Getting "TypeError: 'HuggingFaceEmbeddings' object is not callable"

Search, No Filter
, , ,
1

TypeError: ‘HuggingFaceEmbeddings’ object is not callable

I have written bellow code and getting error given above.

As per best of my understanding what i have done is:

  • The download_hugging_face_embedding() function creates an instance of the HuggingFaceEmbeddings class with the specified model name ("sentence-transformers/all-MiniLM-L6-v2" ).
  • The embedding variable is assigned the result of calling download_hugging_face_embedding() , which is the HuggingFaceEmbeddings instance.
  • The PineconeStore is created using the embedding instance, and the text_key parameter is set to "text" .
  • The RetrievalQA chain is created using the PineconeStore 's as_retriever() method, with the search_kwargs parameter set to {'k': 2} .
  • passing the input to the qa object, and prints the result.
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")

PROMPT=PromptTemplate(template=prompt_template, input_variables=["context", "question"])
chain_type_kwargs={"prompt": PROMPT}

llm = None
path_to_model = r'C:\Users\Naruto\Desktop\generative_ai\generative_ai_material\project\Medical_Chat_Bot\model\llama-2-7b-chat.ggmlv3.q4_0.bin'
llm = CTransformers(
    model=path_to_model,
    model_type='llama',
    config={'max_new_tokens':552,
            'temperature':0.8}
    )

vectordb = PineconeStore(index, embedding, text_key="text")
qa=RetrievalQA.from_chain_type(
    llm=llm, 
    chain_type="stuff", 
    retriever=vectordb.as_retriever(search_kwargs={'k': 2}),
    return_source_documents=True, 
    chain_type_kwargs=chain_type_kwargs)

result=qa({"query": question})

FULL ERROR:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[66], line 1
----> 1 result=qa({"query": question})

File c:\Users\Naruto\Desktop\generative_ai\generative_ai_material\project\Medical_Chat_Bot\mcbvenv\lib\site-packages\langchain\chains\base.py:181, in Chain.__call__(self, inputs, return_only_outputs, callbacks, tags, metadata, include_run_info)
    179 except (KeyboardInterrupt, Exception) as e:
    180     run_manager.on_chain_error(e)
--> 181     raise e
    182 run_manager.on_chain_end(outputs)
    183 final_outputs: Dict[str, Any] = self.prep_outputs(
    184     inputs, outputs, return_only_outputs
    185 )

File c:\Users\Naruto\Desktop\generative_ai\generative_ai_material\project\Medical_Chat_Bot\mcbvenv\lib\site-packages\langchain\chains\base.py:175, in Chain.__call__(self, inputs, return_only_outputs, callbacks, tags, metadata, include_run_info)
    169 run_manager = callback_manager.on_chain_start(
    170     dumpd(self),
    171     inputs,
    172 )
    173 try:
    174     outputs = (
--> 175         self._call(inputs, run_manager=run_manager)
    176         if new_arg_supported
    177         else self._call(inputs)
    178     )
...
   (...)
    125     filter=filter,
    126 )

TypeError: 'HuggingFaceEmbeddings' object is not callable
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...

if I am doing result=qa.run({"query": question}) also not working. ERROR as bellow

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[71], line 1
----> 1 result=qa.run({"query": question})

File c:\Users\Naruto\Desktop\generative_ai\generative_ai_material\project\Medical_Chat_Bot\mcbvenv\lib\site-packages\langchain\chains\base.py:310, in Chain.run(self, callbacks, tags, metadata, *args, **kwargs)
    308 """Run the chain as text in, text out or multiple variables, text out."""
    309 # Run at start to make sure this is possible/defined
--> 310 _output_key = self._run_output_key
    312 if args and not kwargs:
    313     if len(args) != 1:

File c:\Users\Naruto\Desktop\generative_ai\generative_ai_material\project\Medical_Chat_Bot\mcbvenv\lib\site-packages\langchain\chains\base.py:294, in Chain._run_output_key(self)
    291 @property
    292 def _run_output_key(self) -> str:
    293     if len(self.output_keys) != 1:
--> 294         raise ValueError(
    295             f"`run` not supported when there is not exactly "
    296             f"one output key. Got {self.output_keys}."
    297         )
    298     return self.output_keys[0]

ValueError: `run` not supported when there is not exactly one output key. Got ['result', 'source_documents'].
2

Hi @mishraatharva, and thank you for your question.

It looks like you’re trying to call the HuggingFaceEmbeddings object like it’s a function, whereas it’s actually an object.

The correct usage is detailed here:

embedding = HuggingFaceEmbeddings()
embedded_data = embedding.embed_documents(["Some text"])

Hope that helps!

Best,
Zack