> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Capabilities Overview

> LiteLLM endpoint parity capabilities for PraisonAI

## Overview

PraisonAI Capabilities provide direct access to LiteLLM endpoints with full parity, enabling you to use completions, embeddings, images, audio, and more through a unified API.

## Available Capabilities

### Core APIs

| Capability | Description | Code Docs | CLI Docs |
| - | - | - | - |
| [Completions](/docs/capabilities/completions) | Chat and text completions | [Code](/docs/capabilities/completions) | [CLI](/docs/capabilities/completions-cli) |
| [Embeddings](/docs/capabilities/embeddings) | Text embeddings | [Code](/docs/capabilities/embeddings) | [CLI](/docs/capabilities/embeddings-cli) |
| [Messages](/docs/capabilities/messages) | Anthropic-style messages | [Code](/docs/capabilities/messages) | [CLI](/docs/capabilities/messages-cli) |

### Media Generation

| Capability | Description | Code Docs | CLI Docs |
| - | - | - | - |
| [Images](/docs/capabilities/images) | Image generation | [Code](/docs/capabilities/images) | [CLI](/docs/capabilities/images-cli) |
| [Videos](/docs/capabilities/videos) | Video generation (default `openai/sora-2`) | [Code](/docs/capabilities/videos) | [CLI](/docs/capabilities/videos-cli) |
| [Realtime](/docs/capabilities/realtime) | Audio/video streaming | [Code](/docs/capabilities/realtime) | [CLI](/docs/capabilities/realtime-cli) |

### Safety & Moderation

| Capability | Description | Code Docs | CLI Docs |
| - | - | - | - |
| [Moderations](/docs/capabilities/moderations) | Content moderation | [Code](/docs/capabilities/moderations) | [CLI](/docs/capabilities/moderations-cli) |
| [Audio](/docs/capabilities/audio) | Transcription (STT) and text-to-speech (TTS) | [Code](/docs/capabilities/audio) | [CLI](/docs/capabilities/audio-cli) |

### Advanced

| Capability | Description | Docs |
| - | - | - |
| [Vector Store Files](/docs/features/capabilities-vector-store-files) | Add, list, and delete files in a vector store | [Guide](/docs/features/capabilities-vector-store-files) |
| [Search](/docs/features/capabilities-search) | Web search via DuckDuckGo (requires `ddgs`) | [Guide](/docs/features/capabilities-search) |
| [Containers](/docs/features/capabilities-containers) | Container management (no backend yet) | [Guide](/docs/features/capabilities-containers) |

<Warning>
  `container_create` and the other container functions have **no backend** and raise `NotImplementedError`. `search` requires the `ddgs` package and **raises** on error instead of returning empty results. See the linked guides.
</Warning>

## Quick Start

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai import embed, embedding  # Both work identically
from praisonai.capabilities import chat_completion, image_generate, moderate

# Chat completion
result = chat_completion(
    messages=[{"role": "user", "content": "Hello!"}],
    model="gpt-4o-mini"
)
print(result.content)

# Embeddings (embed and embedding are aliases)
result = embed("Hello world", model="text-embedding-3-small")
print(f"Dimensions: {len(result.embeddings[0])}")

# Image generation
result = image_generate("A sunset", model="dall-e-3")
print(f"URL: {result[0].url}")

# Moderation
result = moderate("Check this content")
print(f"Flagged: {result[0].flagged}")
```

## CLI Quick Start

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Chat completion
praisonai completions "What is AI?"

# Embeddings (both commands work)
praisonai embed "Hello world"
praisonai embedding "Hello world"

# Image generation
praisonai images "A beautiful sunset"

# Moderation
praisonai moderate "Check this content"
```

## All Capabilities

The full list of 116 capabilities includes:

* **Audio**: transcribe, speech
* **Images**: image\_generate, image\_edit
* **Videos**: [video\_generate](/docs/capabilities/videos) (default `openai/sora-2`)
* **Files**: file\_create, file\_list, file\_retrieve, file\_delete
* **Batches**: batch\_create, batch\_list, batch\_retrieve, batch\_cancel
* **Vector Stores**: vector\_store\_create, vector\_store\_search, vector\_store\_file\_create, vector\_store\_file\_list, vector\_store\_file\_delete
* **Embeddings**: embed, embedding (alias)
* **Rerank**: rerank
* **Moderations**: moderate
* **OCR**: ocr
* **Assistants**: assistant\_create, assistant\_list
* **Fine-tuning**: fine\_tuning\_create, fine\_tuning\_list
* **Responses**: responses\_create
* **Passthrough**: passthrough
* **Containers**: container\_create *(no backend yet — raises `NotImplementedError`, see [Containers](/docs/features/capabilities-containers))*
* **Search**: search *(requires the `ddgs` package; raises on error, see [Search](/docs/features/capabilities-search))*
* **A2A**: a2a\_send
* **Completions**: chat\_completion, text\_completion
* **Messages**: messages\_create, count\_tokens
* **Guardrails**: [apply\_guardrail](/docs/features/apply-guardrail) — fails closed by default; `on_error="allow"` for the old permissive behaviour
* **RAG**: rag\_query
* **Realtime**: realtime\_connect
* **Skills**: skill\_list, skill\_load
* **MCP**: mcp\_list\_tools, mcp\_call\_tool

All capabilities have both sync and async versions (prefixed with `a`).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.