conversational retrieval chain in lcel (#8532)

docs/extras/guides/expression_language/cookbook.ipynb

@@ -22,19 +22,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 10,
    "id": "466b65b3",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/harrisonchase/.pyenv/versions/3.9.1/envs/langchain/lib/python3.9/site-packages/deeplake/util/check_latest_version.py:32: UserWarning: A newer version of deeplake (3.6.14) is available. It's recommended that you update to the latest version using `pip install -U deeplake`.\n",
-      "  warnings.warn(\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain.prompts import ChatPromptTemplate\n",
     "from langchain.chat_models import ChatOpenAI"
@@ -42,7 +33,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 11,
    "id": "3c634ef0",
    "metadata": {},
    "outputs": [],
@@ -211,7 +202,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 12,
    "id": "f799664d",
    "metadata": {},
    "outputs": [],
@@ -356,7 +347,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 13,
    "id": "5d3d8ffe",
    "metadata": {},
    "outputs": [],
@@ -377,7 +368,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 14,
    "id": "33be32af",
    "metadata": {},
    "outputs": [],
@@ -389,7 +380,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 15,
    "id": "df3f3fa2",
    "metadata": {},
    "outputs": [],
@@ -401,7 +392,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 16,
    "id": "bfc47ec1",
    "metadata": {},
    "outputs": [],
@@ -416,7 +407,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 17,
    "id": "eae31755",
    "metadata": {},
    "outputs": [],
@@ -431,7 +422,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 18,
    "id": "f3040b0c",
    "metadata": {
     "scrolled": false
@@ -450,7 +441,7 @@
        "'Harrison worked at Kensho.'"
       ]
      },
-     "execution_count": 25,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -461,7 +452,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 19,
    "id": "e1d20c7c",
    "metadata": {},
    "outputs": [],
@@ -484,7 +475,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 20,
    "id": "7ee8b2d4",
    "metadata": {
     "scrolled": false
@@ -503,7 +494,7 @@
        "'Harrison ha lavorato a Kensho.'"
       ]
      },
-     "execution_count": 28,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -512,6 +503,170 @@
     "chain.invoke({\"question\": \"where did harrison work\", \"language\": \"italian\"})"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "f007669c",
+   "metadata": {},
+   "source": [
+    "## Conversational Retrieval Chain\n",
+    "\n",
+    "We can easily add in conversation history. This primarily means adding in chat_message_history"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "id": "3f30c348",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema.runnable import RunnableMap\n",
+    "from langchain.schema import format_document"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "64ab1dbf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts.prompt import PromptTemplate\n",
+    "\n",
+    "_template = \"\"\"Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, in its original language.\n",
+    "\n",
+    "Chat History:\n",
+    "{chat_history}\n",
+    "Follow Up Input: {question}\n",
+    "Standalone question:\"\"\"\n",
+    "CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "7d628c97",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Answer the question based only on the following context:\n",
+    "{context}\n",
+    "\n",
+    "Question: {question}\n",
+    "\"\"\"\n",
+    "ANSWER_PROMPT = ChatPromptTemplate.from_template(template)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "id": "f60a5d0f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DEFAULT_DOCUMENT_PROMPT = PromptTemplate.from_template(template=\"{page_content}\")\n",
+    "def _combine_documents(docs, document_prompt = DEFAULT_DOCUMENT_PROMPT, document_separator=\"\\n\\n\"):\n",
+    "    doc_strings = [format_document(doc, document_prompt) for doc in docs]\n",
+    "    return document_separator.join(doc_strings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "id": "7d007db6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Tuple, List\n",
+    "def _format_chat_history(chat_history: List[Tuple]) -> str:\n",
+    "    buffer = \"\"\n",
+    "    for dialogue_turn in chat_history:\n",
+    "        human = \"Human: \" + dialogue_turn[0]\n",
+    "        ai = \"Assistant: \" + dialogue_turn[1]\n",
+    "        buffer += \"\\n\" + \"\\n\".join([human, ai])\n",
+    "    return buffer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "id": "5c32cc89",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "conversational_qa_chain = RunnableMap({\n",
+    "    \"standalone_question\": {\n",
+    "        \"question\": lambda x: x[\"question\"],\n",
+    "        \"chat_history\": lambda x: _format_chat_history(x['chat_history'])\n",
+    "    } | CONDENSE_QUESTION_PROMPT | ChatOpenAI(temperature=0) | StrOutputParser(),\n",
+    "}) | {\n",
+    "    \"context\": itemgetter(\"standalone_question\") | retriever | _combine_documents,\n",
+    "    \"question\": lambda x: x[\"standalone_question\"]\n",
+    "} | ANSWER_PROMPT | ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "id": "135c8205",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Number of requested results 4 is greater than number of elements in index 1, updating n_results = 1\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 71,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversational_qa_chain.invoke({\n",
+    "    \"question\": \"where did harrison work?\",\n",
+    "    \"chat_history\": [],\n",
+    "})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "id": "424e7e7a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Number of requested results 4 is greater than number of elements in index 1, updating n_results = 1\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Harrison worked at Kensho.', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 62,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversational_qa_chain.invoke({\n",
+    "    \"question\": \"where did he work?\",\n",
+    "    \"chat_history\": [(\"Who wrote this notebook?\", \"Harrison\")],\n",
+    "})"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "0f2bf8d3",