Closed sergej-d closed 7 months ago
🤖
Hello @sergej-d,
I'm Dosu, a bot here to assist while we wait for a human maintainer. I'm here to help you troubleshoot issues, answer questions, and guide you in contributing to the project. Let's work together to find a solution!
Based on the information you've provided and the similar issues I found in the LangChain repository, it seems like you want to prevent the ConversationalRetrievalChain
from returning sources for questions without sources.
To achieve this, you can set the return_source_documents
attribute to False
when initializing the ConversationalRetrievalChain
class. This attribute controls whether the retrieved source documents are returned as part of the final result. Here is an example of how to do this:
chain = ConversationalRetrievalChain(
combine_docs_chain=combine_docs_chain,
retriever=retriever,
question_generator=question_generator_chain,
return_source_documents=False, # Set this to False
)
This is supported by the following code in the BaseConversationalRetrievalChain
class:
return_source_documents: bool = False
"""Return the retrieved source documents as part of the final result."""
And in the _call
and _acall
methods, the source documents are only added to the output if return_source_documents
is True
:
if self.return_source_documents:
output["source_documents"] = docs
You can find this in the BaseConversationalRetrievalChain class definition.
Please note that the default value of the return_source_documents
attribute in the ConversationalRetrievalChain
class is False
. If you're still seeing sources returned, it might be due to some other part of your code overriding this default.
I hope this helps! If you have any other questions or need further clarification, feel free to ask.
Best, Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.
Help me be more useful! Please leave a đź‘Ť if this is helpful and đź‘Ž if it is irrelevant.
If you want to continue the conversation, start your reply with @dosu-bot.
My problem is that the ConversationalRetrievalChain returns sources for questions without context. So basically my documents have no information about the question, but the sources are returned anyway. @dosubot any idea how to fix this?
🤖
Based on the issues you've described, it seems you want LangChain to not specify a document name when the answer to a question is not found within the provided documents, or to label the source as "Generic" for such responses.
There are similar issues that have been solved in the LangChain repository. For instance, the issue titled Agent answer questions that is not related to my custom data and Issue: Not answering questions out of context using RetrievalQA Chain and ConversationalChatAgent provide solutions to similar problems.
To achieve this, you can modify the FINAL ANSWER
section of the template in the map_reduce_prompt.py
file. Currently, when the answer is not found, the SOURCES
section is left blank. You can modify this to return "Generic" instead. Here's how you can do it:
combine_prompt_template = """Given the following extracted parts of a long document and a question, create a final answer with references ("SOURCES").
If you don't know the answer, just say that you don't know. Don't try to make up an answer.
ALWAYS return a "SOURCES" part in your answer.
QUESTION: Which state/country's law governs the interpretation of the contract?
=========
Content: This Agreement is governed by English law and the parties submit to the exclusive jurisdiction of the English courts in relation to any dispute (contractual or non-contractual) concerning this Agreement save that either party may apply to any court for an injunction or other relief to protect its Intellectual Property Rights.
Source: 28-pl
Content: No Waiver. Failure or delay in exercising any right or remedy under this Agreement shall not constitute a waiver of such (or any other) right or remedy.\n\n11.7 Severability. The invalidity, illegality or unenforceability of any term (or part of a term) of this Agreement shall not affect the continuation in force of the remainder of the term (if any) and this Agreement.\n\n11.8 No Agency. Except as expressly stated otherwise, nothing in this Agreement shall create an agency, partnership or joint venture of any kind between the parties.\n\n11.9 No Third-Party Beneficiaries.
Source: 30-pl
Content: (b) if Google believes, in good faith, that the Distributor has violated or caused Google to violate any Anti-Bribery Laws (as defined in Clause 8.5) or that such a violation is reasonably likely to occur,
Source: 4-pl
=========
FINAL ANSWER: This Agreement is governed by English law.
SOURCES: 28-pl
QUESTION: What did the president say about Michael Jackson?
=========
Content: Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans. \n\nLast year COVID-19 kept us apart. This year we are finally together again. \n\nTonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \n\nWith a duty to one another to the American people to the Constitution. \n\nAnd with an unwavering resolve that freedom will always triumph over tyranny. \n\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \n\nHe thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \n\nHe met the Ukrainian people. \n\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. \n\nGroups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland.
Source: 0-pl
Content: And we won’t stop. \n\nWe have lost so much to COVID-19. Time with one another. And worst of all, so much loss of life. \n\nLet’s use this moment to reset. Let’s stop looking at COVID-19 as a partisan dividing line and see it for what it is: A God-awful disease. \n\nLet’s stop seeing each other as enemies, and start seeing each other for who we really are: Fellow Americans. \n\nWe can’t change how divided we’ve been. But we can change how we move forward—on COVID-19 and other issues we must face together. \n\nI recently visited the New York City Police Department days after the funerals of Officer Wilbert Mora and his partner, Officer Jason Rivera. \n\nThey were responding to a 9-1-1 call when a man shot and killed them with a stolen gun. \n\nOfficer Mora was 27 years old. \n\nOfficer Rivera was 22. \n\nBoth Dominican Americans who’d grown up on the same streets they later chose to patrol as police officers. \n\nI spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves.
Source: 24-pl
Content: And a proud Ukrainian people, who have known 30 years of independence, have repeatedly shown that they will not tolerate anyone who tries to take their country backwards. \n\nTo all Americans, I will be honest with you, as I’ve always promised. A Russian dictator, invading a foreign country, has costs around the world. \n\nAnd I’m taking robust action to make sure the pain of our sanctions is targeted at Russia’s economy. And I will use every tool at our disposal to protect American businesses and consumers. \n\nTonight, I can announce that the United States has worked with 30 other countries to release 60 Million barrels of oil from reserves around the world. \n\nAmerica will lead that effort, releasing 30 Million barrels from our own Strategic Petroleum Reserve. And we stand ready to do more if necessary, unified with our allies. \n\nThese steps will help blunt gas prices here at home. And I know the news about what’s happening can seem alarming. \n\nBut I want you to know that we are going to be okay.
Source: 5-pl
Content: More support for patients and families. \n\nTo get there, I call on Congress to fund ARPA-H, the Advanced Research Projects Agency for Health. \n\nIt’s based on DARPA—the Defense Department project that led to the Internet, GPS, and so much more. \n\nARPA-H will have a singular purpose—to drive breakthroughs in cancer, Alzheimer’s, diabetes, and more. \n\nA unity agenda for the nation. \n\nWe can do this. \n\nMy fellow Americans—tonight , we have gathered in a sacred space—the citadel of our democracy. \n\nIn this Capitol, generation after generation, Americans have debated great questions amid great strife, and have done great things. \n\nWe have fought for freedom, expanded liberty, defeated totalitarianism and terror. \n\nAnd built the strongest, freest, and most prosperous nation the world has ever known. \n\nNow is the hour. \n\nOur moment of responsibility. \n\nOur test of resolve and conscience, of history itself. \n\nIt is in this moment that our character is formed. Our purpose is found. Our future is forged. \n\nWell I know this nation.
Source: 34-pl
=========
FINAL ANSWER: The president did not mention Michael Jackson.
SOURCES: Generic
QUESTION: {question}
=========
{summaries}
=========
FINAL ANSWER:"""
COMBINE_PROMPT = PromptTemplate(
template=combine_prompt_template, input_variables=["summaries", "question"]
)
In this modified template, when the answer is not found, the SOURCES
section will return "Generic".
I hope this helps! If you have any other questions, feel free to ask.
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.
Help me be more useful! Please leave a đź‘Ť if this is helpful and đź‘Ž if it is irrelevant.
If you want to continue the conversation, start your reply with @dosu-bot.
@sergej-d you can use threshold for this https://python.langchain.com/docs/modules/data_connection/retrievers/vectorstore#similarity-score-threshold-retrieval
Hi, @sergej-d,
I'm helping the LangChain team manage their backlog and am marking this issue as stale. From what I understand, you were looking for a way to prevent the ConversationalRetrievalChain from returning sources for questions without context. Dosubot and Umair313 provided detailed responses and suggestions, ultimately leading to the resolution of setting the return_source_documents
attribute to False
when initializing the ConversationalRetrievalChain
class.
Could you please confirm if this issue is still relevant to the latest version of the LangChain repository? If it is, kindly let the LangChain team know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days. Thank you!
I have the same problem
Issue you'd like to raise.
Hi,
I am wondering if anyone has a work around using ConversationalRetrievalChain to retrieve documents with their sources, and prevent the chain from returning sources for questions without sources.
query = "How are you doing?" result = chain({"question": query, "chat_history": chat_history}) result['answer']
""" I'm doing well, thank you.
SOURCES: /content/xxx.pdf """
Suggestion:
SOURCES: