[DOC]: Guidance for complex use cases

README.md

@@ -61,6 +61,7 @@ This code snippet demonstrates how to build a prompt with table information, and
 > pip install transformers>=4.37.0
 > ```
 
+
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
@@ -123,6 +124,13 @@ generated_ids = [
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 ```
 
+**Complex Usage Scenarios**
+
+For complex usage scenarios, we provide a [tablegpt-agent]((https://github.com/tablegpt/tablegpt-agent)) toolkit to help you more conveniently handle various types of tabular inputs.
+
+This agent is built on top of the `Langgraph` library and provides a user-friendly interface for interacting with `TableGPT2`.
+
+
 **Deployment**
 
 For deployment, we recommend using vLLM.
@@ -150,6 +158,7 @@ For deployment, we recommend using vLLM.
   ```
   For more details about how to use TableGPT2, please refer to [our repository on GitHub](https://github.com/tablegpt/tablegpt-agent)
 
+
 **License**  
 
 TableGPT2-7B is under apache-2.0 license.