AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-12 23:19:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

solve knowledgegraph issue when calling gemini model (#2738)

Browse Source 
### What problem does this PR solve?
#2720

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
JobSmithManipulation 2024-10-08 18:27:04 +08:00 committed by GitHub
parent d92acdcf1d
commit 16472eb3ea
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 64 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
rag/llm/chat_model.py
View File

@ -252,7 +252,8 @@ class QWenChat(Base):
[ans]) else "······\n由于长度的原因，回答被截断了，要继续吗？"
yield ans
else:
yield ans + "\n**ERROR**: " + resp.message if str(resp.message).find("Access")<0 else "Out of credit. Please set the API key in **settings > Model providers.**"
yield ans + "\n**ERROR**: " + resp.message if str(resp.message).find(
"Access") < 0 else "Out of credit. Please set the API key in **settings > Model providers.**"
except Exception as e:
yield ans + "\n**ERROR**: " + str(e)
@ -623,7 +624,6 @@ class BedrockChat(Base):
if not isinstance(item["content"], list) and not isinstance(item["content"], tuple):
item["content"] = [{"text": item["content"]}]
try:
# Send the message to the model, using a basic inference configuration.
response = self.client.converse(
@ -702,7 +702,6 @@ class GeminiChat(Base):
self.model = GenerativeModel(model_name=self.model_name)
self.model._client = _client
def chat(self, system, history, gen_conf):
from google.generativeai.types import content_types
@ -717,6 +716,8 @@ class GeminiChat(Base):
for item in history:
if 'role' in item and item['role'] == 'assistant':
item['role'] = 'model'
if 'role' in item and item['role'] == 'system':
item['role'] = 'user'
if 'content' in item:
item['parts'] = item.pop('content')
@ -1151,7 +1152,8 @@ class BaiduYiyanChat(Base):
if system:
self.system = system
gen_conf["penalty_score"] = (
(gen_conf.get("presence_penalty", 0) + gen_conf.get("frequency_penalty", 0)) / 2
(gen_conf.get("presence_penalty", 0) + gen_conf.get("frequency_penalty",
0)) / 2
) + 1
if "max_tokens" in gen_conf:
gen_conf["max_output_tokens"] = gen_conf["max_tokens"]
@ -1174,7 +1176,8 @@ class BaiduYiyanChat(Base):
if system:
self.system = system
gen_conf["penalty_score"] = (
(gen_conf.get("presence_penalty", 0) + gen_conf.get("frequency_penalty", 0)) / 2
(gen_conf.get("presence_penalty", 0) + gen_conf.get("frequency_penalty",
0)) / 2
) + 1
if "max_tokens" in gen_conf:
gen_conf["max_output_tokens"] = gen_conf["max_tokens"]
@ -1415,4 +1418,3 @@ class GoogleChat(Base):
yield ans + "\n**ERROR**: " + str(e)
yield response._chunks[-1].usage_metadata.total_token_count