我正在尝试使用拆分、索引并存储在磁盘上的Chroma中持久化的PDF产品手册创建RAG。当我尝试使用文档上下文对评论进行分类的函数时，出现了以下错误：

from langchain import PromptTemplatefrom langchain_core.output_parsers import StrOutputParserfrom langchain_core.runnables import RunnablePassthroughfrom langchain.embeddings import AzureOpenAIEmbeddingsfrom langchain.chat_models import AzureChatOpenAIfrom langchain.vectorstores import Chromallm = AzureChatOpenAI(        azure_deployment="ChatGPT-16K",        openai_api_version="2023-05-15",        azure_endpoint=endpoint,        api_key=result["access_token"],        temperature=0,        seed = 100    )embedding_model = AzureOpenAIEmbeddings(    api_version="2023-05-15",    azure_endpoint=endpoint,    api_key=result["access_token"],    azure_deployment="ada002",)vectordb = Chroma(    persist_directory=vector_db_path,    embedding_function=embedding_model,    collection_name="product_manuals",)def format_docs(docs):    return "\n\n".join(doc.page_content for doc in docs)def classify (review_title, review_text, product_num):    template = """            You are a customer service AI Assistant that handles responses to negative product reviews.        Use the context below and categorize {review_title} and {review_text} into defect, misuse or poor quality categories based only on provided context. If you don't know, say that you do not know, don't try to make up an answer. Respond back with an answer in the following format:        poor quality        misuse        defect        {context}                Category:     """    rag_prompt = PromptTemplate.from_template(template)        retriever = vectordb.as_retriever(search_type="similarity", search_kwargs={'filter': {'product_num': product_num}})    retrieval_chain = (            {"context": retriever | format_docs, "review_title: RunnablePassthrough(), "review_text": RunnablePassthrough()}            | rag_prompt            | llm            | StrOutputParser()    )    return retrieval_chain.invoke({"review_title": review_title, "review_text": review_text})classify(review_title="Terrible", review_text ="This baking sheet is terrible. It stains so easily and i've tried everything to get it clean", product_num ="8888999")

错误堆栈：

---------------------------------------------------------------------------TypeError                                 Traceback (most recent call last)File <command-3066972537097411>, line 1----> 1 issue_recommendation(      2     review_title="Terrible",      3     review_text="This baking sheet is terrible. It stains so easily and i've tried everything to get it clean. I've maybe used it 5 times and it looks like it's 20 years old. The side of the pan also hold water, so when you pick it up off the drying rack, water runs out. I would never purchase these again.",      4     product_num="8888999"      5          6 )File <command-3066972537097410>, line 44, in issue_recommendation(review_title, review_text, product_num)     36 retriever = vectordb.as_retriever(search_type="similarity", search_kwargs={'filter': {'product_num': product_num}})     38 retrieval_chain = (     39         {"context": retriever | format_docs, "review_text": RunnablePassthrough()}     40         | rag_prompt     41         | llm     42         | StrOutputParser()     43 )---> 44 return retrieval_chain.invoke({"review_title":review_title, "review_text": review_text})File /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_core/runnables/base.py:1762, in RunnableSequence.invoke(self, input, config)   1760 try:   1761     for i, step in enumerate(self.steps):-> 1762         input = step.invoke(   1763             input,   1764             # mark each step as a child run   1765             patch_config(   1766                 config, callbacks=run_manager.get_child(f"seq:step:{i+1}")   1767             ),   1768         )   1769 # finish the root run   1770 except BaseException as e:File /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_core/runnables/base.py:2327, in RunnableParallel.invoke(self, input, config)   2314     with get_executor_for_config(config) as executor:   2315         futures = [   2316             executor.submit(   (...)   2325             for key, step in steps.items()   2326         ]-> 2327         output = {key: future.result() for key, future in zip(steps, futures)}   2328 # finish the root run   2329 except BaseException as e:File /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_core/runnables/base.py:2327, in <dictcomp>(.0)   2314     with get_executor_for_config(config) as executor:   2315         futures = [   2316             executor.submit(   (...)   2325             for key, step in steps.items()   2326         ]-> 2327         output = {key: future.result() for key, future in zip(steps, futures)}   2328 # finish the root run   2329 except BaseException as e:File /usr/lib/python3.10/concurrent/futures/_base.py:451, in Future.result(self, timeout)    449     raise CancelledError()    450 elif self._state == FINISHED:--> 451     return self.__get_result()    453 self._condition.wait(timeout)    455 if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:File /usr/lib/python3.10/concurrent/futures/_base.py:403, in Future.__get_result(self)    401 if self._exception:    402     try:--> 403         raise self._exception    404     finally:    405         # Break a reference cycle with the exception in self._exception    406         self = NoneFile /usr/lib/python3.10/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 /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_core/runnables/base.py:1762, in RunnableSequence.invoke(self, input, config)   1760 try:   1761     for i, step in enumerate(self.steps):-> 1762         input = step.invoke(   1763             input,   1764             # mark each step as a child run   1765             patch_config(   1766                 config, callbacks=run_manager.get_child(f"seq:step:{i+1}")   1767             ),   1768         )   1769 # finish the root run   1770 except BaseException as e:File /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_core/retrievers.py:121, in BaseRetriever.invoke(self, input, config)    117 def invoke(    118     self, input: str, config: Optional[RunnableConfig] = None    119 ) -> List[Document]:    120     config = ensure_config(config)--> 121     return self.get_relevant_documents(    122         input,    123         callbacks=config.get("callbacks"),    124         tags=config.get("tags"),    125         metadata=config.get("metadata"),    126         run_name=config.get("run_name"),    127     )File /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_core/retrievers.py:223, in BaseRetriever.get_relevant_documents(self, query, callbacks, tags, metadata, run_name, **kwargs)    221 except Exception as e:    222     run_manager.on_retriever_error(e)--> 223     raise e    224 else:    225     run_manager.on_retriever_end(    226         result,    227         **kwargs,    228     )File /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_core/retrievers.py:216, in BaseRetriever.get_relevant_documents(self, query, callbacks, tags, metadata, run_name, **kwargs)    214 _kwargs = kwargs if self._expects_other_args else {}    215 if self._new_arg_supported:--> 216     result = self._get_relevant_documents(    217         query, run_manager=run_manager, **_kwargs    218     )    219 else:    220     result = self._get_relevant_documents(query, **_kwargs)File /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_core/vectorstores.py:654, in VectorStoreRetriever._get_relevant_documents(self, query, run_manager)    650 def _get_relevant_documents(    651     self, query: str, *, run_manager: CallbackManagerForRetrieverRun    652 ) -> List[Document]:    653     if self.search_type == "similarity":--> 654         docs = self.vectorstore.similarity_search(query, **self.search_kwargs)    655     elif self.search_type == "similarity_score_threshold":    656         docs_and_similarities = (    657             self.vectorstore.similarity_search_with_relevance_scores(    658                 query, **self.search_kwargs    659             )    660         )File /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_community/vectorstores/chroma.py:348, in Chroma.similarity_search(self, query, k, filter, **kwargs)    331 def similarity_search(    332     self,    333     query: str,   (...)    336     **kwargs: Any,    337 ) -> List[Document]:    338     """Run similarity search with Chroma.    339     340     Args:   (...)    346         List[Document]: List of documents most similar to the query text.    347     """--> 348     docs_and_scores = self.similarity_search_with_score(    349         query, k, filter=filter, **kwargs    350     )    351     return [doc for doc, _ in docs_and_scores]File /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_community/vectorstores/chroma.py:437, in Chroma.similarity_search_with_score(self, query, k, filter, where_document, **kwargs)    429     results = self.__query_collection(    430         query_texts=[query],    431         n_results=k,   (...)    434         **kwargs,    435     )    436 else:--> 437     query_embedding = self._embedding_function.embed_query(query)    438     results = self.__query_collection(    439         query_embeddings=[query_embedding],    440         n_results=k,   (...)    443         **kwargs,    444     )    446 return _results_to_docs_and_scores(results)File /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_community/embeddings/openai.py:691, in OpenAIEmbeddings.embed_query(self, text)    682 def embed_query(self, text: str) -> List[float]:    683     """Call out to OpenAI's embedding endpoint for embedding query text.    684     685     Args:   (...)    689         Embedding for the text.    690     """--> 691     return self.embed_documents([text])[0]File /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_community/embeddings/openai.py:662, in OpenAIEmbeddings.embed_documents(self, texts, chunk_size)    659 # NOTE: to keep things simple, we assume the list may contain texts longer    660 #       than the maximum context and use length-safe embedding function.    661 engine = cast(str, self.deployment)--> 662 return self._get_len_safe_embeddings(texts, engine=engine)File /local_disk0/.ephemeral_nfs/envs/pythonEnv-65a09d8c-062d-4f4f-9c52-1bf534f6511e/lib/python3.10/site-packages/langchain_community/embeddings/openai.py:465, in OpenAIEmbeddings._get_len_safe_embeddings(self, texts, engine, chunk_size)    459 if self.model.endswith("001"):    460     # See: https://github.com/openai/openai-python/    461     #      issues/418#issuecomment-1525939500    462     # replace newlines, which can negatively affect performance.    463     text = text.replace("\n", " ")--> 465 token = encoding.encode(    466     text=text,    467     allowed_special=self.allowed_special,    468     disallowed_special=self.disallowed_special,    469 )    471 # Split tokens into chunks respecting the embedding_ctx_length    472 for j in range(0, len(token), self.embedding_ctx_length):File /databricks/python/lib/python3.10/site-packages/tiktoken/core.py:116, in Encoding.encode(self, text, allowed_special, disallowed_special)    114     if not isinstance(disallowed_special, frozenset):    115         disallowed_special = frozenset(disallowed_special)--> 116     if match := _special_token_regex(disallowed_special).search(text):    117         raise_disallowed_special_token(match.group())    119 try:TypeError: 预期字符串或缓冲区

在测试时，嵌入似乎工作正常。当我从链中移除上下文和检索器时，它也正常工作。这似乎与嵌入有关。Langchain 网站上的示例是从Chroma.from_documents()实例化检索器，而我是从持久化路径加载Chroma向量存储。我还尝试仅使用review_text（而不是review title和review text）调用，但错误仍然存在。不确定为什么会发生这种情况。这些是我使用的包版本：

名称：openai版本：1.6.1

名称：langchain版本：0.0.354

回答：

我遇到了同样的问题，发现langchain将键值对作为输入传递给encoding.code()，而它需要str类型。一个解决方法是使用itemgetter()来获取直接的字符串输入。可能类似于这样

        retrieval_chain = (            {                "document": itemgetter("question") | self.retriever,                "question": itemgetter("question"),            }            | prompt            | model            | StrOutputParser()        )

你可以在这里找到参考这里