From f8fc2e15bce87e5470ce451d298f37ef0e065b6c Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Thu, 21 May 2026 16:05:17 +0000 Subject: [PATCH] docs: add Inception LLM service documentation - Added inception.mdx with full API reference for InceptionLLMService - Updated docs.json to include Inception in LLM navigation - Updated supported-services.mdx to list Inception in LLM table - Documents Mercury-2 model with reasoning_effort and realtime settings --- .../server/services/llm/inception.mdx | 149 ++++++++++++++++++ .../server/services/supported-services.mdx | 1 + docs.json | 1 + 3 files changed, 151 insertions(+) create mode 100644 api-reference/server/services/llm/inception.mdx diff --git a/api-reference/server/services/llm/inception.mdx b/api-reference/server/services/llm/inception.mdx new file mode 100644 index 00000000..a7effe33 --- /dev/null +++ b/api-reference/server/services/llm/inception.mdx @@ -0,0 +1,149 @@ +--- +title: "Inception" +description: "LLM service implementation using Inception's API with OpenAI-compatible interface" +--- + +## Overview + +`InceptionLLMService` provides access to Inception's Mercury-2 diffusion-based reasoning model through an OpenAI-compatible interface. It inherits from `OpenAILLMService` and supports streaming responses, function calling, and context management with advanced reasoning capabilities. + + + + Pipecat's API methods for Inception integration + + + Complete example with function calling + + + Access models and manage API keys + + + +## Installation + +To use Inception services, install the required dependency: + +```bash +uv add "pipecat-ai[inception]" +``` + +## Prerequisites + +### Inception Account Setup + +Before using Inception LLM services, you need: + +1. **Inception Account**: Sign up at [Inception Labs](https://inceptionlabs.ai/) +2. **API Key**: Generate an API key from your account dashboard +3. **Model Selection**: Access to Mercury-2, Inception's diffusion-based reasoning model + +### Required Environment Variables + +- `INCEPTION_API_KEY`: Your Inception API key for authentication + +## Configuration + + + Inception API key for authentication. + + + + Base URL for Inception API endpoint. + + + + Runtime-configurable settings. See [Settings](#settings) below. + + +### Settings + +Runtime-configurable settings passed via the `settings` constructor argument using `InceptionLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. + +This service extends `OpenAILLMService.Settings` with Inception-specific parameters: + + + Model identifier to use. Defaults to "mercury-2", Inception's diffusion-based reasoning model. + + + + Controls how much reasoning the model applies. Options are "instant", "low", "medium", or "high". When unset, the parameter is omitted and Inception's server-side default applies. + + + + When True, reduces time to first diffusion block (TTFT) for faster initial response times. + + +For additional settings inherited from OpenAI, see [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings). + +## Usage + +### Basic Setup + +```python +import os +from pipecat.services.inception import InceptionLLMService + +llm = InceptionLLMService( + api_key=os.getenv("INCEPTION_API_KEY"), +) +``` + +### With Custom Settings + +```python +from pipecat.services.inception import InceptionLLMService + +llm = InceptionLLMService( + api_key=os.getenv("INCEPTION_API_KEY"), + settings=InceptionLLMService.Settings( + model="mercury-2", + reasoning_effort="instant", + realtime=True, + temperature=0.7, + max_tokens=2048, + ), +) +``` + +### With Function Calling + +```python +from pipecat.services.inception import InceptionLLMService +from pipecat.services.llm_service import FunctionCallParams + +async def get_weather(params: FunctionCallParams): + await params.result_callback({"temperature": "75", "conditions": "sunny"}) + +llm = InceptionLLMService( + api_key=os.getenv("INCEPTION_API_KEY"), + settings=InceptionLLMService.Settings( + reasoning_effort="low", + ), +) + +llm.register_function("get_weather", get_weather) +``` + +## Notes + +- Inception does not support the `"developer"` message role. Use `"system"` instead. +- The Mercury-2 model uses a diffusion-based reasoning approach, which can be controlled via the `reasoning_effort` parameter. +- Setting `realtime=True` optimizes for lower time-to-first-token at the potential cost of reasoning depth. + + + The `InputParams` / `params=` pattern is deprecated as of v0.0.105. Use + `Settings` / `settings=` instead. See the [Service Settings + guide](/pipecat/fundamentals/service-settings) for migration details. + diff --git a/api-reference/server/services/supported-services.mdx b/api-reference/server/services/supported-services.mdx index e4b6073e..cb1ca373 100644 --- a/api-reference/server/services/supported-services.mdx +++ b/api-reference/server/services/supported-services.mdx @@ -75,6 +75,7 @@ LLMs receive text or audio based input and output a streaming text response. | [Google Vertex AI](/api-reference/server/services/llm/google-vertex) | `uv add "pipecat-ai[google]"` | | [Grok](/api-reference/server/services/llm/grok) | `uv add "pipecat-ai[grok]"` | | [Groq](/api-reference/server/services/llm/groq) | `uv add "pipecat-ai[groq]"` | +| [Inception](/api-reference/server/services/llm/inception) | `uv add "pipecat-ai[inception]"` | | [Mistral](/api-reference/server/services/llm/mistral) | `uv add "pipecat-ai[mistral]"` | | [Nebius](/api-reference/server/services/llm/nebius) | `uv add "pipecat-ai[nebius]"` | | [Novita AI](/api-reference/server/services/llm/novita) | `uv add "pipecat-ai[novita]"` | diff --git a/docs.json b/docs.json index d64aef7d..49e90dfd 100644 --- a/docs.json +++ b/docs.json @@ -384,6 +384,7 @@ "api-reference/server/services/llm/google-vertex", "api-reference/server/services/llm/grok", "api-reference/server/services/llm/groq", + "api-reference/server/services/llm/inception", "api-reference/server/services/llm/mistral", "api-reference/server/services/llm/nebius", "api-reference/server/services/llm/novita",