You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: website/blog/2025-10-30-ragflow-in-practice-an-intelligent-agent-for-in-depth-research-on-company-research-reports/index.md
+10-10Lines changed: 10 additions & 10 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,7 +4,7 @@ title: ragflow in practice an intelligent agent for in depth research on company
4
4
tags: ragflow
5
5
---
6
6
7
-
![]()
7
+

8
8
9
9
# Background
10
10
@@ -238,11 +238,11 @@ We have also received requests from everyone expressing a preference not to extr
238
238
239
239
## 2.4 Build the "Research Report Information Extraction" function
240
240
241
-

241
+

242
242
243
243
Utilize an information extraction agent, which, based on the `stockCode`, calls the AlphaVantage API to extract the latest authoritative research reports and insights. Meanwhile, it invokes the internal research report retrieval agent to obtain the full text of the complete research reports. Finally, it outputs the two parts of content separately in a fixed structure, thereby achieving an efficient information extraction function.
244
244
245
-

245
+

246
246
247
247
System prompt:
248
248
@@ -278,17 +278,17 @@ Directly output the content provided by the Internal Research Report Retrieval A
278
278
279
279
Add the MCP tool:
280
280
281
-

281
+

282
282
283
283
Add the MCP tool under the agent and select the required method, such as "EARNINGS_CALL_TRANSCRIPT".
284
284
285
-

285
+

286
286
287
287
### 2.4.2 Internal Research Report Retrieval Agent
288
288
289
289
The key focus in constructing the internal research report retrieval agent lies in accurately identifying the company or stock code in user queries. It then invokes the Retrieval tool to search for research reports from the knowledge base and outputs the full text, ensuring that information such as data, viewpoints, conclusions, tables, and risk warnings is not omitted. This enables high-fidelity extraction of research report content.
290
290
291
-

291
+

292
292
293
293
System Prompt:
294
294
@@ -324,7 +324,7 @@ Read user input → Identify the involved company/stock (supports abbreviations,
324
324
325
325
The research report generation agent automatically extracts and structurally organizes financial and economic information, generating foundational data and content for investment bank analysts that are professional, retain differentiation, and can be directly used in investment research reports.
326
326
327
-

327
+

328
328
329
329
```
330
330
<role>
@@ -405,20 +405,20 @@ Apply this format consistently to all section headings (Summary, Company Overvie
405
405
406
406
The reply message node is used to output the "financial statements" and "research report content" that are the final outputs of the workflow.
407
407
408
-

408
+

409
409
410
410
## 2.7 Save and Test
411
411
412
412
Click "Save" - "Run" - and view the execution results.
413
413
The entire process takes approximately 5 minutes to run.
414
414
Execution Results:
415
415
416
-

416
+

417
417
418
418
Log:
419
419
The entire process took approximately 5 minutes to run.
0 commit comments