From 4d835b73035c5efb16f75ca4a4f8f72e4c75f803 Mon Sep 17 00:00:00 2001
From: Qidi Cao <105201479+XiaoCaoAskedForHelp@users.noreply.github.com>
Date: Wed, 28 May 2025 10:58:06 +0800
Subject: [PATCH] =?UTF-8?q?fix:=20resolve=20=E2=80=9Chas=20no=20attribute?=
 =?UTF-8?q?=20'max=5Flength'=E2=80=9D=20error=20in=20keyword=5Fextraction?=
 =?UTF-8?q?=20(#7903)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

### What problem does this PR solve?

**Issue Description:**

When using the `/api/retrieval` endpoint with a POST request and setting
the `keyword` parameter to `true`, the system invokes the
`model_instance` method from `TenantLLMService` to create a `chat_mdl`
instance. Subsequently, it calls the `keyword_extraction` method to
extract keywords.

However, within the `keyword_extraction` method, the `chat` function of
the LLM attempts to access the `chat_mdl.max_length` attribute to
validate input length. This results in the following error:

```
AttributeError: 'SILICONFLOWChat' object has no attribute 'max_length'
```

**Proposed Solution:**

Upon reviewing other parts of the codebase where `chat_mdl` instances
are created, it appears that utilizing `LLMBundle` for instantiation is
more appropriate. `LLMBundle` includes the `max_length` attribute, which
should resolve the encountered error.



### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
---
 api/apps/api_app.py | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/api/apps/api_app.py b/api/apps/api_app.py
index cc417c9a2..f66eb8067 100644
--- a/api/apps/api_app.py
+++ b/api/apps/api_app.py
@@ -18,7 +18,7 @@ import os
 import re
 from datetime import datetime, timedelta
 from flask import request, Response
-from api.db.services.llm_service import TenantLLMService
+from api.db.services.llm_service import LLMBundle
 from flask_login import login_required, current_user
 
 from api.db import VALID_FILE_TYPES, VALID_TASK_STATUS, FileType, LLMType, ParserType, FileSource
@@ -875,14 +875,12 @@ def retrieval():
                 data=False, message='Knowledge bases use different embedding models or does not exist."',
                 code=settings.RetCode.AUTHENTICATION_ERROR)
 
-        embd_mdl = TenantLLMService.model_instance(
-            kbs[0].tenant_id, LLMType.EMBEDDING.value, llm_name=kbs[0].embd_id)
+        embd_mdl = LLMBundle(kbs[0].tenant_id, LLMType.EMBEDDING, llm_name=kbs[0].embd_id)
         rerank_mdl = None
         if req.get("rerank_id"):
-            rerank_mdl = TenantLLMService.model_instance(
-                kbs[0].tenant_id, LLMType.RERANK.value, llm_name=req["rerank_id"])
+            rerank_mdl = LLMBundle(kbs[0].tenant_id, LLMType.RERANK, llm_name=req["rerank_id"])
         if req.get("keyword", False):
-            chat_mdl = TenantLLMService.model_instance(kbs[0].tenant_id, LLMType.CHAT)
+            chat_mdl = LLMBundle(kbs[0].tenant_id, LLMType.CHAT)
             question += keyword_extraction(chat_mdl, question)
         ranks = settings.retrievaler.retrieval(question, embd_mdl, kbs[0].tenant_id, kb_ids, page, size,
                                                similarity_threshold, vector_similarity_weight, top,