Update README.md

README.md

@@ -3,14 +3,18 @@ license: cc-by-nc-4.0
 tags:
 - agent
 - chemistry
+- environment
 ---
 ## Model Overview
-This model is an **Contaminants of Emerging Concern Annotation Intelligent Agent** built on the Dify platform, integrated with the Norman knowledge base, Pubchemlite_exposomics database, and Invitrodb_v4.3 database. It enables high-throughput, large-scale annotation of emerging contaminants, including **usage classification**, **toxicity endpoints**, and corresponding **AC50 value queries** by inputting the IUPAC name of the target contaminant.
+This model is an **Contaminants of Emerging Concern Annotation Intelligent Agent** built on the Dify platform, integrated with the Norman knowledge base, Pubchemlite_exposomics database, and Invitrodb_v4.3 database. It enables high-throughput, large-scale annotation of emerging contaminants, including **usage classification** and **toxicity endpoints** by inputting the IUPAC name of the target contaminant.
+<div align="center">
+<img src="figure/pipeline.jpg" alt="Norman_category" width="800">
+</div>
 
 ## Model Purpose
 To construct a specialized knowledge database for emerging contaminants usage classification, which combines multi-source chemical/toxicological databases and AI agents. The core goals are:
 1. Realize fast and large-scale annotation of emerging contaminants' usage categories.
-2. Provide efficient query services for toxicity endpoints and their corresponding AC50 values.
+2. Provide efficient query services for toxicity endpoints.
 3. Support high-throughput data analysis scenarios for emerging contaminants in environmental chemistry and toxicology research.
 
 ## Key Definitions
@@ -29,7 +33,8 @@ To construct a specialized knowledge database for emerging contaminants usage cl
 The system integrates three core databases with differentiated deployment strategies:
 1. **Norman Chemical Classification Database**
    - Serves as a relational knowledge base, uploaded and parsed on the FastGPT platform, then embedded into the Dify platform.
-   - Optimized classification: Integrated or removed redundant categories, finally categorized chemicals into **9 classes** (see Figure 1).
+   - Optimized classification: Integrated or removed redundant categories, finally categorized chemicals into **9 classes**.
+    <img src="figure/Norman_category.png" alt="Norman_category" width="400">
 2. **Pubchemlite_exposomics & Invitrodb_v4.3 Databases**
    - Deployed in local SQL databases to support efficient local query and invocation.
    - Query workflow: GPT-4o generates SQL statements → Extract valid SQL queries → Backend executes database queries and returns results.
@@ -69,7 +74,7 @@ The system integrates three core databases with differentiated deployment strate
 1. Input the **IUPAC name** of the emerging contaminant into the Dify chat interface.
 2. The AI agent invokes:
    - FastGPT knowledge base for **usage classification** via FDA plugin.
-   - Local SQL databases for **toxicity endpoints and AC50 values** via GPT-4o-generated SQL queries.
+   - Local SQL databases for **toxicity endpoints** via GPT-4o-generated SQL queries.
 3. Receive the structured output (JSON format) containing usage category, toxicity endpoints, and corresponding AC50 values.
 
 ## Limitations