mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
25f2c82ae8
Improve internal consistency in LangChain documentation - Change occurrences of eg and eg. to e.g. - Fix headers containing unnecessary capital letters. - Change instances of "few shot" to "few-shot". - Add periods to end of sentences where missing. - Minor spelling and grammar fixes.
1665 lines
42 KiB
Plaintext
1665 lines
42 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "9a9acd2e",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Cookbook\n",
|
|
"\n",
|
|
"In this notebook we'll take a look at a few common types of sequences to create."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "93aa2c87",
|
|
"metadata": {},
|
|
"source": [
|
|
"## PromptTemplate + LLM\n",
|
|
"\n",
|
|
"A PromptTemplate -> LLM is a core chain that is used in most other larger chains/systems."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "466b65b3",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.prompts import ChatPromptTemplate\n",
|
|
"from langchain.chat_models import ChatOpenAI"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"id": "3c634ef0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"model = ChatOpenAI()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "d1850a1f",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"prompt = ChatPromptTemplate.from_template(\"tell me a joke about {foo}\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "56d0669f",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"chain = prompt | model"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "e3d0a6cd",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"AIMessage(content='Why don\\'t bears use cell phones? \\n\\nBecause they always get terrible \"grizzly\" reception!', additional_kwargs={}, example=False)"
|
|
]
|
|
},
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.invoke({\"foo\": \"bears\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "7eb9ef50",
|
|
"metadata": {},
|
|
"source": [
|
|
"Often times we want to attach kwargs to the model that's passed in. Here's a few examples of that:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "0b1d8f88",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Attaching Stop Sequences"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "562a06bf",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"chain = prompt | model.bind(stop=[\"\\n\"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "43f5d04c",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"AIMessage(content=\"Why don't bears use cell phones?\", additional_kwargs={}, example=False)"
|
|
]
|
|
},
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.invoke({\"foo\": \"bears\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "f3eaf88a",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Attaching Function Call information"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "f94b71b2",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"functions = [\n",
|
|
" {\n",
|
|
" \"name\": \"joke\",\n",
|
|
" \"description\": \"A joke\",\n",
|
|
" \"parameters\": {\n",
|
|
" \"type\": \"object\",\n",
|
|
" \"properties\": {\n",
|
|
" \"setup\": {\n",
|
|
" \"type\": \"string\",\n",
|
|
" \"description\": \"The setup for the joke\"\n",
|
|
" },\n",
|
|
" \"punchline\": {\n",
|
|
" \"type\": \"string\",\n",
|
|
" \"description\": \"The punchline for the joke\"\n",
|
|
" }\n",
|
|
" },\n",
|
|
" \"required\": [\"setup\", \"punchline\"]\n",
|
|
" }\n",
|
|
" }\n",
|
|
" ]\n",
|
|
"chain = prompt | model.bind(function_call= {\"name\": \"joke\"}, functions= functions)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "decf7710",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"AIMessage(content='', additional_kwargs={'function_call': {'name': 'joke', 'arguments': '{\\n \"setup\": \"Why don\\'t bears wear shoes?\",\\n \"punchline\": \"Because they have bear feet!\"\\n}'}}, example=False)"
|
|
]
|
|
},
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.invoke({\"foo\": \"bears\"}, config={})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "9098c5ed",
|
|
"metadata": {},
|
|
"source": [
|
|
"## PromptTemplate + LLM + OutputParser\n",
|
|
"\n",
|
|
"We can also add in an output parser to easily trasform the raw LLM/ChatModel output into a more workable format"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"id": "f799664d",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.schema.output_parser import StrOutputParser"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"id": "cc194c78",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"chain = prompt | model | StrOutputParser()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "77acf448",
|
|
"metadata": {},
|
|
"source": [
|
|
"Notice that this now returns a string - a much more workable format for downstream tasks"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 13,
|
|
"id": "e3d69a18",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\""
|
|
]
|
|
},
|
|
"execution_count": 13,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.invoke({\"foo\": \"bears\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "c01864e5",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Functions Output Parser\n",
|
|
"\n",
|
|
"When you specify the function to return, you may just want to parse that directly"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 14,
|
|
"id": "ad0dd88e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.output_parsers.openai_functions import JsonOutputFunctionsParser\n",
|
|
"chain = (\n",
|
|
" prompt \n",
|
|
" | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
|
|
" | JsonOutputFunctionsParser()\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 15,
|
|
"id": "1e7aa8eb",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"{'setup': \"Why don't bears wear shoes?\",\n",
|
|
" 'punchline': 'Because they have bear feet!'}"
|
|
]
|
|
},
|
|
"execution_count": 15,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.invoke({\"foo\": \"bears\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 17,
|
|
"id": "d4aa1a01",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.output_parsers.openai_functions import JsonKeyOutputFunctionsParser\n",
|
|
"chain = (\n",
|
|
" prompt \n",
|
|
" | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
|
|
" | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 18,
|
|
"id": "8b6df9ba",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"Why don't bears like fast food?\""
|
|
]
|
|
},
|
|
"execution_count": 18,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.invoke({\"foo\": \"bears\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "2ed58136",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Passthroughs and itemgetter\n",
|
|
"\n",
|
|
"Often times when constructing a chain you may want to pass along original input variables to future steps in the chain. How exactly you do this depends on what exactly the input is:\n",
|
|
"\n",
|
|
"- If the original input was a string, then you likely just want to pass along the string. This can be done with `RunnablePassthrough`. For an example of this, see `LLMChain + Retriever`\n",
|
|
"- If the original input was a dictionary, then you likely want to pass along specific keys. This can be done with `itemgetter`. For an example of this see `Multiple LLM Chains`"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"id": "5d3d8ffe",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.schema.runnable import RunnablePassthrough\n",
|
|
"from operator import itemgetter"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "91c5ef3d",
|
|
"metadata": {},
|
|
"source": [
|
|
"## LLMChain + Retriever\n",
|
|
"\n",
|
|
"Let's now look at adding in a retrieval step, which adds up to a \"retrieval-augmented generation\" chain"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "33be32af",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.vectorstores import Chroma\n",
|
|
"from langchain.embeddings import OpenAIEmbeddings\n",
|
|
"from langchain.schema.runnable import RunnablePassthrough"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "df3f3fa2",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Create the retriever\n",
|
|
"vectorstore = Chroma.from_texts([\"harrison worked at kensho\"], embedding=OpenAIEmbeddings())\n",
|
|
"retriever = vectorstore.as_retriever()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 16,
|
|
"id": "bfc47ec1",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"template = \"\"\"Answer the question based only on the following context:\n",
|
|
"{context}\n",
|
|
"\n",
|
|
"Question: {question}\n",
|
|
"\"\"\"\n",
|
|
"prompt = ChatPromptTemplate.from_template(template)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 17,
|
|
"id": "eae31755",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"chain = (\n",
|
|
" {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
|
|
" | prompt \n",
|
|
" | model \n",
|
|
" | StrOutputParser()\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 18,
|
|
"id": "f3040b0c",
|
|
"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": [
|
|
"'Harrison worked at Kensho.'"
|
|
]
|
|
},
|
|
"execution_count": 18,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.invoke(\"where did harrison work?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 19,
|
|
"id": "e1d20c7c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"template = \"\"\"Answer the question based only on the following context:\n",
|
|
"{context}\n",
|
|
"\n",
|
|
"Question: {question}\n",
|
|
"\n",
|
|
"Answer in the following language: {language}\n",
|
|
"\"\"\"\n",
|
|
"prompt = ChatPromptTemplate.from_template(template)\n",
|
|
"\n",
|
|
"chain = {\n",
|
|
" \"context\": itemgetter(\"question\") | retriever, \n",
|
|
" \"question\": itemgetter(\"question\"), \n",
|
|
" \"language\": itemgetter(\"language\")\n",
|
|
"} | prompt | model | StrOutputParser()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 20,
|
|
"id": "7ee8b2d4",
|
|
"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": [
|
|
"'Harrison ha lavorato a Kensho.'"
|
|
]
|
|
},
|
|
"execution_count": 20,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"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": 4,
|
|
"id": "3f30c348",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.schema.runnable import RunnableMap\n",
|
|
"from langchain.schema import format_document"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"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": 6,
|
|
"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": 7,
|
|
"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": 8,
|
|
"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": 16,
|
|
"id": "5c32cc89",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"_inputs = RunnableMap(\n",
|
|
" {\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",
|
|
")\n",
|
|
"_context = {\n",
|
|
" \"context\": itemgetter(\"standalone_question\") | retriever | _combine_documents,\n",
|
|
" \"question\": lambda x: x[\"standalone_question\"]\n",
|
|
"}\n",
|
|
"conversational_qa_chain = _inputs | _context | ANSWER_PROMPT | ChatOpenAI()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 17,
|
|
"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": 17,
|
|
"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": 15,
|
|
"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": 15,
|
|
"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": "c5543183",
|
|
"metadata": {},
|
|
"source": [
|
|
"### With Memory and returning source documents\n",
|
|
"\n",
|
|
"This shows how to use memory with the above. For memory, we need to manage that outside at the memory. For returning the retrieved documents, we just need to pass them through all the way."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 18,
|
|
"id": "e31dd17c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.memory import ConversationBufferMemory"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 44,
|
|
"id": "d4bffe94",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"memory = ConversationBufferMemory(return_messages=True, output_key=\"answer\", input_key=\"question\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 45,
|
|
"id": "733be985",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# First we add a step to load memory\n",
|
|
"# This needs to be a RunnableMap because its the first input\n",
|
|
"loaded_memory = RunnableMap(\n",
|
|
" {\n",
|
|
" \"question\": itemgetter(\"question\"),\n",
|
|
" \"memory\": memory.load_memory_variables,\n",
|
|
" }\n",
|
|
")\n",
|
|
"# Next we add a step to expand memory into the variables\n",
|
|
"expanded_memory = {\n",
|
|
" \"question\": itemgetter(\"question\"),\n",
|
|
" \"chat_history\": lambda x: x[\"memory\"][\"history\"]\n",
|
|
"}\n",
|
|
"\n",
|
|
"# Now we calculate the standalone question\n",
|
|
"standalone_question = {\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",
|
|
"# Now we retrieve the documents\n",
|
|
"retrieved_documents = {\n",
|
|
" \"docs\": itemgetter(\"standalone_question\") | retriever,\n",
|
|
" \"question\": lambda x: x[\"standalone_question\"]\n",
|
|
"}\n",
|
|
"# Now we construct the inputs for the final prompt\n",
|
|
"final_inputs = {\n",
|
|
" \"context\": lambda x: _combine_documents(x[\"docs\"]),\n",
|
|
" \"question\": itemgetter(\"question\")\n",
|
|
"}\n",
|
|
"# And finally, we do the part that returns the answers\n",
|
|
"answer = {\n",
|
|
" \"answer\": final_inputs | ANSWER_PROMPT | ChatOpenAI(),\n",
|
|
" \"docs\": itemgetter(\"docs\"),\n",
|
|
"}\n",
|
|
"# And now we put it all together!\n",
|
|
"final_chain = loaded_memory | expanded_memory | standalone_question | retrieved_documents | answer"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 46,
|
|
"id": "806e390c",
|
|
"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": [
|
|
"{'answer': AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False),\n",
|
|
" 'docs': [Document(page_content='harrison worked at kensho', metadata={})]}"
|
|
]
|
|
},
|
|
"execution_count": 46,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"inputs = {\"question\": \"where did harrison work?\"}\n",
|
|
"result = final_chain.invoke(inputs)\n",
|
|
"result"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 47,
|
|
"id": "977399fd",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Note that the memory does not save automatically\n",
|
|
"# This will be improved in the future\n",
|
|
"# For now you need to save it yourself\n",
|
|
"memory.save_context(inputs, {\"answer\": result[\"answer\"].content})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 48,
|
|
"id": "f94f7de4",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"{'history': [HumanMessage(content='where did harrison work?', additional_kwargs={}, example=False),\n",
|
|
" AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False)]}"
|
|
]
|
|
},
|
|
"execution_count": 48,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"memory.load_memory_variables({})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "0f2bf8d3",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Multiple LLM Chains\n",
|
|
"\n",
|
|
"This can also be used to string together multiple LLMChains"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 31,
|
|
"id": "d65d4e9e",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'El país en el que nació la ciudad de Honolulu, Hawái, donde nació Barack Obama, el 44º presidente de los Estados Unidos, es Estados Unidos.'"
|
|
]
|
|
},
|
|
"execution_count": 31,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"from operator import itemgetter\n",
|
|
"\n",
|
|
"prompt1 = ChatPromptTemplate.from_template(\"what is the city {person} is from?\")\n",
|
|
"prompt2 = ChatPromptTemplate.from_template(\"what country is the city {city} in? respond in {language}\")\n",
|
|
"\n",
|
|
"chain1 = prompt1 | model | StrOutputParser()\n",
|
|
"\n",
|
|
"chain2 = {\"city\": chain1, \"language\": itemgetter(\"language\")} | prompt2 | model | StrOutputParser()\n",
|
|
"\n",
|
|
"chain2.invoke({\"person\": \"obama\", \"language\": \"spanish\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 32,
|
|
"id": "878f8176",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.schema.runnable import RunnableMap\n",
|
|
"prompt1 = ChatPromptTemplate.from_template(\"generate a random color\")\n",
|
|
"prompt2 = ChatPromptTemplate.from_template(\"what is a fruit of color: {color}\")\n",
|
|
"prompt3 = ChatPromptTemplate.from_template(\"what is countries flag that has the color: {color}\")\n",
|
|
"prompt4 = ChatPromptTemplate.from_template(\"What is the color of {fruit} and {country}\")\n",
|
|
"chain1 = prompt1 | model | StrOutputParser()\n",
|
|
"chain2 = RunnableMap(steps={\"color\": chain1}) | {\n",
|
|
" \"fruit\": prompt2 | model | StrOutputParser(),\n",
|
|
" \"country\": prompt3 | model | StrOutputParser(),\n",
|
|
"} | prompt4"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 33,
|
|
"id": "d621a870",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"ChatPromptValue(messages=[HumanMessage(content=\"What is the color of A fruit that has a color similar to #7E7DE6 is the Peruvian Apple Cactus (Cereus repandus). It is a tropical fruit with a vibrant purple or violet exterior. and The country's flag that has the color #7E7DE6 is North Macedonia.\", additional_kwargs={}, example=False)])"
|
|
]
|
|
},
|
|
"execution_count": 33,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain2.invoke({})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "d094d637",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Router\n",
|
|
"\n",
|
|
"You can also use the router runnable to conditionally route inputs to different runnables."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "252625fd",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.chains import create_tagging_chain_pydantic\n",
|
|
"from pydantic import BaseModel, Field\n",
|
|
"\n",
|
|
"class PromptToUse(BaseModel):\n",
|
|
" \"\"\"Used to determine which prompt to use to answer the user's input.\"\"\"\n",
|
|
" \n",
|
|
" name: str = Field(description=\"Should be one of `math` or `english`\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "57886e84",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"tagger = create_tagging_chain_pydantic(PromptToUse, ChatOpenAI(temperature=0))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "a303b089",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"chain1 = ChatPromptTemplate.from_template(\"You are a math genius. Answer the question: {question}\") | ChatOpenAI()\n",
|
|
"chain2 = ChatPromptTemplate.from_template(\"You are an english major. Answer the question: {question}\") | ChatOpenAI()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "7aa9ea06",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.schema.runnable import RouterRunnable\n",
|
|
"router = RouterRunnable({\"math\": chain1, \"english\": chain2})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "6a3d3f5d",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"chain = {\n",
|
|
" \"key\": {\"input\": lambda x: x[\"question\"]} | tagger | (lambda x: x['text'].name),\n",
|
|
" \"input\": {\"question\": lambda x: x[\"question\"]}\n",
|
|
"} | router"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "8aeda930",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"AIMessage(content='Thank you for the compliment! The sum of 2 + 2 is equal to 4.', additional_kwargs={}, example=False)"
|
|
]
|
|
},
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.invoke({\"question\": \"whats 2 + 2\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "29781123",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Tools\n",
|
|
"\n",
|
|
"You can use any LangChain tool easily"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "9232d2a9",
|
|
"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"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from langchain.tools import DuckDuckGoSearchRun"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "a0c64d2c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"search = DuckDuckGoSearchRun()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "391969b6",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"template = \"\"\"turn the following user input into a search query for a search engine:\n",
|
|
"\n",
|
|
"{input}\"\"\"\n",
|
|
"prompt = ChatPromptTemplate.from_template(template)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "e3d9d20d",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"chain = prompt | model | StrOutputParser() | search"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"id": "55f2967d",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"What sports games are on TV today & tonight? Watch and stream live sports on TV today, tonight, tomorrow. Today's 2023 sports TV schedule includes football, basketball, baseball, hockey, motorsports, soccer and more. Watch on TV or stream online on ESPN, FOX, FS1, CBS, NBC, ABC, Peacock, Paramount+, fuboTV, local channels and many other networks. Weather Alerts Alerts Bar. Not all offers available in all states, please visit BetMGM for the latest promotions for your area. Must be 21+ to gamble, please wager responsibly. If you or someone ... Speak of the Devils. Good Morning Arizona. Happy Hour Spots. Jaime's Local Love. Surprise Squad. Silver Apple. Field Trip Friday. Seen on TV. Arizona Highways TV. MLB Games Tonight: How to Watch on TV, Streaming & Odds - Friday, July 28. San Diego Padres' Juan Soto plays during the first baseball game in a doubleheader, Saturday, July 15, 2023, in Philadelphia. (AP Photo/Matt Slocum) (APMedia) Today's MLB schedule features top teams in action. Among those games is the Texas Rangers playing the San Diego ... TV. Cleveland at Chi. White Sox. 1:10pm. Bally Sports. NBCS-CHI. Cleveland Guardians (50-51) are second place in AL Central and Chicago White Sox (41-61) are fourth place in AL Central. The Guardians are 23-27 on the road this season and White Sox are 21-26 at home. Chi. Cubs at St. Louis.\""
|
|
]
|
|
},
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.invoke({\"input\": \"I'd like to figure out what games are tonight\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "fbc4bf6e",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Arbitrary Functions\n",
|
|
"\n",
|
|
"You can use arbitrary functions in the pipeline\n",
|
|
"\n",
|
|
"Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single input and unpacks it into multiple argument."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 35,
|
|
"id": "6bb221b3",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.schema.runnable import RunnableLambda\n",
|
|
"\n",
|
|
"def length_function(text):\n",
|
|
" return len(text)\n",
|
|
"\n",
|
|
"def _multiple_length_function(text1, text2):\n",
|
|
" return len(text1) * len(text2)\n",
|
|
"\n",
|
|
"def multiple_length_function(_dict):\n",
|
|
" return _multiple_length_function(_dict[\"text1\"], _dict[\"text2\"])\n",
|
|
"\n",
|
|
"prompt = ChatPromptTemplate.from_template(\"what is {a} + {b}\")\n",
|
|
"\n",
|
|
"chain1 = prompt | model\n",
|
|
"\n",
|
|
"chain = {\n",
|
|
" \"a\": itemgetter(\"foo\") | RunnableLambda(length_function),\n",
|
|
" \"b\": {\"text1\": itemgetter(\"foo\"), \"text2\": itemgetter(\"bar\")} | RunnableLambda(multiple_length_function)\n",
|
|
"} | prompt | model"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 36,
|
|
"id": "5488ec85",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"AIMessage(content='3 + 9 is equal to 12.', additional_kwargs={}, example=False)"
|
|
]
|
|
},
|
|
"execution_count": 36,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.invoke({\"foo\": \"bar\", \"bar\": \"gah\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "506e9636",
|
|
"metadata": {},
|
|
"source": [
|
|
"## SQL Database\n",
|
|
"\n",
|
|
"We can also try to replicate our SQLDatabaseChain using this style."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 37,
|
|
"id": "7a927516",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"template = \"\"\"Based on the table schema below, write a SQL query that would answer the user's question:\n",
|
|
"{schema}\n",
|
|
"\n",
|
|
"Question: {question}\"\"\"\n",
|
|
"prompt = ChatPromptTemplate.from_template(template)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 38,
|
|
"id": "3f51f386",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.utilities import SQLDatabase"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 41,
|
|
"id": "2ccca6fc",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"db = SQLDatabase.from_uri(\"sqlite:///../../../../notebooks/Chinook.db\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 42,
|
|
"id": "05ba88ee",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def get_schema(_):\n",
|
|
" return db.get_table_info()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 43,
|
|
"id": "a4eda902",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def run_query(query):\n",
|
|
" return db.run(query)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 47,
|
|
"id": "5046cb17",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"inputs = {\n",
|
|
" \"schema\": RunnableLambda(get_schema),\n",
|
|
" \"question\": itemgetter(\"question\")\n",
|
|
"}\n",
|
|
"sql_response = (\n",
|
|
" RunnableMap(inputs)\n",
|
|
" | prompt\n",
|
|
" | model.bind(stop=[\"\\nSQLResult:\"])\n",
|
|
" | StrOutputParser()\n",
|
|
" )"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 48,
|
|
"id": "a5552039",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'SELECT COUNT(*) \\nFROM Employee;'"
|
|
]
|
|
},
|
|
"execution_count": 48,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"sql_response.invoke({\"question\": \"How many employees are there?\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 49,
|
|
"id": "d6fee130",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"template = \"\"\"Based on the table schema below, question, sql query, and sql response, write a natural language response:\n",
|
|
"{schema}\n",
|
|
"\n",
|
|
"Question: {question}\n",
|
|
"SQL Query: {query}\n",
|
|
"SQL Response: {response}\"\"\"\n",
|
|
"prompt_response = ChatPromptTemplate.from_template(template)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 52,
|
|
"id": "923aa634",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"full_chain = (\n",
|
|
" RunnableMap({\n",
|
|
" \"question\": itemgetter(\"question\"),\n",
|
|
" \"query\": sql_response,\n",
|
|
" }) \n",
|
|
" | {\n",
|
|
" \"schema\": RunnableLambda(get_schema),\n",
|
|
" \"question\": itemgetter(\"question\"),\n",
|
|
" \"query\": itemgetter(\"query\"),\n",
|
|
" \"response\": lambda x: db.run(x[\"query\"]) \n",
|
|
" } \n",
|
|
" | prompt_response \n",
|
|
" | model\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 53,
|
|
"id": "e94963d8",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"AIMessage(content='There are 8 employees.', additional_kwargs={}, example=False)"
|
|
]
|
|
},
|
|
"execution_count": 53,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"full_chain.invoke({\"question\": \"How many employees are there?\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "f09fd305",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Code Writing"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 57,
|
|
"id": "bd7c259a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.utilities import PythonREPL\n",
|
|
"from langchain.prompts import SystemMessagePromptTemplate, HumanMessagePromptTemplate"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 58,
|
|
"id": "73795d2d",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"template = \"\"\"Write some python code to solve the user's problem. \n",
|
|
"\n",
|
|
"Return only python code in Markdown format, e.g.:\n",
|
|
"\n",
|
|
"```python\n",
|
|
"....\n",
|
|
"```\"\"\"\n",
|
|
"prompt = ChatPromptTemplate(messages=[\n",
|
|
" SystemMessagePromptTemplate.from_template(template),\n",
|
|
" HumanMessagePromptTemplate.from_template(\"{input}\")\n",
|
|
"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 64,
|
|
"id": "42859e8a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def _sanitize_output(text: str):\n",
|
|
" _, after = text.split(\"```python\")\n",
|
|
" return after.split(\"```\")[0]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 67,
|
|
"id": "5ded1a86",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"chain = prompt | model | StrOutputParser() | _sanitize_output | PythonREPL().run"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 68,
|
|
"id": "208c2b75",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Python REPL can execute arbitrary code. Use with caution.\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'4\\n'"
|
|
]
|
|
},
|
|
"execution_count": 68,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.invoke({\"input\": \"whats 2 plus 2\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "5062941a",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Memory\n",
|
|
"\n",
|
|
"This shows how to add memory to an arbitrary chain. Right now, you can use the memory classes but need to hook it up manually"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 99,
|
|
"id": "7998efd8",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.memory import ConversationBufferMemory\n",
|
|
"from langchain.schema.runnable import RunnableMap\n",
|
|
"from langchain.prompts import MessagesPlaceholder\n",
|
|
"model = ChatOpenAI()\n",
|
|
"prompt = ChatPromptTemplate.from_messages([\n",
|
|
" (\"system\", \"You are a helpful chatbot\"),\n",
|
|
" MessagesPlaceholder(variable_name=\"history\"),\n",
|
|
" (\"human\", \"{input}\")\n",
|
|
"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 100,
|
|
"id": "fa0087f3",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"memory = ConversationBufferMemory(return_messages=True)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 101,
|
|
"id": "06b531ae",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"{'history': []}"
|
|
]
|
|
},
|
|
"execution_count": 101,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"memory.load_memory_variables({})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 102,
|
|
"id": "d9437af6",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"chain = RunnableMap({\n",
|
|
" \"input\": lambda x: x[\"input\"],\n",
|
|
" \"memory\": memory.load_memory_variables\n",
|
|
"}) | {\n",
|
|
" \"input\": lambda x: x[\"input\"],\n",
|
|
" \"history\": lambda x: x[\"memory\"][\"history\"]\n",
|
|
"} | prompt | model"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 103,
|
|
"id": "bed1e260",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"AIMessage(content='Hello Bob! How can I assist you today?', additional_kwargs={}, example=False)"
|
|
]
|
|
},
|
|
"execution_count": 103,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"inputs = {\"input\": \"hi im bob\"}\n",
|
|
"response = chain.invoke(inputs)\n",
|
|
"response"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 104,
|
|
"id": "890475b4",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"memory.save_context(inputs, {\"output\": response.content})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 105,
|
|
"id": "e8fcb77f",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"{'history': [HumanMessage(content='hi im bob', additional_kwargs={}, example=False),\n",
|
|
" AIMessage(content='Hello Bob! How can I assist you today?', additional_kwargs={}, example=False)]}"
|
|
]
|
|
},
|
|
"execution_count": 105,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"memory.load_memory_variables({})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 106,
|
|
"id": "d837d5c3",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"AIMessage(content='Your name is Bob. You mentioned it in your previous message. Is there anything else I can help you with, Bob?', additional_kwargs={}, example=False)"
|
|
]
|
|
},
|
|
"execution_count": 106,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"inputs = {\"input\": \"whats my name\"}\n",
|
|
"response = chain.invoke(inputs)\n",
|
|
"response"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "4927a727-b4c8-453c-8c83-bd87b4fcac14",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Moderation\n",
|
|
"\n",
|
|
"This shows how to add in moderation (or other safeguards) around your LLM application."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 26,
|
|
"id": "4f5f6449-940a-4f5c-97c0-39b71c3e2a68",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.chains import OpenAIModerationChain\n",
|
|
"from langchain.llms import OpenAI"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 35,
|
|
"id": "fcb8312b-7e7a-424f-a3ec-76738c9a9d21",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"moderate = OpenAIModerationChain()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 32,
|
|
"id": "b24b9148-f6b0-4091-8ea8-d3fb281bd950",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"model = OpenAI()\n",
|
|
"prompt = ChatPromptTemplate.from_messages([\n",
|
|
" (\"system\", \"repeat after me: {input}\")\n",
|
|
"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 33,
|
|
"id": "1c8ed87c-9ca6-4559-bf60-d40e94a0af08",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"chain = prompt | model"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 34,
|
|
"id": "5256b9bd-381a-42b0-bfa8-7e6d18f853cb",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'\\n\\nYou are stupid.'"
|
|
]
|
|
},
|
|
"execution_count": 34,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"chain.invoke({\"input\": \"you are stupid\"})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 36,
|
|
"id": "fe6e3b33-dc9a-49d5-b194-ba750c58a628",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"moderated_chain = chain | moderate"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 37,
|
|
"id": "d8ba0cbd-c739-4d23-be9f-6ae092bd5ffb",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"{'input': '\\n\\nYou are stupid.',\n",
|
|
" 'output': \"Text was found that violates OpenAI's content policy.\"}"
|
|
]
|
|
},
|
|
"execution_count": 37,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"moderated_chain.invoke({\"input\": \"you are stupid\"})"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.10.1"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|