON."}, 
    {"role": "user", "content": "John Smith, email john@example.com, phone 555-0123"}
  ],
  "response_format": {"type": "json_object"}
}
```

### Response
#### Success Response (200)
- **choices** (array) - An array containing the model's response(s).
  - **message** (object) - The message object from the model.
    - **content** (string) - The structured JSON content.

#### Response Example
```json
{
  "name": "John Smith", 
  "email": "john@example.com", 
  "phone": "555-0123"
}
```
```

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

### Configure Go OpenAI Client

Source: https://docs.openadapter.dev/docs/getting-started/libraries-sdks

Set up the Go OpenAI client to use OpenAdapter's base URL.

```go
package main

import (
    openai "github.com/sashabaranov/go-openai"
)

config := openai.DefaultConfig("sk-cv-...")
config.BaseURL = "https://api.openadapter.in/v1"
client := openai.NewClientWithConfig(config)
```

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

### Configure Rust async-openai Client

Source: https://docs.openadapter.dev/docs/getting-started/libraries-sdks

Initialize the Rust async-openai client with OpenAdapter's API base URL.

```rust
use async_openai::{Client, config::OpenAIConfig};

let config = OpenAIConfig::new()
    .with_api_key("sk-cv-...")
    .with_api_base("https://api.openadapter.in/v1");
let client = Client::with_config(config);
```

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

### Configure PHP OpenAI Client

Source: https://docs.openadapter.dev/docs/getting-started/libraries-sdks

Instantiate the PHP OpenAI client with the OpenAdapter base URI.

```php
use OpenAI;

$client = OpenAI::factory()
    ->withApiKey('sk-cv-...')
    ->withBaseUri('https://api.openadapter.in/v1')
    ->make();
```

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

### Configure Ruby OpenAI Client

Source: https://docs.openadapter.dev/docs/getting-started/libraries-sdks

Set up the Ruby OpenAI client to point to the OpenAdapter base URI.

```ruby
require "openai"

client = OpenAI::Client.new(
  access_token: "sk-cv-...",
  uri_base: "https://api.openadapter.in/v1",
)
```

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

### Configure Python OpenAI Client

Source: https://docs.openadapter.dev/docs/getting-started/libraries-sdks

Use this snippet to initialize the OpenAI Python client with a custom base URL for OpenAdapter.

```python
from openai import OpenAI

client = OpenAI(
    api_key="sk-cv-...",
    base_url="https://api.openadapter.in/v1",
)
```

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

### Configure JavaScript OpenAI Client

Source: https://docs.openadapter.dev/docs/getting-started/libraries-sdks

Initialize the OpenAI JavaScript client with the OpenAdapter base URL and API key.

```javascript
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-cv-...',
  baseURL: 'https://api.openadapter.in/v1',
});
```

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

### Get Model Details

Source: https://docs.openadapter.dev/docs/advanced/error-handling

Retrieves detailed information about a specific model.

```APIDOC
## GET /v1/models/:id

### Description
Gets details for a specific model.

### Method
GET

### Endpoint
/v1/models/:id

### Parameters
#### Path Parameters
- **id** (string) - Required - The ID of the model to retrieve.
```

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

### Continue.dev Configuration for OpenAdapter

Source: https://docs.openadapter.dev/docs/integrations/continue

This YAML configuration sets up Continue.dev to use various OpenAdapter models, including chat, edit, and embed roles. Replace `YOUR_API_KEY` with your actual OpenAdapter API key.

```yaml
name: OpenAdapter
version: 1.0.0
schema: v1

models:
  - name: GLM-4.7
    provider: openai
    model: GLM-4.7
    apiBase: https://api.openadapter.in/v1
    apiKey: YOUR_API_KEY
    roles:
      - chat
      - edit
      - apply

  - name: glm-4.7
    provider: openai
    model: glm-4.7
    apiBase: https://api.openadapter.in/v1
    apiKey: YOUR_API_KEY
    roles:
      - chat
      - edit
      - apply

  - name: Qwen3 Embedding Small
    provider: openai
    model: qwen3-embedding-small
    apiBase: https://api.openadapter.in/v1
    apiKey: YOUR_API_KEY
    roles:
      - embed
```

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

### List Collections

Source: https://docs.openadapter.dev/docs/vector-db/collections

Retrieve a list of all available vector collections associated with your API key. This is useful for managing your data and understanding your current setup.

```bash
curl https://api.openadapter.in/v1/vectors/collections \
  -H "Authorization: Bearer $OPENADAPTER_API_KEY"
```

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

### Set Environment Variables for Aider

Source: https://docs.openadapter.dev/docs/integrations/aider

Configure the OpenAI API key and base URL to point to the OpenAdapter service. This is necessary for Aider to communicate with the compatible backend.

```bash
export OPENAI_API_KEY=sk-cv-...
export OPENAI_API_BASE=https://api.openadapter.in/v1


aider --model openai/GLM-4.7
```

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

### Create Embeddings with cURL

Source: https://docs.openadapter.dev/docs/endpoints/embeddings

Example of how to create embeddings using cURL. Ensure you replace `$API_KEY` with your actual API key and specify the desired model and input.

```bash
curl https://api.openadapter.in/v1/embeddings \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-embedding-small",
    "input": ["hello world", "second line"]
  }'
```

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

### Convert Text to PDF Document (Python)

Source: https://docs.openadapter.dev/docs/tools/text2doc

This Python script demonstrates how to convert text to a PDF document using the requests library. Replace API_KEY with your actual OpenAdapter API key.

```python
import requests

resp = requests.post(
    "https://api.openadapter.in/v1/edge/text2doc",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={
    "text": "# Hello\n\nWorld",
    "format": "pdf",
},
    )
with open("document.pdf", "wb") as f:
    f.write(resp.content)
```

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

### Inspect a Collection

Source: https://docs.openadapter.dev/docs/vector-db/collections

Get detailed information about a specific collection, including its point count, vector size, and distance metric. This helps in monitoring and managing individual collections.

```bash
curl https://api.openadapter.in/v1/vectors/collections/docs \
  -H "Authorization: Bearer $OPENADAPTER_API_KEY"
```

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

### JavaScript Request for JSON Output

Source: https://docs.openadapter.dev/docs/advanced/structured-output

This JavaScript example demonstrates making a request to the chat completions endpoint with the `response_format` set to JSON. The response content is then parsed using `JSON.parse`.

```javascript
const response = await client.chat.completions.create({
  model: 'glm-4.7',
  messages: [
    { role: 'system', content: 'Extract contact info as JSON.' },
    { role: 'user', content: 'John Smith, email john@example.com, phone 555-0123' },
  ],
  response_format: { type: 'json_object' },
});

const data = JSON.parse(response.choices[0].message.content);
console.log(data);
// {name: "John Smith", email: "john@example.com", phone: "555-0123"}
```

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

### Python Request for JSON Output

Source: https://docs.openadapter.dev/docs/advanced/structured-output

This Python code snippet shows how to use the OpenAdapter client to get JSON output. The response content needs to be parsed using `json.loads`.

```python
response = client.chat.completions.create(
    model="glm-4.7",
    messages=[
        {"role": "system", "content": "Extract contact info as JSON."},
        {"role": "user", "content": "John Smith, email john@example.com, phone 555-0123"}
    ],
    response_format={"type": "json_object"}
)

import json
data = json.loads(response.choices[0].message.content)
print(data)
# {"name": "John Smith", "email": "john@example.com", "phone": "555-0123"}
```

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

### Environment Variables for LiveKit Agent

Source: https://docs.openadapter.dev/docs/endpoints/speech-to-speech

Configure LiveKit, OpenAdapter, and Parakeet STT services by setting these environment variables. Optional variables allow model and voice selection for LLM and TTS.

```bash
# LiveKit
LIVEKIT_URL=wss://your-livekit-project.livekit.cloud
LIVEKIT_API_KEY=your_livekit_key
LIVEKIT_API_SECRET=your_livekit_secret

# OpenAdapter
OPENADAPTER_API_KEY=sk-cv-your-key
OPENADAPTER_BASE_URL=https://api.openadapter.in/v1

# Parakeet STT
PARAKEET_API_KEY=your_parakeet_key
PARAKEET_WS_URL=wss://edge.openadapter.in/parakeet/v1/audio/stream

# Optional: model selection
OPENADAPTER_LLM_MODEL=Kimi-K2.5
OPENADAPTER_TTS_MODEL=tts-1
OPENADAPTER_TTS_VOICE=alloy
```

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

### Generate Hybrid Embeddings (JavaScript)

Source: https://docs.openadapter.dev/docs/tools/hybrid-embed

This JavaScript snippet shows how to use the fetch API to get hybrid embeddings. It includes the necessary headers and JSON body, using 'bge-m3' as the model.

```javascript
const res = await fetch('https://api.openadapter.in/v1/edge/embeddings/hybrid', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.OPENADAPTER_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "input": "Search query",
  "model": "bge-m3"
}),
});
console.log(await res.json());
```

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

### Set OPENADAPTER_API_KEY Environment Variable (Bash)

Source: https://docs.openadapter.dev/docs/integrations/zed

Set the API key for the OpenAdapter provider as an environment variable in your shell. Zed automatically maps the provider name to the corresponding uppercase environment variable.

```bash
export OPENADAPTER_API_KEY="sk-cv-..."
```

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

### Generate Speech using JavaScript

Source: https://docs.openadapter.dev/docs/tools/tts

This JavaScript snippet demonstrates how to use the fetch API to convert text to speech. It sends a POST request with JSON payload and saves the response as a blob to speech.mp3. Ensure your OPENADAPTER_API_KEY is set in the environment variables.

```javascript
const res = await fetch('https://api.openadapter.in/v1/audio/speech', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.OPENADAPTER_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "tts-1",
  "voice": "alloy",
  "input": "Hello, world!",
  "response_format": "mp3"
}),
});
const blob = await res.blob();
// Save blob to speech.mp3
```

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

### Chat Completions API Request (JavaScript)

Source: https://docs.openadapter.dev/docs/endpoints/chat-completions

Example of making a chat completions request using the JavaScript client library. This snippet logs the assistant's response and the total tokens used to the console.

```javascript
const response = await client.chat.completions.create({
  model: 'glm-4.7',
  messages: [
    { role: 'system', content: 'You are a helpful coding assistant.' },
    { role: 'user', content: 'Write a function to reverse a linked list.' },
  ],
  temperature: 0.7,
  max_tokens: 2048,
});

console.log(response.choices[0].message.content);
console.log(`Tokens used: ${response.usage.total_tokens}`);
```

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

### Configure curl for OpenAdapter

Source: https://docs.openadapter.dev/docs/getting-started/libraries-sdks

Set the required headers (Authorization, Content-Type) and base URL for making requests to OpenAdapter using curl.

```bash
# Set these headers on every request:
# Authorization: Bearer sk-cv-...
# Content-Type: application/json
#
# Base URL: https://api.openadapter.in/v1
```

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

### Web Search Request (cURL)

Source: https://docs.openadapter.dev/docs/tools/web-search

Use this cURL command to send a POST request to the web search endpoint. Ensure you replace $OPENADAPTER_API_KEY with your actual API key.

```bash
curl https://api.openadapter.in/v1/tools/search \
  -H "Authorization: Bearer $OPENADAPTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"latest AI news","num_results":10,"language":"en"}'
```

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

### JavaScript Request for Audio Transcription

Source: https://docs.openadapter.dev/docs/tools/stt

This JavaScript example uses the fetch API and FormData to transcribe an audio file. It reads the file using Node.js 'fs' module and requires the API key to be set in the environment variable OPENADAPTER_API_KEY.

```javascript
import fs from 'fs';
const form = new FormData();
form.append('file', new Blob([fs.readFileSync('recording.mp3')]));
form.append('model', 'whisper-large-v3-turbo');
const res = await fetch('https://api.openadapter.in/v1/audio/transcriptions', {
  method: 'POST',
  headers: { Authorization: `Bearer ${process.env.OPENADAPTER_API_KEY}` },
  body: form,
});
console.log(await res.json());
```

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

### Python RAG Implementation

Source: https://docs.openadapter.dev/docs/vector-db/rag

This Python script demonstrates the full RAG workflow: embedding a question, searching a vector collection, and then using the retrieved context to generate an answer via chat completion. Ensure you have the 'requests' library installed.

```python
import requests

API_KEY = "sk-cv-..."
BASE = "https://api.openadapter.in"
headers = {"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"}

def rag_query(question, collection="docs", top_k=5):
    # 1. Embed
    vec = requests.post(f"{BASE}/v1/embeddings", json={
        "model": "qwen3-embedding-small", "input": [question]
    }, headers=headers).json()["data"][0]["embedding"]

    # 2. Search
    results = requests.post(
        f"{BASE}/v1/vectors/collections/{collection}/search",
        json={"vector": vec, "limit": top_k},
        headers=headers,
    ).json()["results"]
    context = "\n\n".join(f"[{i+1}] {r['payload']['text']}" for i, r in enumerate(results))

    # 3. Chat
    resp = requests.post(f"{BASE}/v1/chat/completions", json={
        "model": "GLM-4.7",
        "messages": [
            {"role": "system", "content": f"Answer using context:\n{context}"},
            {"role": "user", "content": question},
        ],
    }, headers=headers).json()
    return resp["choices"][0]["message"]["content"]

print(rag_query("How do I create a collection?"))
```

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

### Python Chat Completion

Source: https://docs.openadapter.dev/docs/getting-started/quick-start

Connect to OpenAdapter using the OpenAI Python client. Configure the client with your API key and base URL.

```python
from openai import OpenAI

client = OpenAI(
    api_key="sk-cv-ாலத்தில்",
    base_url="https://api.openadapter.in/v1",
)

response = client.chat.completions.create(
    model="glm-4.7",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
```

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

### Web Search Request (Python)

Source: https://docs.openadapter.dev/docs/tools/web-search

This Python script demonstrates how to make a POST request to the web search API using the requests library. Replace API_KEY with your actual API key.

```python
import requests

resp = requests.post(
    "https://api.openadapter.in/v1/tools/search",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={
    "query": "latest AI news",
    "num_results": 10,
    "language": "en",
},
    )
print(resp.json())
```