Change RunnableMap to RunnableParallel for consistency (#14142)

- **Description:** Change instances of RunnableMap to RunnableParallel, as that should be the one used going forward. This makes it consistent across the codebase.
2025-08-08 04:25:46 +00:00 · 2023-12-01 13:36:40 -08:00 · 2023-12-01 13:36:40 -08:00 · 0caef3cde7
commit 0caef3cde7
parent 96f6b90349
13 changed files with 37 additions and 33 deletions
--- a/docs/docs/expression_language/cookbook/multiple_chains.ipynb
+++ b/docs/docs/expression_language/cookbook/multiple_chains.ipynb
@ -146,7 +146,7 @@
   "source": [
    "### Branching and Merging\n",
    "\n",
-    "You may want the output of one component to be processed by 2 or more other components. [RunnableMaps](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.base.RunnableMap.html) let you split or fork the chain so multiple components can process the input in parallel. Later, other components can join or merge the results to synthesize a final response. This type of chain creates a computation graph that looks like the following:\n",
+    "You may want the output of one component to be processed by 2 or more other components. [RunnableParallels](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableParallel.html#langchain_core.runnables.base.RunnableParallel) let you split or fork the chain so multiple components can process the input in parallel. Later, other components can join or merge the results to synthesize a final response. This type of chain creates a computation graph that looks like the following:\n",
    "\n",
    "```text\n",
    "     Input\n",
--- a/docs/docs/expression_language/cookbook/prompt_llm_parser.ipynb
+++ b/docs/docs/expression_language/cookbook/prompt_llm_parser.ipynb
@ -317,7 +317,7 @@
   "source": [
    "## Simplifying input\n",
    "\n",
-    "To make invocation even simpler, we can add a `RunnableMap` to take care of creating the prompt input dict for us:"
+    "To make invocation even simpler, we can add a `RunnableParallel` to take care of creating the prompt input dict for us:"
   ]
  },
  {
@ -327,9 +327,9 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "from langchain.schema.runnable import RunnableMap, RunnablePassthrough\n",
+    "from langchain.schema.runnable import RunnableParallel, RunnablePassthrough\n",
    "\n",
-    "map_ = RunnableMap(foo=RunnablePassthrough())\n",
+    "map_ = RunnableParallel(foo=RunnablePassthrough())\n",
    "chain = (\n",
    "    map_\n",
    "    | prompt\n",
--- a/docs/docs/expression_language/cookbook/retrieval.ipynb
+++ b/docs/docs/expression_language/cookbook/retrieval.ipynb
@ -171,7 +171,7 @@
   "outputs": [],
   "source": [
    "from langchain.schema import format_document\n",
-    "from langchain.schema.runnable import RunnableMap"
+    "from langchain.schema.runnable import RunnableParallel"
   ]
  },
  {
@ -256,7 +256,7 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "_inputs = RunnableMap(\n",
+    "_inputs = RunnableParallel(\n",
    "    standalone_question=RunnablePassthrough.assign(\n",
    "        chat_history=lambda x: _format_chat_history(x[\"chat_history\"])\n",
    "    )\n",
--- a/docs/docs/expression_language/how_to/map.ipynb
+++ b/docs/docs/expression_language/how_to/map.ipynb
@ -104,7 +104,7 @@
   "source": [
    "Here the input to prompt is expected to be a map with keys \"context\" and \"question\". The user input is just the question. So we need to get the context using our retriever and passthrough the user input under the \"question\" key.\n",
    "\n",
-    "Note that when composing a RunnableMap with another Runnable we don't even need to wrap our dictionary in the RunnableMap class — the type conversion is handled for us."
+    "Note that when composing a RunnableParallel with another Runnable we don't even need to wrap our dictionary in the RunnableParallel class — the type conversion is handled for us."
   ]
  },
  {
@ -114,7 +114,7 @@
   "source": [
    "## Parallelism\n",
    "\n",
-    "RunnableMaps are also useful for running independent processes in parallel, since each Runnable in the map is executed in parallel. For example, we can see our earlier `joke_chain`, `poem_chain` and `map_chain` all have about the same runtime, even though `map_chain` executes both of the other two."
+    "RunnableParallel are also useful for running independent processes in parallel, since each Runnable in the map is executed in parallel. For example, we can see our earlier `joke_chain`, `poem_chain` and `map_chain` all have about the same runtime, even though `map_chain` executes both of the other two."
   ]
  },
  {
--- a/docs/docs/expression_language/how_to/message_history.ipynb
+++ b/docs/docs/expression_language/how_to/message_history.ipynb
@ -290,9 +290,9 @@
   ],
   "source": [
    "from langchain.schema.messages import HumanMessage\n",
-    "from langchain.schema.runnable import RunnableMap\n",
+    "from langchain.schema.runnable import RunnableParallel\n",
    "\n",
-    "chain = RunnableMap({\"output_message\": ChatAnthropic(model=\"claude-2\")})\n",
+    "chain = RunnableParallel({\"output_message\": ChatAnthropic(model=\"claude-2\")})\n",
    "chain_with_history = RunnableWithMessageHistory(\n",
    "    chain,\n",
    "    lambda session_id: RedisChatMessageHistory(session_id, url=REDIS_URL),\n",
--- a/docs/docs/guides/privacy/presidio_data_anonymization/qa_privacy_protection.ipynb
+++ b/docs/docs/guides/privacy/presidio_data_anonymization/qa_privacy_protection.ipynb
@ -667,7 +667,11 @@
    "from langchain.chat_models.openai import ChatOpenAI\n",
    "from langchain.prompts import ChatPromptTemplate\n",
    "from langchain.schema.output_parser import StrOutputParser\n",
-    "from langchain.schema.runnable import RunnableLambda, RunnableMap, RunnablePassthrough\n",
+    "from langchain.schema.runnable import (\n",
+    "    RunnableLambda,\n",
+    "    RunnableParallel,\n",
+    "    RunnablePassthrough,\n",
+    ")\n",
    "\n",
    "# 6. Create anonymizer chain\n",
    "template = \"\"\"Answer the question based only on the following context:\n",
@ -680,7 +684,7 @@
    "model = ChatOpenAI(temperature=0.3)\n",
    "\n",
    "\n",
-    "_inputs = RunnableMap(\n",
+    "_inputs = RunnableParallel(\n",
    "    question=RunnablePassthrough(),\n",
    "    # It is important to remember about question anonymization\n",
    "    anonymized_question=RunnableLambda(anonymizer.anonymize),\n",
@ -882,7 +886,7 @@
    "\n",
    "\n",
    "chain_with_deanonymization = (\n",
-    "    RunnableMap({\"question\": RunnablePassthrough()})\n",
+    "    RunnableParallel({\"question\": RunnablePassthrough()})\n",
    "    | {\n",
    "        \"context\": itemgetter(\"question\")\n",
    "        | retriever\n",
--- a/docs/docs/use_cases/question_answering/index.ipynb
+++ b/docs/docs/use_cases/question_answering/index.ipynb
@ -846,7 +846,7 @@
   "source": [
    "from operator import itemgetter\n",
    "\n",
-    "from langchain.schema.runnable import RunnableMap\n",
+    "from langchain.schema.runnable import RunnableParallel\n",
    "\n",
    "rag_chain_from_docs = (\n",
    "    {\n",
@ -857,7 +857,7 @@
    "    | llm\n",
    "    | StrOutputParser()\n",
    ")\n",
-    "rag_chain_with_source = RunnableMap(\n",
+    "rag_chain_with_source = RunnableParallel(\n",
    "    {\"documents\": retriever, \"question\": RunnablePassthrough()}\n",
    ") | {\n",
    "    \"documents\": lambda input: [doc.metadata for doc in input[\"documents\"]],\n",
--- a/templates/anthropic-iterative-search/anthropic_iterative_search/retriever_agent.py
+++ b/templates/anthropic-iterative-search/anthropic_iterative_search/retriever_agent.py
@ -2,7 +2,7 @@ from langchain.agents import AgentExecutor
 from langchain.chat_models import ChatAnthropic
 from langchain.prompts import ChatPromptTemplate
 from langchain.schema.output_parser import StrOutputParser
-from langchain.schema.runnable import RunnableMap, RunnablePassthrough
+from langchain.schema.runnable import RunnableParallel, RunnablePassthrough

 from .agent_scratchpad import format_agent_scratchpad
 from .output_parser import parse_output
@ -29,7 +29,7 @@ chain = (
 )

 agent_chain = (
-    RunnableMap(
+    RunnableParallel(
        {
            "partial_completion": chain,
            "intermediate_steps": lambda x: x["intermediate_steps"],
--- a/templates/rag-conversation-zep/rag_conversation_zep/chain.py
+++ b/templates/rag-conversation-zep/rag_conversation_zep/chain.py
@ -14,7 +14,7 @@ from langchain.schema.runnable import (
    ConfigurableField,
    RunnableBranch,
    RunnableLambda,
-    RunnableMap,
+    RunnableParallel,
    RunnablePassthrough,
 )
 from langchain.schema.runnable.utils import ConfigurableFieldSingleOption
@ -133,7 +133,7 @@ class ChatHistory(BaseModel):
    question: str


-_inputs = RunnableMap(
+_inputs = RunnableParallel(
    {
        "question": lambda x: x["question"],
        "chat_history": lambda x: _format_chat_history(x["chat_history"]),
--- a/templates/rag-conversation/rag_conversation/chain.py
+++ b/templates/rag-conversation/rag_conversation/chain.py
@ -11,7 +11,7 @@ from langchain.schema.output_parser import StrOutputParser
 from langchain.schema.runnable import (
    RunnableBranch,
    RunnableLambda,
-    RunnableMap,
+    RunnableParallel,
    RunnablePassthrough,
 )
 from langchain.vectorstores import Pinecone
@ -108,7 +108,7 @@ _search_query = RunnableBranch(
    RunnableLambda(itemgetter("question")),
 )

-_inputs = RunnableMap(
+_inputs = RunnableParallel(
    {
        "question": lambda x: x["question"],
        "chat_history": lambda x: _format_chat_history(x["chat_history"]),
--- a/templates/rag-elasticsearch/rag_elasticsearch/chain.py
+++ b/templates/rag-elasticsearch/rag_elasticsearch/chain.py
@ -5,7 +5,7 @@ from langchain.chat_models import ChatOpenAI
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.schema import BaseMessage, format_document
 from langchain.schema.output_parser import StrOutputParser
-from langchain.schema.runnable import RunnableMap, RunnablePassthrough
+from langchain.schema.runnable import RunnableParallel, RunnablePassthrough
 from langchain.vectorstores.elasticsearch import ElasticsearchStore
 from pydantic import BaseModel, Field

@ -49,7 +49,7 @@ class ChainInput(BaseModel):
    question: str = Field(..., description="The question to answer.")


-_inputs = RunnableMap(
+_inputs = RunnableParallel(
    standalone_question=RunnablePassthrough.assign(
        chat_history=lambda x: _format_chat_history(x["chat_history"])
    )
--- a/templates/rag-google-cloud-sensitive-data-protection/rag_google_cloud_sensitive_data_protection/chain.py
+++ b/templates/rag-google-cloud-sensitive-data-protection/rag_google_cloud_sensitive_data_protection/chain.py
@ -7,7 +7,7 @@ from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langchain.pydantic_v1 import BaseModel, Field
 from langchain.schema.messages import AIMessage, HumanMessage
 from langchain.schema.output_parser import StrOutputParser
-from langchain.schema.runnable import RunnableLambda, RunnableMap
+from langchain.schema.runnable import RunnableLambda, RunnableParallel


 # Formatting for chat history
@ -96,7 +96,7 @@ class ChatHistory(BaseModel):
    chat_history: List[Tuple[str, str]] = Field(..., extra={"widget": {"type": "chat"}})


-_inputs = RunnableMap(
+_inputs = RunnableParallel(
    {
        "question": RunnableLambda(
            lambda x: _deidentify_with_replace(
--- a/templates/rag-timescale-conversation/rag_timescale_conversation/chain.py
+++ b/templates/rag-timescale-conversation/rag_timescale_conversation/chain.py
@ -13,7 +13,7 @@ from langchain.schema.output_parser import StrOutputParser
 from langchain.schema.runnable import (
    RunnableBranch,
    RunnableLambda,
-    RunnableMap,
+    RunnableParallel,
    RunnablePassthrough,
 )
 from langchain.vectorstores.timescalevector import TimescaleVector
@ -136,7 +136,7 @@ def get_retriever_with_metadata(x):

 _retriever = RunnableLambda(get_retriever_with_metadata)

-_inputs = RunnableMap(
+_inputs = RunnableParallel(
    {
        "question": lambda x: x["question"],
        "chat_history": lambda x: _format_chat_history(x["chat_history"]),