diff --git a/examples/combine_docs.ipynb b/examples/combine_docs.ipynb index 3e6478f80..7cbf6994b 100644 --- a/examples/combine_docs.ipynb +++ b/examples/combine_docs.ipynb @@ -12,7 +12,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 11, "id": "624c452c-ddd5-4390-9065-7ec55dc64b96", "metadata": {}, "outputs": [], @@ -20,10 +20,14 @@ "from operator import itemgetter\n", "\n", "from langchain.chat_models.openai import ChatOpenAI\n", - "from langchain.prompts import SystemMessagePromptTemplate, ChatPromptTemplate, PromptTemplate\n", + "from langchain.prompts import (\n", + " SystemMessagePromptTemplate,\n", + " ChatPromptTemplate,\n", + " PromptTemplate,\n", + ")\n", "from langchain.schema.output_parser import StrOutputParser\n", "from langchain.runnables.openai_functions import OpenAIFunctionsRouter\n", - "from langchain.schema.runnable import RunnableMap\n", + "from langchain.schema.runnable import RunnableMap, RunnablePassthrough\n", "from langchain.schema.document import Document\n", "from langchain.schema import format_document\n", "\n", @@ -59,7 +63,9 @@ "source": [ "DEFAULT_DOCUMENT_PROMPT = PromptTemplate.from_template(template=\"{page_content}\")\n", "\n", - "_combine_documents = RunnableLambda(lambda x: format_document(x, DEFAULT_DOCUMENT_PROMPT)).map() | (lambda x: \"\\n\\n\".join(x))" + "_combine_documents = RunnableLambda(\n", + " lambda x: format_document(x, DEFAULT_DOCUMENT_PROMPT)\n", + ").map() | (lambda x: \"\\n\\n\".join(x))" ] }, { @@ -69,28 +75,40 @@ "metadata": {}, "outputs": [], "source": [ - "docs = [Document(page_content=\"Harrison used to work at Kensho\"), Document(page_content=\"Ankush worked at Facebook\")]" + "docs = [\n", + " Document(page_content=\"Harrison used to work at Kensho\"),\n", + " Document(page_content=\"Ankush worked at Facebook\"),\n", + "]" ] }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 5, "id": "17da58b7-8685-4d0a-9a47-c398c085d477", "metadata": {}, "outputs": [], "source": [ - "stuff_chain = {\n", - " \"question\": lambda x: x[\"question\"],\n", - " \"context\": (lambda x: x['docs']) | _combine_documents\n", - "} |ChatPromptTemplate.from_messages([\n", - " (\"system\", \"Answer user questions based on the following documents:\\n\\n{context}\"),\n", - " (\"human\", \"{question}\"),\n", - "]) | ChatOpenAI()" + "stuff_chain = (\n", + " {\n", + " \"question\": lambda x: x[\"question\"],\n", + " \"context\": (lambda x: x[\"docs\"]) | _combine_documents,\n", + " }\n", + " | ChatPromptTemplate.from_messages(\n", + " [\n", + " (\n", + " \"system\",\n", + " \"Answer user questions based on the following documents:\\n\\n{context}\",\n", + " ),\n", + " (\"human\", \"{question}\"),\n", + " ]\n", + " )\n", + " | ChatOpenAI()\n", + ")" ] }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 6, "id": "87295b71-0afc-4901-b57c-a7b945aa4bd9", "metadata": {}, "outputs": [ @@ -100,7 +118,7 @@ "AIMessage(content='Harrison used to work at Kensho.')" ] }, - "execution_count": 9, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -121,7 +139,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 7, "id": "b15f5abb-1cfe-4965-a021-c891506c5dd2", "metadata": {}, "outputs": [], @@ -131,7 +149,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 8, "id": "ccad04a3-fd3f-4e73-b895-29e53535f000", "metadata": {}, "outputs": [], @@ -156,7 +174,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 9, "id": "11cfd337-9f3b-4b26-ba30-251e17b18994", "metadata": {}, "outputs": [ @@ -175,7 +193,7 @@ " Document(page_content='Ankush worked at Facebook')]]" ] }, - "execution_count": 12, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -188,10 +206,23 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 10, "id": "8d524ba6-0939-4a5d-8db0-4fa1ef06eaeb", "metadata": {}, - "outputs": [], + "outputs": [ + { + "ename": "TypeError", + "evalue": "LastValue() takes no arguments", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[10], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m input_inbox \u001b[38;5;241m=\u001b[39m \u001b[43mchannels\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mLastValue\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;28;43mstr\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43minput_inbox\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2\u001b[0m reduce_inbox \u001b[38;5;241m=\u001b[39m channels\u001b[38;5;241m.\u001b[39mLastValue[\u001b[38;5;28mstr\u001b[39m](\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mreduce_inbox\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 3\u001b[0m collapse_inbox \u001b[38;5;241m=\u001b[39m channels\u001b[38;5;241m.\u001b[39mLastValue[\u001b[38;5;28mstr\u001b[39m](\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcollapse_inbox\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n", + "File \u001b[0;32m/opt/homebrew/Cellar/python@3.11/3.11.5/Frameworks/Python.framework/Versions/3.11/lib/python3.11/typing.py:1268\u001b[0m, in \u001b[0;36m_BaseGenericAlias.__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1265\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_inst:\n\u001b[1;32m 1266\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mType \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m cannot be instantiated; \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1267\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124muse \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m__origin__\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m() instead\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m-> 1268\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__origin__\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1269\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1270\u001b[0m result\u001b[38;5;241m.\u001b[39m__orig_class__ \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\n", + "\u001b[0;31mTypeError\u001b[0m: LastValue() takes no arguments" + ] + } + ], "source": [ "input_inbox = channels.LastValue[str](\"input_inbox\")\n", "reduce_inbox = channels.LastValue[str](\"reduce_inbox\")\n", @@ -208,25 +239,31 @@ "source": [ "# Decide if should finish or should reduce one more step\n", "def decide_end(plan):\n", - " if len(plan['docs']) > 1:\n", + " if len(plan[\"docs\"]) > 1:\n", " return Pregel.send_to(\"reduce_inbox\")\n", " else:\n", - " return {\"docs\": lambda x: x[\"docs\"][0], \"question\": lambda x: x[\"question\"]} | stuff_chain | Pregel.send_to(\"output_inbox\")\n", + " return stuff_chain | Pregel.send_to(\"output_inbox\")\n", + "\n", "\n", "# Chain that collapses documents then chooses end\n", - "collapse_chain = Pregel.subscribe_to(input=collapse_inbox) | RunnableMap({\n", - " \"docs\": lambda x: _split_list_of_docs(x[\"docs\"]),\n", - " \"question\": lambda x: x[\"question\"]\n", - "}) | decide_end\n", + "collapse_chain = (\n", + " Pregel.subscribe_to(docs=collapse_inbox, question=\"question\")\n", + " | RunnablePassthrough.assign(docs=lambda x: _split_list_of_docs(x[\"docs\"]))\n", + " | decide_end\n", + ")\n", "\n", "\n", "reduce_chain = (\n", " Pregel.subscribe_to(input=input_inbox)\n", - " | (lambda x: [{\"docs\": d, \"question\": x[\"question\"]} for d in x['docs']])\n", - " | stuff_chain.map() \n", - " | Pregel.send_to({\"collapse_inbox\": {\n", - " \"docs\": lambda x: [Document(page_content=m.content) for m in x],\n", - " }})\n", + " | (lambda x: [{\"docs\": d, \"question\": x[\"question\"]} for d in x[\"docs\"]])\n", + " | stuff_chain.map()\n", + " | Pregel.send_to(\n", + " {\n", + " \"collapse_inbox\": {\n", + " \"docs\": lambda x: [Document(page_content=m.content) for m in x],\n", + " }\n", + " }\n", + " )\n", ")" ] }, @@ -252,7 +289,9 @@ } ], "source": [ - "pubsub = Pregel(input_inbox, reduce_inbox, collapse_inbox, input=input_inbox, output=output_inbox)\n" + "pubsub = Pregel(\n", + " input_inbox, reduce_inbox, collapse_inbox, input=input_inbox, output=output_inbox\n", + ")" ] }, { @@ -301,7 +340,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.1" + "version": "3.11.5" } }, "nbformat": 4,