return source documents for chat vector db chain (#1128)

docs/modules/chains/combine_docs_examples/chat_vector_db.ipynb

@@ -214,6 +214,58 @@
     "result['answer']"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "0eaadf0f",
+   "metadata": {},
+   "source": [
+    "## Return Source Documents\n",
+    "You can also easily return source documents from the ChatVectorDBChain. This is useful for when you want to inspect what documents were returned."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "562769c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "qa = ChatVectorDBChain.from_llm(OpenAI(temperature=0), vectorstore, return_source_documents=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "ea478300",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat_history = []\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "4cb75b4e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \\n\\nWe cannot let this happen. \\n\\nTonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result['source_documents'][0]"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "7fb44daa",

langchain/chains/chat_vector_db/base.py

@@ -31,6 +31,8 @@ class ChatVectorDBChain(Chain, BaseModel):
     combine_docs_chain: BaseCombineDocumentsChain
     question_generator: LLMChain
     output_key: str = "answer"
+    return_source_documents: bool = False
+    """Return the source documents."""
 
     @property
     def _chain_type(self) -> str:
@@ -43,8 +45,14 @@ class ChatVectorDBChain(Chain, BaseModel):
 
     @property
     def output_keys(self) -> List[str]:
-        """Output keys."""
-        return [self.output_key]
+        """Return the output keys.
+
+        :meta private:
+        """
+        _output_keys = [self.output_key]
+        if self.return_source_documents:
+            _output_keys = _output_keys + ["source_documents"]
+        return _output_keys
 
     @classmethod
     def from_llm(
@@ -54,6 +62,7 @@ class ChatVectorDBChain(Chain, BaseModel):
         condense_question_prompt: BasePromptTemplate = CONDENSE_QUESTION_PROMPT,
         qa_prompt: BasePromptTemplate = QA_PROMPT,
         chain_type: str = "stuff",
+        **kwargs: Any,
     ) -> ChatVectorDBChain:
         """Load chain from LLM."""
         doc_chain = load_qa_chain(
@@ -66,9 +75,10 @@ class ChatVectorDBChain(Chain, BaseModel):
             vectorstore=vectorstore,
             combine_docs_chain=doc_chain,
             question_generator=condense_question_chain,
+            **kwargs,
         )
 
-    def _call(self, inputs: Dict[str, Any]) -> Dict[str, str]:
+    def _call(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
         question = inputs["question"]
         chat_history_str = _get_chat_history(inputs["chat_history"])
         if chat_history_str:
@@ -82,7 +92,10 @@ class ChatVectorDBChain(Chain, BaseModel):
         new_inputs["question"] = new_question
         new_inputs["chat_history"] = chat_history_str
         answer, _ = self.combine_docs_chain.combine_docs(docs, **new_inputs)
-        return {self.output_key: answer}
+        if self.return_source_documents:
+            return {self.output_key: answer, "source_documents": docs}
+        else:
+            return {self.output_key: answer}
 
     async def _acall(self, inputs: Dict[str, Any]) -> Dict[str, str]:
         question = inputs["question"]