Exception: list index out of range

[2044745733]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

Every time I perform a knowledge base search, the input question fails to be converted into a vector. I am using the shaw/dmeta-embedding-zh model on Ollama

2. Additional context or comments

model='shaw/dmeta-embedding-zh' embeddings=[] usage=EmbeddingUsage(tokens=4, total_tokens=4, unit_price=Decimal('0'), price_unit=Decimal('0'), total_price=Decimal('0E-7'), currency='USD', latency=0.05005987361073494)
2024-12-07 12:31:12.949 ERROR [Thread-772 (_generate_worker)] [node.py:74] - Node 1733563649719 failed to run
Traceback (most recent call last):
File "/mnt/data8/liuhuan/dify-main/api/core/workflow/nodes/base/node.py", line 72, in run
result = self._run()
^^^^^^^^^^^
File "/mnt/data8/liuhuan/dify-main/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py", line 65, in _run
results = self._fetch_dataset_retriever(node_data=self.node_data, query=query)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/data8/liuhuan/dify-main/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py", line 162, in _fetch_dataset_retriever
all_documents = dataset_retrieval.multiple_retrieve(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/data8/liuhuan/dify-main/api/core/rag/retrieval/dataset_retrieval.py", line 420, in multiple_retrieve
all_documents = data_post_processor.invoke(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/data8/liuhuan/dify-main/api/core/rag/data_post_processor/data_post_processor.py", line 37, in invoke
documents = self.rerank_runner.run(query, documents, score_threshold, top_n, user)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/data8/liuhuan/dify-main/api/core/rag/rerank/weight_rerank.py", line 49, in run
query_vector_scores = self._calculate_cosine(self.tenant_id, query, documents, self.weights.vector_setting)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/data8/liuhuan/dify-main/api/core/rag/rerank/weight_rerank.py", line 162, in _calculate_cosine
query_vector = cache_embedding.embed_query(query)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/data8/liuhuan/dify-main/api/core/rag/embedding/cached_embedding.py", line 118, in embed_query
raise ex
File "/mnt/data8/liuhuan/dify-main/api/core/rag/embedding/cached_embedding.py", line 113, in embed_query
embedding_results = embedding_result.embeddings[0]
~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^
IndexError: list index out of range

[loganclark360]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

Every time I perform a knowledge base search, the input question fails to be converted into a vector. I am using the shaw/dmeta-embedding-zh model on Ollama

2. Additional context or comments

model='shaw/dmeta-embedding-zh' embeddings=[] usage=EmbeddingUsage(tokens=4, total_tokens=4, unit_price=Decimal('0'), price_unit=Decimal('0'), total_price=Decimal('0E-7'), currency='USD', latency=0.05005987361073494)

2024-12-07 12:31:12.949 ERROR [Thread-772 (_generate_worker)] [node.py:74] - Node 1733563649719 failed to run

Traceback (most recent call last):

File "/mnt/data8/liuhuan/dify-main/api/core/workflow/nodes/base/node.py", line 72, in run

result = self._run()

         ^^^^^^^^^^^

File "/mnt/data8/liuhuan/dify-main/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py", line 65, in _run

results = self._fetch_dataset_retriever(node_data=self.node_data, query=query)

          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/mnt/data8/liuhuan/dify-main/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py", line 162, in _fetch_dataset_retriever

all_documents = dataset_retrieval.multiple_retrieve(

                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/mnt/data8/liuhuan/dify-main/api/core/rag/retrieval/dataset_retrieval.py", line 420, in multiple_retrieve

all_documents = data_post_processor.invoke(

                ^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/mnt/data8/liuhuan/dify-main/api/core/rag/data_post_processor/data_post_processor.py", line 37, in invoke

documents = self.rerank_runner.run(query, documents, score_threshold, top_n, user)

            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/mnt/data8/liuhuan/dify-main/api/core/rag/rerank/weight_rerank.py", line 49, in run

query_vector_scores = self._calculate_cosine(self.tenant_id, query, documents, self.weights.vector_setting)

                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/mnt/data8/liuhuan/dify-main/api/core/rag/rerank/weight_rerank.py", line 162, in _calculate_cosine

query_vector = cache_embedding.embed_query(query)

               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/mnt/data8/liuhuan/dify-main/api/core/rag/embedding/cached_embedding.py", line 118, in embed_query

raise ex

File "/mnt/data8/liuhuan/dify-main/api/core/rag/embedding/cached_embedding.py", line 113, in embed_query

embedding_results = embedding_result.embeddings[0]

                    ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^

IndexError: list index out of range