Update README.md
Browse files
README.md
CHANGED
|
@@ -39,11 +39,11 @@ The system integrates three core databases with differentiated deployment strate
|
|
| 39 |
- Deployed in local SQL databases to support efficient local query and invocation.
|
| 40 |
- Query workflow: GPT-4o generates SQL statements → Extract valid SQL queries → Backend executes database queries and returns results.
|
| 41 |
|
| 42 |
-
###
|
| 43 |
1. **Base Model**: GPT-4o is used to generate SQL query statements and organize output data in JSON format for subsequent data extraction.
|
| 44 |
2. **Custom Schema Tool**
|
| 45 |
- Created on the Dify platform to standardize SQL statement generation and API invocation logic.
|
| 46 |
-
- Implementation steps: Create custom tool → Configure tool name and Schema rules (see
|
| 47 |
3. **Knowledge Base Integration (FastGPT + Dify)**
|
| 48 |
- **FastGPT Knowledge Base Construction**
|
| 49 |
1. Log in to FastGPT (https://fastgpt.aiown.top/) and enter the main interface.
|
|
|
|
| 39 |
- Deployed in local SQL databases to support efficient local query and invocation.
|
| 40 |
- Query workflow: GPT-4o generates SQL statements → Extract valid SQL queries → Backend executes database queries and returns results.
|
| 41 |
|
| 42 |
+
### Agent Workflow Design (Dify Chatflow)
|
| 43 |
1. **Base Model**: GPT-4o is used to generate SQL query statements and organize output data in JSON format for subsequent data extraction.
|
| 44 |
2. **Custom Schema Tool**
|
| 45 |
- Created on the Dify platform to standardize SQL statement generation and API invocation logic.
|
| 46 |
+
- Implementation steps: Create custom tool → Configure tool name and Schema rules (see sql_executor_pubchemlite_invitrodb_schema.txt for details).
|
| 47 |
3. **Knowledge Base Integration (FastGPT + Dify)**
|
| 48 |
- **FastGPT Knowledge Base Construction**
|
| 49 |
1. Log in to FastGPT (https://fastgpt.aiown.top/) and enter the main interface.
|