在下面的代码中,您可以看到我如何使用 Langchain with Memory 的 ParentDocumentRetriever 构建 RAG 模型。目前我正在使用带有默认 chain_type="stuff" 的 RetrievalQA-Chain。不过我想尝试不同的链类型,例如“map_reduce”。但是当替换 chain_type="map_reduce" 并创建检索 QA 链时,我收到以下错误:
ValidationError: 1 validation error for RefineDocumentsChain
prompt
extra fields not permitted (type=value_error.extra)
我假设我的提示未正确构建,但我该如何更改它才能使其正常工作?我看到“map_reduce”需要两个不同的提示:“map_prompt”和“combine_prompt”。但我不确定如何更改典型 RAG 检索任务的提示,用户可以与模型交互并要求模型为他回答问题。这是我的代码:
from langchain.chains import RetrievalQA
from langchain.memory import ConversationBufferMemory
from langchain.prompts import PromptTemplate
from langchain.callbacks.manager import CallbackManager
from langchain.document_loaders import PyPDFLoader, DirectoryLoader
loader = DirectoryLoader("MY_PATH_TO_PDF_FILES",
glob='*.pdf',
loader_cls=PyPDFLoader)
documents = loader.load()
# This text splitter is used to create the parent documents - The big chunks
parent_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=400)
# This text splitter is used to create the child documents - The small chunks
child_splitter = RecursiveCharacterTextSplitter(chunk_size=400)
# The vectorstore to use to index the child chunks
from chromadb.errors import InvalidDimensionException
try:
vectorstore = Chroma(collection_name="split_parents", embedding_function=bge_embeddings, persist_directory="chroma_db")
except InvalidDimensionException:
Chroma().delete_collection()
vectorstore = Chroma(collection_name="split_parents", embedding_function=bge_embeddings, persist_directory="chroma_db")
# The storage layer for the parent documents
store = InMemoryStore()
big_chunks_retriever = ParentDocumentRetriever(
vectorstore=vectorstore,
docstore=store,
child_splitter=child_splitter,
parent_splitter=parent_splitter,
)
big_chunks_retriever.add_documents(documents)
qa_template = """
Use the following information from the context (separated with <ctx></ctx>) to answer the question.
Answer in German only, because the user does not understand English! \
If you don't know the answer, answer with "Unfortunately, I don't have the information." \
If you don't find enough information below, also answer with "Unfortunately, I don't have the information." \
------
<ctx>
{context}
</ctx>
------
<hs>
{chat_history}
</hs>
------
{query}
Answer:
"""
prompt = PromptTemplate(template=qa_template,
input_variables=['context','history', 'question'])
chain_type_kwargs={
"verbose": True,
"prompt": prompt,
"memory": ConversationSummaryMemory(
llm=build_llm(),
memory_key="history",
input_key="question",
return_messages=True)}
refine = RetrievalQA.from_chain_type(llm=build_llm(),
chain_type="map_reduce",
return_source_documents=True,
chain_type_kwargs=chain_type_kwargs,
retriever=big_chunks_retriever,
verbose=True)
query = "Hi, I am Max, can you help me??"
refine(query)
你已经快找到答案了。 取决于你要做什么,让我们看下面的代码:
qa_template = """
Use the following information from the context (separated with <ctx></ctx>) to answer the question.
Answer in German only, because the user does not understand English! \
If you don't know the answer, answer with "Unfortunately, I don't have the information." \
If you don't find enough information below, also answer with "Unfortunately, I don't have the information." \
------
<ctx>
{context}
</ctx>
------
<hs>
{chat_history}
</hs>
------
{question}
Answer:
"""
prompt = PromptTemplate(template=qa_template,
input_variables=['context','history', 'question'])
combine_custom_prompt='''
Generate a summary of the following text that includes the following elements:
* A title that accurately reflects the content of the text.
* An introduction paragraph that provides an overview of the topic.
* Bullet points that list the key points of the text.
* A conclusion paragraph that summarizes the main points of the text.
Text:`{context}`
'''
combine_prompt_template = PromptTemplate(
template=combine_custom_prompt,
input_variables=['context']
)
chain_type_kwargs={
"verbose": True,
"question_prompt": prompt,
"combine_prompt": combine_prompt_template,
"combine_document_variable_name": "context",
"memory": ConversationSummaryMemory(
llm=OpenAI(),
memory_key="history",
input_key="question",
return_messages=True)}
refine = RetrievalQA.from_chain_type(llm=OpenAI(),
chain_type="map_reduce",
return_source_documents=True,
chain_type_kwargs=chain_type_kwargs,
retriever=big_chunks_retriever,
verbose=True)