# Infinigence

Are you experiencing this: you’ve saved 26 practical articles in WeChat Favorites but never opened them again; your computer has 10+ scattered files in a folder called “Study Materials”; you want to find a theory you read half a year ago but only remember a few keywords. And when the amount of information you receive each day exceeds your brain’s processing limit, 90% of valuable knowledge is forgotten within 72 hours.\
Now, by using the Infini-AI Model Service Platform API + Cherry Studio to build a personal knowledge base, you can turn WeChat articles that have been gathering dust in Favorites and fragmented course content into structured knowledge for precise retrieval.\\

### 1. Building a Personal Knowledge Base

#### 1. Infini-AI API Service: The “thinking center” of your knowledge base — easy to use and stable

As the “thinking center” of the knowledge base, the Infini-AI Model Service Platform provides model versions such as the full-powered DeepSeek R1, offering stable API services,**Currently, after registration, it can be used for free with no barrier.**It supports mainstream embedding models such as bge and jina to build a knowledge base,**and the platform is also continuously updating stable, latest, and most powerful open-source model services**covering multiple modalities such as images, video, and voice.

<figure><img src="/files/7d81f0d1ab9d5b8b0a4bf8ee99f26b928ddc8718" alt=""><figcaption></figcaption></figure>

#### 2. Cherry Studio: Build a knowledge base with no code

Cherry Studio is an easy-to-use AI tool. Compared with RAG knowledge base development, which requires a 1–2 month deployment cycle, this tool’s advantage is that it supports**zero-code operation,**&#x61;nd can import Markdown/PDF/web pages and other formats with one click. A 40 MB file can be parsed in 1 minute. In addition, you can also add local computer folders, article URLs from WeChat Favorites, and course notes.\\

### 2. Build Your Exclusive Knowledge Manager in 3 Steps

#### Step 1: Basic Preparation

1. Visit the Cherry Studio official website to download the appropriate version (<https://cherry-ai.com/>)
2. Register an account: log in to the Infini-AI Model Service Platform (<https://cloud.infini-ai.com/genstudio/model?cherrystudio>)

<figure><img src="/files/8c66f387756dea82b8cc04ba32b742b0fb61e5d5" alt=""><figcaption></figcaption></figure>

* Get the API key: in the "Model Plaza", select deepseek-r1, click Create and get the APIKEY, and copy the model name

<figure><img src="/files/05b895589130f8ad9addc744c3f2506e5c53ea3e" alt=""><figcaption></figcaption></figure>

#### Step 2: Open CherryStudio settings, select Infini-AI in the model service, fill in the API key, and enable the Infini-AI model service

<figure><img src="/files/2fcc201e2698ebe6c05020b9749ab49ad820c582" alt=""><figcaption></figcaption></figure>

After completing the above steps, choose the required large model during interaction, and you can use Infini-AI's API service in CherryStudio.\
For convenience, you can also set a "default model"\\

<figure><img src="/files/e00a01de4d5d20a56fc1b754d333ea3c3bf8cf97" alt=""><figcaption></figcaption></figure>

Step 3: Add a knowledge base

Choose any version of the embedding models from the bge series or jina series on the Infini-AI Model Service Platform

<figure><img src="/files/6b7bebdd7dd27c95d6ec2457b302133bad9e6d1c" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/09048226986170b9a4c3b58d53fa53c2f6007376" alt=""><figcaption></figcaption></figure>

### 3. Real User Scenario Test

* After importing the study materials, enter "Organize the core formula derivation of Chapter 3 of Machine Learning"

<figure><img src="/files/3d95a50412539ff2a8c24d59c0d24472e03fe584" alt=""><figcaption></figcaption></figure>

\
**See the generated result image**

<figure><img src="/files/6971447bc3a2d52b3c273d8aa458b89181d5fa43" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.cherry-ai.com/docs/en-us/pre-basic/providers/wu-wen-xin-qiong.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.