[Question]: I want to make sure that the chatbot uses the retriever only when the question is related to ingested documents.

[SiddharthMurjani]

Question Validation

• I have searched both the documentation and discord for an answer.

Question

I have this code here that goes to the vector db for every user_query to provide an answer.

chat_engine = vector_index.as_chat_engine(
        chat_mode=ChatMode.CONTEXT,
        memory=memory,
        chat_store=chat_store,
        verbose=True
    )

    response = chat_engine.chat(user_query)

Here, if the user_query is "HI" or "thankyou!" the chat_engine still goes through the RAG process to provide an answer.
Can we do something to make sure that the chat_engine uses the knowledge base only when the user_query is related to it?

[dosubot]

To ensure that the chatbot uses the retriever only when the question is related to ingested documents, you can implement a check within the _generate_context and _agenerate_context methods of the ContextChatEngine class. This check can determine if the query is related to the ingested documents before proceeding with the retrieval process.

Here is an example of how you might modify the _generate_context and _agenerate_context methods to include such a check:

class ContextChatEngine(BaseChatEngine):
    # ... other methods ...

    def _generate_context(self, message: str) -> Tuple[str, List[NodeWithScore]]:
        """Generate context information from a message."""
        if not self._is_related_to_ingested_documents(message):
            return "The question is not related to the ingested documents.", []

        nodes = self._retriever.retrieve(message)
        for postprocessor in self._node_postprocessors:
            nodes = postprocessor.postprocess_nodes(
                nodes, query_bundle=QueryBundle(message)
            )

        context_str = "\n\n".join(
            [n.node.get_content(metadata_mode=MetadataMode.LLM).strip() for n in nodes]
        )

        return self._context_template.format(context_str=context_str), nodes

    async def _agenerate_context(self, message: str) -> Tuple[str, List[NodeWithScore]]:
        """Generate context information from a message."""
        if not self._is_related_to_ingested_documents(message):
            return "The question is not related to the ingested documents.", []

        nodes = await self._retriever.aretrieve(message)
        for postprocessor in self._node_postprocessors:
            nodes = postprocessor.postprocess_nodes(
                nodes, query_bundle=QueryBundle(message)
            )
        context_str = "\n\n".join(
            [n.node.get_content(metadata_mode=MetadataMode.LLM).strip() for n in nodes]
        )

        return self._context_template.format(context_str=context_str), nodes

    def _is_related_to_ingested_documents(self, query_str: str) -> bool:
        # Implement your logic to determine if the query is related to ingested documents
        # For example, you could check for specific keywords or use a more complex NLP model
        return True  # Placeholder implementation

In this example, the _is_related_to_ingested_documents method should contain the logic to determine if the query is related to the ingested documents. This could be a simple keyword check or a more sophisticated natural language processing (NLP) model. If the query is not related, the method returns a message indicating that the question is not related to the ingested documents ^[1][2][3].

To continue talking to Dosu, mention @dosu.