github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2026-01-04 23:47:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Harrison/memory refactor (#1478)

Browse Source 
moves memory to own module, factors out common stuff
This commit is contained in:
Harrison Chase
2023-03-07 07:59:37 -08:00
committed by GitHub
parent df6865cd52
commit 7bec461782
44 changed files with 3084 additions and 1610 deletions
Download Patch File Download Diff File Expand all files Collapse all files

123
docs/modules/memory/examples/chatgpt_clone.ipynb
View File

@@ -14,7 +14,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 2,
"id": "a99acd89",
"metadata": {},
"outputs": [
@@ -24,9 +24,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -36,20 +36,19 @@
"\n",
"\n",
"Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"```\n",
"$ pwd\n",
"/\n",
"/home/user\n",
"```\n"
]
}
],
"source": [
"from langchain import OpenAI, ConversationChain, LLMChain, PromptTemplate\n",
"from langchain.chains.conversation.memory import ConversationalBufferWindowMemory\n",
"from langchain.memory import ConversationBufferWindowMemory\n",
"\n",
"\n",
"template = \"\"\"Assistant is a large language model trained by OpenAI.\n",
@@ -74,7 +73,7 @@
" llm=OpenAI(temperature=0), \n",
" prompt=prompt, \n",
" verbose=True, \n",
" memory=ConversationalBufferWindowMemory(k=2),\n",
" memory=ConversationBufferWindowMemory(k=2),\n",
")\n",
"\n",
"output = chatgpt_chain.predict(human_input=\"I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\")\n",
@@ -93,9 +92,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -110,9 +109,9 @@
"/\n",
"```\n",
"Human: ls ~\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"```\n",
"$ ls ~\n",
@@ -138,9 +137,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -161,9 +160,9 @@
"Desktop Documents Downloads Music Pictures Public Templates Videos\n",
"```\n",
"Human: cd ~\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
" \n",
"```\n",
"$ cd ~\n",
@@ -190,9 +189,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -214,9 +213,9 @@
"/home/user\n",
"```\n",
"Human: {Please make a file jokes.txt inside and put some jokes inside}\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -245,9 +244,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -272,9 +271,9 @@
"$ echo \"Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!\" >> jokes.txt\n",
"```\n",
"Human: echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py && python3 run.py\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -304,9 +303,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -332,9 +331,9 @@
"Result: 33\n",
"```\n",
"Human: echo -e \"print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])\" > run.py && python3 run.py\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -362,9 +361,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -391,9 +390,9 @@
"Human: echo -e \"echo 'Hello from Docker\" > entrypoint.sh && echo -e \"FROM ubuntu:20.04\n",
"COPY entrypoint.sh entrypoint.sh\n",
"ENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]\">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -426,9 +425,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -459,9 +458,9 @@
"Hello from Docker\n",
"```\n",
"Human: nvidia-smi\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -502,9 +501,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -548,9 +547,9 @@
"|=============================================================================|\n",
"\n",
"Human: ping bbc.com\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -584,9 +583,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -630,9 +629,9 @@
"round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms\n",
"```\n",
"Human: curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -659,9 +658,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -691,9 +690,9 @@
"1.8.1\n",
"```\n",
"Human: lynx https://www.deepmind.com/careers\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -726,9 +725,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -757,9 +756,9 @@
"Explore our current openings and apply today. We look forward to hearing from you.\n",
"```\n",
"Human: curl https://chat.openai.com/chat\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
" \n",
"\n",
"```\n",
@@ -799,9 +798,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -843,9 +842,9 @@
"</html>\n",
"```\n",
"Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"What is artificial intelligence?\"}' https://chat.openai.com/chat\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -875,9 +874,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -916,9 +915,9 @@
"}\n",
"```\n",
"Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\"}' https://chat.openai.com/chat\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
" \n",
"\n",
"```\n",
@@ -961,7 +960,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.9.1"
}
},
"nbformat": 4,