fix OpenAI Embedding length error (#1972)

### What problem does this PR solve? #1958 fix OpenAI Embedding length error ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) --------- Co-authored-by: Zhedong Cen <[email protected]>
infiniflow · Aug 16, 2024 · b4ef50b · b4ef50b
1 parent 5b5e367
commit b4ef50b
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/rag/llm/embedding_model.py b/rag/llm/embedding_model.py
@@ -99,14 +99,14 @@ def __init__(self, key, model_name="text-embedding-ada-002",
         self.model_name = model_name
 
     def encode(self, texts: list, batch_size=32):
-        texts = [truncate(t, 8196) for t in texts]
+        texts = [truncate(t, 8191) for t in texts]
         res = self.client.embeddings.create(input=texts,
                                             model=self.model_name)
         return np.array([d.embedding for d in res.data]
                         ), res.usage.total_tokens
 
     def encode_queries(self, text):
-        res = self.client.embeddings.create(input=[truncate(text, 8196)],
+        res = self.client.embeddings.create(input=[truncate(text, 8191)],
                                             model=self.model_name)
         return np.array(res.data[0].embedding), res.usage.total_tokens