FastGPTFastGPT

SiliconCloud Integration Example

Configure SiliconCloud LLM, embedding, and rerank models in a self-hosted FastGPT deployment.

SiliconCloud provides open-source model inference APIs covering language, embedding, reranking, text-to-speech (TTS), and speech-to-text (STT) models for FastGPT.

Before reading this guide, make sure you've read the Model Configuration Guide.

1. Register an Account

  1. Register a SiliconCloud account
  2. Go to the console and get your API key: https://cloud.siliconflow.cn/account/ak

2. Add Models

The system includes a few SiliconCloud models by default for quick testing. If you need additional models, you can add them manually.

In Admin → System Resources → System Models, enable the required language and vision models (such as Qwen2.5-72B and Qwen2-VL-72B), embedding model (bge-m3), rerank model (bge-reranker-v2-m3), and speech models.

2. Add Models — interface example

3. Add a Model provider

On the Model providers page, add a new SiliconCloud provider and select the models you just added.

3. Add a Model provider — interface example

4. Test Models

First, verify that all SiliconCloud models are running properly.

4. Test Models — interface example

5. Test in an App

Test Chat and Image Recognition

Create a simple app, select the corresponding model, enable image upload, and test:

Test Chat and Image Recognition — interface exampleTest Chat and Image Recognition — interface example

Test Dataset Import and Q&A

Create a Dataset (since only one embedding model is configured, the embedding model selector won't appear on the page):

Test Dataset Import and Q&A — interface exampleTest Dataset Import and Q&A — interface example

Import a local file and complete the chunking and indexing steps, then test Dataset Q&A.

Go back to the app we just created, select the Dataset, adjust the parameters, and start a conversation:

Test Dataset Import and Q&A — interface exampleTest Dataset Import and Q&A — interface exampleTest Dataset Import and Q&A — interface example

After the conversation, click the citation at the bottom to view citation details, including search and reranking scores:

Test Dataset Import and Q&A — interface exampleTest Dataset Import and Q&A — interface example

Test Text-to-Speech

In the same app, find "Voice Playback" in the left sidebar configuration. Click to select a voice model from the popup and preview it:

Test Text-to-Speech — interface example

Test Speech-to-Text

In the same app, find "Voice Input" in the left sidebar configuration. Click to enable voice input from the popup:

Test Speech-to-Text — interface example

Once enabled, a microphone icon appears in the chat input box. Click it to start voice input:

Test Speech-to-Text — interface exampleTest Speech-to-Text — interface example

Summary

If you want to quickly try open source models or get started with FastGPT without applying for API keys from multiple providers, SiliconCloud is a great option for a fast start.

If you plan to self-host models and FastGPT in the future, you can use SiliconCloud for initial testing and validation, then proceed with hardware procurement later — reducing POC time and cost.

Edit on GitHub

Last updated

On this page

Put your business knowledge to work with AI

Import company documents and build accurate, reliable, traceable AI answers.