mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-01 19:12:42 +00:00
Samantha/add conversation chain (#166)
Add MemoryChain and ConversationChain as chains that take a docstore in addition to the prompt, and use the docstore to stuff context into the prompt. This can be used to have an ongoing conversation with a chatbot. Probably needs a bit of refactoring for code quality Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This commit is contained in:
Samantha Whitmore
committed by
GitHub
GitHub
parent
4334ffa6f9
commit
a408ed3ea3
283
docs/examples/chains/conversation.ipynb
Normal file
283
docs/examples/chains/conversation.ipynb
Normal file
@@ -0,0 +1,283 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "ae046bff",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' Hello! How are you today?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain import OpenAI, ConversationChain\n",
|
||||
"from langchain.chains.conversation.memory import ConversationSummaryMemory\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"conversation = ConversationChain(llm=llm, verbose=True)\n",
|
||||
"\n",
|
||||
"conversation.predict(input=\"Hi there!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "d8e2a6ff",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI: Hello! How are you today?\n",
|
||||
"Human: I'm doing well! Just having a conversation with an AI.\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" That's great! What would you like to talk about?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"I'm doing well! Just having a conversation with an AI.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "15eda316",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI: Hello! How are you today?\n",
|
||||
"Human: I'm doing well! Just having a conversation with an AI.\n",
|
||||
"AI: That's great! What would you like to talk about?\n",
|
||||
"Human: Tell me about yourself.\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' I am an AI created to provide information and support to humans. I enjoy learning and exploring new things.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"Tell me about yourself.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "b7274f2c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi, what's up?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"\\n\\nI'm doing well, thank you for asking. I'm currently working on a project that I'm really excited about.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary = ConversationChain(llm=llm, memory=ConversationSummaryMemory(llm=OpenAI()), verbose=True)\n",
|
||||
"conversation_with_summary.predict(input=\"Hi, what's up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "a6b6b88f",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"The human greets the AI and asks how it is doing. The AI responds that it is doing well and is currently working on a project that it is excited about.\n",
|
||||
"Human: Tell me more about it!\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"\\n\\nI'm working on a project that involves helping people to better understand and use artificial intelligence. I'm really excited about it because I think it has the potential to make a big difference in people's lives.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary.predict(input=\"Tell me more about it!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "dad869fe",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"The human greets the AI and asks how it is doing. The AI responds that it is doing well and is currently working on a project that it is excited about - a project that involves helping people to better understand and use artificial intelligence.\n",
|
||||
"Human: Very cool -- what is the scope of the project?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'\\n\\nThe project is still in the early stages, but the goal is to create a resource that will help people to understand artificial intelligence and how to use it effectively.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary.predict(input=\"Very cool -- what is the scope of the project?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "0eb11bd0",
|
||||
"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": "3.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -83,7 +83,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.6"
|
||||
"version": "3.10.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Reference in New Issue
Block a user