AttributeError: 'dict' object has no attribute 'replace'

[SaiSanthosh1508]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

loader = TextLoader("state_of_the_union.txt")
documents = loader.load()
print(documents[0].page_content)

text_splitter = RecursiveCharacterTextSplitter(chunk_size=500,chunk_overlap=50)
splits = text_splitter.split_documents(documents)


embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")

vectorstore = FAISS.from_documents(
    splits,
    embeddings
)

retriever = vectorstore.as_retriever()

template = """
            You are an assistant for question-answering tasks.
            If you don't know the answer,just say that you dont know.
            Use ten sentences maximum and keep the answer concise.
            Question: {question}
            Context: {context}
            Answer:
            """

prompt = ChatPromptTemplate.from_template(template)

rag_chain = (
    {"context":retriever,"question":RunnablePassthrough()}
    | prompt | llm | StrOutputParser()
)

rag_chain.invoke({"question":"What is the state of the union?"})

Description

`{
"name": "AttributeError",
"message": "'dict' object has no attribute 'replace'",
"stack": "---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
Cell In[67], line 1
----> 1 rag_chain.invoke({"question":"What is the state of the union?"})

File d:\Sunny-Savita\venv\Lib\site-packages\langchain_core\runnables\base.py:3022, in RunnableSequence.invoke(self, input, config, **kwargs)
3020 context.run(_set_config_context, config)
3021 if i == 0:
-> 3022 input = context.run(step.invoke, input, config, **kwargs)
3023 else:
3024 input = context.run(step.invoke, input, config)

File d:\Sunny-Savita\venv\Lib\site-packages\langchain_core\runnables\base.py:3727, in RunnableParallel.invoke(self, input, config, **kwargs)
3722 with get_executor_for_config(config) as executor:
3723 futures = [
3724 executor.submit(_invoke_step, step, input, config, key)
3725 for key, step in steps.items()
3726 ]
-> 3727 output = {key: future.result() for key, future in zip(steps, futures)}
3728 # finish the root run
3729 except BaseException as e:

File ~\AppData\Local\Programs\Python\Python312\Lib\concurrent\futures\_base.py:449, in Future.result(self, timeout)
447 raise CancelledError()
448 elif self._state == FINISHED:
--> 449 return self.__get_result()
451 self._condition.wait(timeout)
453 if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:

File ~\AppData\Local\Programs\Python\Python312\Lib\concurrent\futures\_base.py:401, in Future.__get_result(self)
399 if self._exception:
400 try:
--> 401 raise self._exception
402 finally:
403 # Break a reference cycle with the exception in self._exception
404 self = None

File ~\AppData\Local\Programs\Python\Python312\Lib\concurrent\futures\thread.py:58, in _WorkItem.run(self)
55 return
57 try:
---> 58 result = self.fn(*self.args, **self.kwargs)
59 except BaseException as exc:
60 self.future.set_exception(exc)

File d:\Sunny-Savita\venv\Lib\site-packages\langchain_core\runnables\base.py:3711, in RunnableParallel.invoke.._invoke_step(step, input, config, key)
3709 context = copy_context()
3710 context.run(_set_config_context, child_config)
-> 3711 return context.run(
3712 step.invoke,
3713 input,
3714 child_config,
3715 )

File d:\Sunny-Savita\venv\Lib\site-packages\langchain_core\retrievers.py:254, in BaseRetriever.invoke(self, input, config, **kwargs)
252 except Exception as e:
253 run_manager.on_retriever_error(e)
--> 254 raise e
255 else:
256 run_manager.on_retriever_end(
257 result,
258 )

File d:\Sunny-Savita\venv\Lib\site-packages\langchain_core\retrievers.py:247, in BaseRetriever.invoke(self, input, config, **kwargs)
245 _kwargs = kwargs if self._expects_other_args else {}
246 if self._new_arg_supported:
--> 247 result = self._get_relevant_documents(
248 input, run_manager=run_manager, **_kwargs
249 )
250 else:
251 result = self._get_relevant_documents(input, **_kwargs)

File d:\Sunny-Savita\venv\Lib\site-packages\langchain_core\vectorstores\base.py:1080, in VectorStoreRetriever._get_relevant_documents(self, query, run_manager)
1076 def _get_relevant_documents(
1077 self, query: str, *, run_manager: CallbackManagerForRetrieverRun
1078 ) -> list[Document]:
1079 if self.search_type == "similarity":
-> 1080 docs = self.vectorstore.similarity_search(query, **self.search_kwargs)
1081 elif self.search_type == "similarity_score_threshold":
1082 docs_and_similarities = (
1083 self.vectorstore.similarity_search_with_relevance_scores(
1084 query, **self.search_kwargs
1085 )
1086 )

File d:\Sunny-Savita\venv\Lib\site-packages\langchain_community\vectorstores\faiss.py:641, in FAISS.similarity_search(self, query, k, filter, fetch_k, **kwargs)
621 def similarity_search(
622 self,
623 query: str,
(...)
627 **kwargs: Any,
628 ) -> List[Document]:
629 """Return docs most similar to query.
630
631 Args:
(...)
639 List of Documents most similar to the query.
640 """
--> 641 docs_and_scores = self.similarity_search_with_score(
642 query, k, filter=filter, fetch_k=fetch_k, **kwargs
643 )
644 return [doc for doc, _ in docs_and_scores]

File d:\Sunny-Savita\venv\Lib\site-packages\langchain_community\vectorstores\faiss.py:513, in FAISS.similarity_search_with_score(self, query, k, filter, fetch_k, **kwargs)
489 def similarity_search_with_score(
490 self,
491 query: str,
(...)
495 **kwargs: Any,
496 ) -> List[Tuple[Document, float]]:
497 """Return docs most similar to query.
498
499 Args:
(...)
511 L2 distance in float. Lower score represents more similarity.
512 """
--> 513 embedding = self._embed_query(query)
514 docs = self.similarity_search_with_score_by_vector(
515 embedding,
516 k,
(...)
519 **kwargs,
520 )
521 return docs

File d:\Sunny-Savita\venv\Lib\site-packages\langchain_community\vectorstores\faiss.py:265, in FAISS._embed_query(self, text)
263 def _embed_query(self, text: str) -> List[float]:
264 if isinstance(self.embedding_function, Embeddings):
--> 265 return self.embedding_function.embed_query(text)
266 else:
267 return self.embedding_function(text)

File d:\Sunny-Savita\venv\Lib\site-packages\langchain_huggingface\embeddings\huggingface.py:108, in HuggingFaceEmbeddings.embed_query(self, text)
99 def embed_query(self, text: str) -> List[float]:
100 """Compute query embeddings using a HuggingFace transformer model.
101
102 Args:
(...)
106 Embeddings for the text.
107 """
--> 108 return self.embed_documents([text])[0]

File d:\Sunny-Savita\venv\Lib\site-packages\langchain_huggingface\embeddings\huggingface.py:79, in HuggingFaceEmbeddings.embed_documents(self, texts)
69 """Compute doc embeddings using a HuggingFace transformer model.
70
71 Args:
(...)
75 List of embeddings, one for each text.
76 """
77 import sentence_transformers # type: ignore[import]
---> 79 texts = list(map(lambda x: x.replace("
", " "), texts))
80 if self.multi_process:
81 pool = self._client.start_multi_process_pool()

File d:\Sunny-Savita\venv\Lib\site-packages\langchain_huggingface\embeddings\huggingface.py:79, in HuggingFaceEmbeddings.embed_documents..(x)
69 """Compute doc embeddings using a HuggingFace transformer model.
70
71 Args:
(...)
75 List of embeddings, one for each text.
76 """
77 import sentence_transformers # type: ignore[import]
---> 79 texts = list(map(lambda x: x.replace("
", " "), texts))
80 if self.multi_process:
81 pool = self._client.start_multi_process_pool()

AttributeError: 'dict' object has no attribute 'replace'"
}`

Im getting this issue,I've seen some youtube videos where the code was correctly executed,is there an issue with my code or with the langchain usage

System Info

Package Information

langchain_core: 0.3.15
langchain: 0.3.7
langchain_community: 0.3.5
langsmith: 0.1.142
langchain_chroma: 0.1.4
langchain_groq: 0.2.1
langchain_huggingface: 0.1.2
langchain_nvidia_ai_endpoints: 0.3.4
langchain_ollama: 0.2.0
langchain_openai: 0.2.6
langchain_text_splitters: 0.3.2
langserve: 0.3.0

[feijoes]

[SaiSanthosh1508]

i cant use split_text since loader.load() returns a list of documents

[feijoes]

@SaiSanthosh1508 Sorry, please disregard that.

As stated in the documentation, you could try using the load_and_split method.

loader = TextLoader("state_of_the_union.txt")
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500,chunk_overlap=50)
loader.load_and_split(text_splitter)