AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-14 07:35:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: the error of Ollama embeddings interface returning "500 Internal Server Error" (#6350)

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

Fix the error where the Ollama embeddings interface returns a “500
Internal Server Error” when using models such as xiaobu-embedding-v2 for
embedding.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
zhou 2025-03-21 15:25:48 +08:00 committed by GitHub
parent f537b6ca00
commit 85480f6292
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
rag/llm/embedding_model.py
View File

@ -260,14 +260,16 @@ class OllamaEmbed(Base):
tks_num = 0 tks_num = 0
for txt in texts: for txt in texts:
res = self.client.embeddings(prompt=txt, res = self.client.embeddings(prompt=txt,
model=self.model_name) model=self.model_name,
options={"use_mmap": True})
arr.append(res["embedding"]) arr.append(res["embedding"])
tks_num += 128 tks_num += 128
return np.array(arr), tks_num return np.array(arr), tks_num
def encode_queries(self, text): def encode_queries(self, text):
res = self.client.embeddings(prompt=text, res = self.client.embeddings(prompt=text,
model=self.model_name) model=self.model_name,
options={"use_mmap": True})
return np.array(res["embedding"]), 128 return np.array(res["embedding"]), 128
@ -834,4 +836,4 @@ class GPUStackEmbed(OpenAIEmbed):
print(key,base_url) print(key,base_url)
self.client = OpenAI(api_key=key, base_url=base_url) self.client = OpenAI(api_key=key, base_url=base_url)
self.model_name = model_name self.model_name = model_name