mirror of
https://github.com/langchain-ai/langgraph.git
synced 2026-08-24 16:42:24 +02:00
Nuno Campos
7f76fbb699
- Topic channel combines the features of Inbox, Archive, UniqueInbox, UniqueArchive, which have been removed.
372 lines
12 KiB
Plaintext
372 lines
12 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "780c1001-557c-4b03-8ebd-a2a381d5f85d",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Combine Docs\n",
|
|
"\n",
|
|
"PermChain is a great choice for implementating workflows that involve operating over longer documents because of its recursive nature"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "624c452c-ddd5-4390-9065-7ec55dc64b96",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.chat_models.openai import ChatOpenAI\n",
|
|
"from langchain.prompts import ChatPromptTemplate, PromptTemplate\n",
|
|
"from langchain.schema.output_parser import StrOutputParser\n",
|
|
"from langchain.schema.runnable import Runnable, RunnablePassthrough\n",
|
|
"from langchain.schema.output_parser import StrOutputParser\n",
|
|
"from langchain.schema.document import Document\n",
|
|
"from langchain.schema import format_document\n",
|
|
"\n",
|
|
"from permchain import Channel, Pregel\n",
|
|
"from permchain.channels import LastValue, Topic"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "271728d7-b3c8-4ec6-a728-19835e282ec3",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Stuff Documents\n",
|
|
"\n",
|
|
"Stuff documents is simple - just a chain"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "0462aff0-1b88-49cc-bfe2-3c169d5e1d63",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.schema.runnable import RunnableLambda"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "59d6430b-c113-4498-9ffc-f4623f7a0b5c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"DEFAULT_DOCUMENT_PROMPT = PromptTemplate.from_template(template=\"{page_content}\")\n",
|
|
"\n",
|
|
"_combine_documents = RunnableLambda(\n",
|
|
" lambda x: format_document(x, DEFAULT_DOCUMENT_PROMPT)\n",
|
|
").map() | (lambda x: \"\\n\\n\".join(x))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "29b2668d-e4a6-4876-9b04-bdc841774c62",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"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": 5,
|
|
"id": "17da58b7-8685-4d0a-9a47-c398c085d477",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"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",
|
|
" | StrOutputParser()\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "87295b71-0afc-4901-b57c-a7b945aa4bd9",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'Harrison used to work at Kensho.'"
|
|
]
|
|
},
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"stuff_chain.invoke({\"question\": \"where did harrison work\", \"docs\": docs})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "fff324c1-7fbf-41e5-861f-a10ba0112dbd",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Reduce Documents\n",
|
|
"\n",
|
|
"Reduce documents tries to merge documents recursively."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "b15f5abb-1cfe-4965-a021-c891506c5dd2",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"many_docs = docs * 5"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "ccad04a3-fd3f-4e73-b895-29e53535f000",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def _split_list_of_docs(docs, max_length=70):\n",
|
|
" new_result_doc_list = []\n",
|
|
" _sub_result_docs = []\n",
|
|
" for doc in docs:\n",
|
|
" _sub_result_docs.append(doc)\n",
|
|
" _num_tokens = sum([len(d.page_content) for d in _sub_result_docs])\n",
|
|
" if _num_tokens > max_length:\n",
|
|
" if len(_sub_result_docs) == 1:\n",
|
|
" raise ValueError(\n",
|
|
" \"A single document was longer than the context length,\"\n",
|
|
" \" we cannot handle this.\"\n",
|
|
" )\n",
|
|
" new_result_doc_list.append(_sub_result_docs[:-1])\n",
|
|
" _sub_result_docs = _sub_result_docs[-1:]\n",
|
|
" new_result_doc_list.append(_sub_result_docs)\n",
|
|
" return new_result_doc_list"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "11cfd337-9f3b-4b26-ba30-251e17b18994",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"[[Document(page_content='Harrison used to work at Kensho'),\n",
|
|
" Document(page_content='Ankush worked at Facebook')],\n",
|
|
" [Document(page_content='Harrison used to work at Kensho'),\n",
|
|
" Document(page_content='Ankush worked at Facebook')],\n",
|
|
" [Document(page_content='Harrison used to work at Kensho'),\n",
|
|
" Document(page_content='Ankush worked at Facebook')],\n",
|
|
" [Document(page_content='Harrison used to work at Kensho'),\n",
|
|
" Document(page_content='Ankush worked at Facebook')],\n",
|
|
" [Document(page_content='Harrison used to work at Kensho'),\n",
|
|
" Document(page_content='Ankush worked at Facebook')]]"
|
|
]
|
|
},
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# Just to show what its like split\n",
|
|
"split_docs = _split_list_of_docs(many_docs)\n",
|
|
"split_docs"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"id": "8d524ba6-0939-4a5d-8db0-4fa1ef06eaeb",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"channels = {\n",
|
|
" # input\n",
|
|
" \"docs\": Topic(Document),\n",
|
|
" # intermediate\n",
|
|
" \"docs_to_finalize\": Topic(Document),\n",
|
|
"}"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 23,
|
|
"id": "67370694-86f4-4b64-9d4f-38b2e306abeb",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def decide(docs: list[Document]) -> Runnable:\n",
|
|
" if len(_split_list_of_docs(docs)) > 1:\n",
|
|
" # send back to the beginning if we still need to collapse more\n",
|
|
" return Channel.write_to(\"docs\")\n",
|
|
" else:\n",
|
|
" # send to the finalizer if we're ready to produce final answer\n",
|
|
" return Channel.write_to(\"docs_to_finalize\")\n",
|
|
"\n",
|
|
"\n",
|
|
"def split_docs_with_question(input: dict[str, str | list[Document]]) -> list[dict[str, str | list[Document]]]:\n",
|
|
" return [\n",
|
|
" {\"docs\": docs, \"question\": input[\"question\"]}\n",
|
|
" for docs in _split_list_of_docs(input[\"docs\"])\n",
|
|
" ]\n",
|
|
"\n",
|
|
"\n",
|
|
"collapse = (\n",
|
|
" Channel.subscribe_to([\"docs\", \"question\"])\n",
|
|
" | split_docs_with_question\n",
|
|
" | stuff_chain.map() # Collapse each list of docs to a single string\n",
|
|
" | (lambda x: [Document(page_content=s) for s in x]) # A new (smaller) list of docs\n",
|
|
" | decide\n",
|
|
")\n",
|
|
"\n",
|
|
"# Convert final set of docs to an answer\n",
|
|
"finalize = (\n",
|
|
" Channel.subscribe_to(\"docs_to_finalize\", key=\"docs\").join([\"question\"])\n",
|
|
" | stuff_chain\n",
|
|
" | Channel.write_to(\"answer\")\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 24,
|
|
"id": "3019e7d2-ab7f-4868-b43c-ad898d824a26",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"reduce_chain = Pregel(\n",
|
|
" chains={\n",
|
|
" \"collapse\": collapse,\n",
|
|
" \"finalize\": finalize,\n",
|
|
" },\n",
|
|
" channels=channels,\n",
|
|
" input=[\"question\", \"docs\"],\n",
|
|
" output=\"answer\",\n",
|
|
" debug=True,\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 25,
|
|
"id": "69fcb829-3dae-432a-8db3-11bbb179a7d2",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\u001b[36;1m\u001b[1;3m[pregel/step]\u001b[0m \u001b[1mStarting step 0 with 1 task. Next tasks:\n",
|
|
"\u001b[0m- collapse({'docs': [Document(page_content='Harrison used to work at Kensho'),\n",
|
|
" Document(page_content='Ankush worked at Facebook'),\n",
|
|
" Document(page_content='Harrison used to work at Kensho'),\n",
|
|
" Document(page_content='Ankush worked at Facebook'),\n",
|
|
" Document(page_content='Harrison used to work at Kensho'),\n",
|
|
" Document(page_content='Ankush worked at Facebook'),\n",
|
|
" Document(page_content='Harrison used to work at Kensho'),\n",
|
|
" Document(page_content='Ankush worked at Facebook'),\n",
|
|
" Document(page_content='Harrison used to work at Kensho'),\n",
|
|
" Document(page_content='Ankush worked at Facebook')],\n",
|
|
" 'question': 'where did harrison work'})\n",
|
|
"\u001b[36;1m\u001b[1;3m[pregel/checkpoint]\u001b[0m \u001b[1mFinishing step 0. Channel values:\n",
|
|
"\u001b[0m{'docs': [...], 'docs_to_finalize': [], 'question': 'where did harrison work'}\n",
|
|
"\u001b[36;1m\u001b[1;3m[pregel/step]\u001b[0m \u001b[1mStarting step 1 with 1 task. Next tasks:\n",
|
|
"\u001b[0m- collapse({'docs': [Document(page_content='Harrison used to work at Kensho.'),\n",
|
|
" Document(page_content='Harrison used to work at Kensho.'),\n",
|
|
" Document(page_content='Harrison used to work at Kensho.'),\n",
|
|
" Document(page_content='Harrison used to work at Kensho.'),\n",
|
|
" Document(page_content='Harrison used to work at Kensho.')],\n",
|
|
" 'question': 'where did harrison work'})\n",
|
|
"\u001b[36;1m\u001b[1;3m[pregel/checkpoint]\u001b[0m \u001b[1mFinishing step 1. Channel values:\n",
|
|
"\u001b[0m{'docs': [...], 'docs_to_finalize': [], 'question': 'where did harrison work'}\n",
|
|
"\u001b[36;1m\u001b[1;3m[pregel/step]\u001b[0m \u001b[1mStarting step 2 with 1 task. Next tasks:\n",
|
|
"\u001b[0m- collapse({'docs': [Document(page_content='Harrison used to work at Kensho.'),\n",
|
|
" Document(page_content='Harrison used to work at Kensho.'),\n",
|
|
" Document(page_content='Harrison used to work at Kensho.')],\n",
|
|
" 'question': 'where did harrison work'})\n",
|
|
"\u001b[36;1m\u001b[1;3m[pregel/checkpoint]\u001b[0m \u001b[1mFinishing step 2. Channel values:\n",
|
|
"\u001b[0m{'docs': [], 'docs_to_finalize': [...], 'question': 'where did harrison work'}\n",
|
|
"\u001b[36;1m\u001b[1;3m[pregel/step]\u001b[0m \u001b[1mStarting step 3 with 1 task. Next tasks:\n",
|
|
"\u001b[0m- finalize({'docs': [Document(page_content='Harrison used to work at Kensho.'),\n",
|
|
" Document(page_content='Harrison used to work at Kensho.')]})\n",
|
|
"\u001b[36;1m\u001b[1;3m[pregel/checkpoint]\u001b[0m \u001b[1mFinishing step 3. Channel values:\n",
|
|
"\u001b[0m{'answer': 'Harrison used to work at Kensho.',\n",
|
|
" 'docs': [],\n",
|
|
" 'docs_to_finalize': [],\n",
|
|
" 'question': 'where did harrison work'}\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'Harrison used to work at Kensho.'"
|
|
]
|
|
},
|
|
"execution_count": 25,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"reduce_chain.invoke({\"question\": \"where did harrison work\", \"docs\": many_docs})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "265b29cd-d4f4-4e48-8d4e-b759e909ac2e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.11.5"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|