Type Error

TypeError                                 Traceback (most recent call last)
Cell In[17], line 10
      7     break
      9 #processed_query = embeddings_model.encode([query])
---> 10 result = qa({"question":query,"chat_history":chat_history})
     12 pattern = r'Helpful Answer:.*'
     13 match = re.search(pattern, result['answer'], re.DOTALL)

File D:\anaconda3\envs\gpt\Lib\site-packages\langchain\chains\base.py:310, in Chain.__call__(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)
    308 except BaseException as e:
    309     run_manager.on_chain_error(e)
--> 310     raise e
    311 run_manager.on_chain_end(outputs)
    312 final_outputs: Dict[str, Any] = self.prep_outputs(
    313     inputs, outputs, return_only_outputs
    314 )

File D:\anaconda3\envs\gpt\Lib\site-packages\langchain\chains\base.py:304, in Chain.__call__(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)
    297 run_manager = callback_manager.on_chain_start(
    298     dumpd(self),
    299     inputs,
    300     name=run_name,
    301 )
    302 try:
    303     outputs = (
--> 304         self._call(inputs, run_manager=run_manager)
    305         if new_arg_supported
    306         else self._call(inputs)
    307     )
    308 except BaseException as e:
    309     run_manager.on_chain_error(e)

File D:\anaconda3\envs\gpt\Lib\site-packages\langchain\chains\conversational_retrieval\base.py:148, in BaseConversationalRetrievalChain._call(self, inputs, run_manager)
    144 accepts_run_manager = (
    145     "run_manager" in inspect.signature(self._get_docs).parameters
    146 )
    147 if accepts_run_manager:
--> 148     docs = self._get_docs(new_question, inputs, run_manager=_run_manager)
    149 else:
    150     docs = self._get_docs(new_question, inputs)  # type: ignore[call-arg]

File D:\anaconda3\envs\gpt\Lib\site-packages\langchain\chains\conversational_retrieval\base.py:305, in ConversationalRetrievalChain._get_docs(self, question, inputs, run_manager)
    297 def _get_docs(
    298     self,
    299     question: str,
   (...)
    302     run_manager: CallbackManagerForChainRun,
    303 ) -> List[Document]:
    304     """Get docs."""
--> 305     docs = self.retriever.get_relevant_documents(
    306         question, callbacks=run_manager.get_child()
    307     )
    308     return self._reduce_tokens_below_limit(docs)

File D:\anaconda3\envs\gpt\Lib\site-packages\langchain\schema\retriever.py:211, in BaseRetriever.get_relevant_documents(self, query, callbacks, tags, metadata, run_name, **kwargs)
    209 except Exception as e:
    210     run_manager.on_retriever_error(e)
--> 211     raise e
    212 else:
    213     run_manager.on_retriever_end(
    214         result,
    215         **kwargs,
    216     )

File D:\anaconda3\envs\gpt\Lib\site-packages\langchain\schema\retriever.py:204, in BaseRetriever.get_relevant_documents(self, query, callbacks, tags, metadata, run_name, **kwargs)
    202 _kwargs = kwargs if self._expects_other_args else {}
    203 if self._new_arg_supported:
--> 204     result = self._get_relevant_documents(
    205         query, run_manager=run_manager, **_kwargs
    206     )
    207 else:
    208     result = self._get_relevant_documents(query, **_kwargs)

File D:\anaconda3\envs\gpt\Lib\site-packages\langchain\schema\vectorstore.py:656, in VectorStoreRetriever._get_relevant_documents(self, query, run_manager)
    652 def _get_relevant_documents(
    653     self, query: str, *, run_manager: CallbackManagerForRetrieverRun
    654 ) -> List[Document]:
    655     if self.search_type == "similarity":
--> 656         docs = self.vectorstore.similarity_search(query, **self.search_kwargs)
    657     elif self.search_type == "similarity_score_threshold":
    658         docs_and_similarities = (
    659             self.vectorstore.similarity_search_with_relevance_scores(
    660                 query, **self.search_kwargs
    661             )
    662         )

File D:\anaconda3\envs\gpt\Lib\site-packages\langchain\vectorstores\faiss.py:509, in FAISS.similarity_search(self, query, k, filter, fetch_k, **kwargs)
    489 def similarity_search(
    490     self,
    491     query: str,
   (...)
    495     **kwargs: Any,
    496 ) -> List[Document]:
    497     """Return docs most similar to query.
    498
    499     Args:
   (...)
    507         List of Documents most similar to the query.
    508     """
--> 509     docs_and_scores = self.similarity_search_with_score(
    510         query, k, filter=filter, fetch_k=fetch_k, **kwargs
    511     )
    512     return [doc for doc, _ in docs_and_scores]

File D:\anaconda3\envs\gpt\Lib\site-packages\langchain\vectorstores\faiss.py:390, in FAISS.similarity_search_with_score(self, query, k, filter, fetch_k, **kwargs)
    369 def similarity_search_with_score(
    370     self,
    371     query: str,
   (...)
    375     **kwargs: Any,
    376 ) -> List[Tuple[Document, float]]:
    377     """Return docs most similar to query.
    378
    379     Args:
   (...)
    388         L2 distance in float. Lower score represents more similarity.
    389     """
--> 390     embedding = self._embed_query(query)
    391     docs = self.similarity_search_with_score_by_vector(
    392         embedding,
    393         k,
   (...)
    396         **kwargs,
    397     )
    398     return docs

File D:\anaconda3\envs\gpt\Lib\site-packages\langchain\vectorstores\faiss.py:155, in FAISS._embed_query(self, text)
    153     return self.embedding_function.embed_query(text)
    154 else:
--> 155     return self.embedding_function(text)

File D:\anaconda3\envs\gpt\Lib\site-packages\torch\nn\modules\module.py:1518, in Module._wrapped_call_impl(self, *args, **kwargs)
   1516     return self._compiled_call_impl(*args, **kwargs)  # type: ignore[misc]
   1517 else:
-> 1518     return self._call_impl(*args, **kwargs)

File D:\anaconda3\envs\gpt\Lib\site-packages\torch\nn\modules\module.py:1527, in Module._call_impl(self, *args, **kwargs)
   1522 # If we don't have any hooks, we want to skip the rest of the logic in
   1523 # this function, and just call forward.
   1524 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks
   1525         or _global_backward_pre_hooks or _global_backward_hooks
   1526         or _global_forward_hooks or _global_forward_pre_hooks):
-> 1527     return forward_call(*args, **kwargs)
   1529 try:
   1530     result = None

File D:\anaconda3\envs\gpt\Lib\site-packages\torch\nn\modules\container.py:215, in Sequential.forward(self, input)
    213 def forward(self, input):
    214     for module in self:
--> 215         input = module(input)
    216     return input

File D:\anaconda3\envs\gpt\Lib\site-packages\torch\nn\modules\module.py:1518, in Module._wrapped_call_impl(self, *args, **kwargs)
   1516     return self._compiled_call_impl(*args, **kwargs)  # type: ignore[misc]
   1517 else:
-> 1518     return self._call_impl(*args, **kwargs)

File D:\anaconda3\envs\gpt\Lib\site-packages\torch\nn\modules\module.py:1527, in Module._call_impl(self, *args, **kwargs)
   1522 # If we don't have any hooks, we want to skip the rest of the logic in
   1523 # this function, and just call forward.
   1524 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks
   1525         or _global_backward_pre_hooks or _global_backward_hooks
   1526         or _global_forward_hooks or _global_forward_pre_hooks):
-> 1527     return forward_call(*args, **kwargs)
   1529 try:
   1530     result = None

File D:\anaconda3\envs\gpt\Lib\site-packages\sentence_transformers\models\Transformer.py:62, in Transformer.forward(self, features)
     60 def forward(self, features):
     61     """Returns token_embeddings, cls_token"""
---> 62     trans_features = {'input_ids': features['input_ids'], 'attention_mask': features['attention_mask']}
     63     if 'token_type_ids' in features:
     64         trans_features['token_type_ids'] = features['token_type_ids']

TypeError: string indices must be integers, not 'str'