Update README.md

README.md

@@ -29,10 +29,12 @@ To construct a specialized knowledge database for emerging contaminants usage cl
 1. Install Navicat on your computer and upload the **invitrodb_v4_3.sql** and **pubchemlite_exposomics_20251226.sql** databases.
 2. Deploy Docker and Dify. Set the Docker engine according to **dockerengine_setting.txt**.
 3. Create a custom tool named **sql_executor_pubchemlite_invitrodb_en** on the Dify platform. The detailed information for the schema tool is stored in **schema_tool.txt**. Note that you need to modify the URL address to your local address.
-4. On the Dify platform, select Import DSL File and upload the **dify_CECs_annotating.yml**.
-5. Before using this agent, you need to run Docker and the **step1_pubchemlite_invitrodb_to_dify_en.py** code. Note that in **step1_pubchemlite_invitrodb_to_dify_en.py**, the DB_CONFIGS needs to be modified to the username and password of your local SQL database.
-6. Once the setup is complete, you can start running.
-7. For batch queries, you can run the mini-program **step2_CECs_annotating_agent_v1.0.py**.
+4. Train the knowledge base on the FastGPT platform. The knowledge base file is **knowledge_database_input_iupac.csv**.  
+5. Deploy the FDA **docker-compose.yml** and import the external knowledge base into Dify.
+6. On the Dify platform, select Import DSL File and upload the **dify_CECs_annotating.yml**.
+7. Before using this agent, you need to run Docker and the **step1_pubchemlite_invitrodb_to_dify_en.py** code. Note that in **step1_pubchemlite_invitrodb_to_dify_en.py**, the DB_CONFIGS needs to be modified to the username and password of your local SQL database.
+8. Once the setup is complete, you can start running.
+9. For batch queries, you can run the mini-program **step2_CECs_annotating_agent_v1.0.py**.
 
 ## System Architecture & Components
 ### Core Databases Deployment
@@ -56,7 +58,7 @@ The system integrates three core databases with differentiated deployment strate
      2. Import dataset (50,000+ chemicals with IUPAC names and categories from the Norman database).
      3. Connect the dataset to a FastGPT application and configure prompts (consistent with Few-shot prompts).
      4. Publish the application and export the API key for subsequent calls.
-   - **Fast-Dify Adaptor (FDA) Plugin**
+   - **FastGPT-Dify Adaptor (FDA) Plugin**
      - Resolves API incompatibility between FastGPT and Dify.
      - Deployment steps: Create `docker-compose.yml` for FDA → Run `docker-compose up -d` in the configuration file directory to deploy the plugin.
    - **Dify External Knowledge Base Connection**: Link the trained FastGPT knowledge base to Dify by importing the FastGPT API key and knowledge base ID.