AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-12 19:59:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix #994 (#1006)

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

#994 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
KevinHuSh 2024-05-31 09:46:22 +08:00 committed by GitHub
parent dc7afe46fb
commit b9bb11879f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 30 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
rag/llm/embedding_model.py
View File

@ -123,30 +123,38 @@ class QWenEmbed(Base):
def encode(self, texts: list, batch_size=10):
import dashscope
res = []
token_count = 0
texts = [truncate(t, 2048) for t in texts]
for i in range(0, len(texts), batch_size):
resp = dashscope.TextEmbedding.call(
model=self.model_name,
input=texts[i:i + batch_size],
text_type="document"
)
embds = [[] for _ in range(len(resp["output"]["embeddings"]))]
for e in resp["output"]["embeddings"]:
embds[e["text_index"]] = e["embedding"]
res.extend(embds)
token_count += resp["usage"]["total_tokens"]
return np.array(res), token_count
try:
res = []
token_count = 0
texts = [truncate(t, 2048) for t in texts]
for i in range(0, len(texts), batch_size):
resp = dashscope.TextEmbedding.call(
model=self.model_name,
input=texts[i:i + batch_size],
text_type="document"
)
embds = [[] for _ in range(len(resp["output"]["embeddings"]))]
for e in resp["output"]["embeddings"]:
embds[e["text_index"]] = e["embedding"]
res.extend(embds)
token_count += resp["usage"]["total_tokens"]
return np.array(res), token_count
except Exception as e:
raise Exception("Account abnormal. Please ensure it's on good standing.")
return np.array([]), 0
def encode_queries(self, text):
resp = dashscope.TextEmbedding.call(
model=self.model_name,
input=text[:2048],
text_type="query"
)
return np.array(resp["output"]["embeddings"][0]
["embedding"]), resp["usage"]["total_tokens"]
try:
resp = dashscope.TextEmbedding.call(
model=self.model_name,
input=text[:2048],
text_type="query"
)
return np.array(resp["output"]["embeddings"][0]
["embedding"]), resp["usage"]["total_tokens"]
except Exception as e:
raise Exception("Account abnormal. Please ensure it's on good standing.")
return np.array([]), 0
class ZhipuEmbed(Base):