From 49d67cbcb797f39bf87d0256a004b5ecf3f4f2f2 Mon Sep 17 00:00:00 2001
From: Rainman <91299664+Rainman5042@users.noreply.github.com>
Date: Tue, 24 Jun 2025 09:35:02 +0800
Subject: [PATCH] fix a bug when using huggingface embedding api (#8432)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

### What problem does this PR solve?

image_version: v0.19.1
This PR fixes a bug in the HuggingFaceEmBedding API method that was
causing AssertionError: assert len(vects) == len(docs) during the
document embedding process.

#### Problem
The HuggingFaceEmbed.encode() method had an early return statement
inside the for loop, causing it to return after processing only the
first text input instead of processing all texts in the input list.

**Error Messenge**
```python
AssertionError: assert len(vects) == len(docs) # input chunks  != embedded  vectors from embedding api
File "/ragflow/rag/svr/task_executor.py", line 442, in embedding
```



**Buggy code(/ragflow/rag/llm/embedding_model.py)**
```python
class HuggingFaceEmbed(Base):
    def __init__(self, key, model_name, base_url=None):
        if not model_name:
            raise ValueError("Model name cannot be None")
        self.key = key
        self.model_name = model_name.split("___")[0]
        self.base_url = base_url or "http://127.0.0.1:8080"
        def encode(self, texts: list):
            embeddings = []
            for text in texts:
                response = requests.post(...)
                if response.status_code == 200:
                    try:
                        embedding = response.json()
                        embeddings.append(embedding[0])
                        # ❌ Early return
                        return np.array(embeddings), sum([num_tokens_from_string(text) for text in texts])
                    except Exception as _e:
                        log_exception(_e, response)
                else:
                    raise Exception(...)
```
**Fixed Code(I just Rollback this function to the v0.19.0 version)**
```python
Class HuggingFaceEmbed(Base):
    def __init__(self, key, model_name, base_url=None):
        if not model_name:
            raise ValueError("Model name cannot be None")
        self.key = key
        self.model_name = model_name.split("___")[0]
        self.base_url = base_url or "http://127.0.0.1:8080"
        def encode(self, texts: list):
            embeddings = []
            for text in texts:
                response = requests.post(...)
                if response.status_code == 200:
                    embedding = response.json()
                    embeddings.append(embedding[0])  # ✅ Only append, no return
                else:
                    raise Exception(...)
            return np.array(embeddings), sum([num_tokens_from_string(text) for text in texts])  # ✅ Return after processing all
```
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 rag/llm/embedding_model.py | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/rag/llm/embedding_model.py b/rag/llm/embedding_model.py
index 25cbc5250..373485b9a 100644
--- a/rag/llm/embedding_model.py
+++ b/rag/llm/embedding_model.py
@@ -871,14 +871,11 @@ class HuggingFaceEmbed(Base):
                 headers={'Content-Type': 'application/json'}
             )
             if response.status_code == 200:
-                try:
-                    embedding = response.json()
-                    embeddings.append(embedding[0])
-                    return np.array(embeddings), sum([num_tokens_from_string(text) for text in texts])
-                except Exception as _e:
-                    log_exception(_e, response)
+                embedding = response.json()
+                embeddings.append(embedding[0])
             else:
                 raise Exception(f"Error: {response.status_code} - {response.text}")
+        return np.array(embeddings), sum([num_tokens_from_string(text) for text in texts])
 
     def encode_queries(self, text):
         response = requests.post(
@@ -887,11 +884,8 @@ class HuggingFaceEmbed(Base):
             headers={'Content-Type': 'application/json'}
         )
         if response.status_code == 200:
-            try:
-                embedding = response.json()
-                return np.array(embedding[0]), num_tokens_from_string(text)
-            except Exception as _e:
-                log_exception(_e, response)
+            embedding = response.json()
+            return np.array(embedding[0]), num_tokens_from_string(text)
         else:
             raise Exception(f"Error: {response.status_code} - {response.text}")