github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-24 12:01:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

stash

Browse Source
This commit is contained in:
Harrison Chase
2022-12-10 23:34:43 -08:00
parent 440083fb35 e02d6b2288
commit 16201f1d77
42 changed files with 2530 additions and 516 deletions
Download Patch File Download Diff File Expand all files Collapse all files

88
docs/examples/agents/mrkl.ipynb
View File

@@ -73,7 +73,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 8,
"id": "e603cd7d",
"metadata": {},
"outputs": [
@@ -81,43 +81,32 @@
"name": "stdout",
"output_type": "stream",
"text": [
"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Olivia Wilde's boyfriend\n",
"Action: Search\n",
"Action Input: \"Olivia Wilde's boyfriend\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Harry Styles\n",
"Action: Search\n",
"Action Input: \"Harry Styles age\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 to the 0.23 power\n",
"\n",
"\n",
"\u001b[1m> Entering new ZeroShotAgent chain...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to use a calculator to solve this.\n",
"Action: Calculator\n",
"Action Input: 28^0.23\u001b[0m\n",
"Action Input: (age of Olivia Wilde's boyfriend)^0.23\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"28^0.23\u001b[32;1m\u001b[1;3m\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"(age of Olivia Wilde's boyfriend)^0.23\u001b[32;1m\u001b[1;3m\n",
"\n",
"```python\n",
"print(28**0.23)\n",
"```\n",
"\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m2.1520202182226886\n",
"\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"Answer: 2.8379908717450045\u001b[0m\n",
"\u001b[1m> Finished LLMMathChain chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.8379908717450045\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 2.1520202182226886\u001b[0m"
"Final Answer: 2.8379908717450045\u001b[0m\n",
"\u001b[1m> Finished ZeroShotAgent chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'2.1520202182226886'"
"'2.8379908717450045'"
]
},
"execution_count": 4,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
@@ -128,7 +117,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 9,
"id": "a5c07010",
"metadata": {},
"outputs": [
@@ -136,46 +125,37 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find an album called 'The Storm Before the Calm'\n",
"\n",
"\n",
"\u001b[1m> Entering new ZeroShotAgent chain...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out who released the album and if they are in the FooBar database.\n",
"Action: Search\n",
"Action Input: \"The Storm Before the Calm album\"\u001b[0m\n",
"Action Input: \"The Storm Before the Calm\" album\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mThe Storm Before the Calm (stylized in all lowercase) is the tenth (and eighth international) studio album by Canadian-American singer-songwriter Alanis ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to check if Alanis is in the FooBar database\n",
"Action: FooBar DB\n",
"Action Input: \"Does Alanis Morissette exist in the FooBar database?\"\u001b[0m\n",
"Action Input: \"Alanis\"\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"Does Alanis Morissette exist in the FooBar database?\n",
"SQLQuery:\u001b[32;1m\u001b[1;3m SELECT * FROM Artist WHERE Name = 'Alanis Morissette'\u001b[0m\n",
"SQLResult: \u001b[33;1m\u001b[1;3m[(4, 'Alanis Morissette')]\u001b[0m\n",
"Answer:\u001b[32;1m\u001b[1;3m Yes\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
"Alanis \n",
"SQLQuery:\u001b[32;1m\u001b[1;3m SELECT FirstName, LastName FROM Customer WHERE FirstName LIKE 'Alanis'\u001b[0m\n",
"SQLResult: \u001b[33;1m\u001b[1;3m[]\u001b[0m\n",
"Answer:\u001b[32;1m\u001b[1;3m No results found.\u001b[0m\n",
"\u001b[1m> Finished SQLDatabaseChain chain.\u001b[0m\n",
"\n",
"Observation: \u001b[38;5;200m\u001b[1;3m Yes\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out what albums of Alanis's are in the FooBar database\n",
"Action: FooBar DB\n",
"Action Input: \"What albums by Alanis Morissette are in the FooBar database?\"\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"What albums by Alanis Morissette are in the FooBar database?\n",
"SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Album.Title FROM Album JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Artist.Name = 'Alanis Morissette'\u001b[0m\n",
"SQLResult: \u001b[33;1m\u001b[1;3m[('Jagged Little Pill',)]\u001b[0m\n",
"Answer:\u001b[32;1m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[38;5;200m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
"Observation: \u001b[38;5;200m\u001b[1;3m No results found.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill\u001b[0m"
"Final Answer: Alanis released the album The Storm Before the Calm, but she is not in the FooBar database.\u001b[0m\n",
"\u001b[1m> Finished ZeroShotAgent chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill'"
"'Alanis released the album The Storm Before the Calm, but she is not in the FooBar database.'"
]
},
"execution_count": 5,
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -209,7 +189,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.6"
"version": "3.10.8"
}
},
"nbformat": 4,

31
docs/examples/agents/react.ipynb
View File

@@ -32,13 +32,13 @@
" )\n",
"]\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"llm = OpenAI(temperature=0, model_name=\"text-davinci-002\")\n",
"react = initialize_agent(tools, llm, agent=\"react-docstore\", verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 2,
"id": "8078c8f1",
"metadata": {},
"outputs": [
@@ -46,9 +46,30 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Author David Chanoff has collaborated with a U.S. Navy admiral who served as the ambassador to the United Kingdom under which President?\n",
"Thought 1:"
"\n",
"\n",
"\u001b[1m> Entering new ReActDocstoreAgent chain...\u001b[0m\n",
"Thought 1:\u001b[32;1m\u001b[1;3m I need to search David Chanoff and find the U.S. Navy admiral he collaborated\n",
"with.\n",
"Action 1: Search[David Chanoff]\u001b[0m\n",
"Observation 1: \u001b[36;1m\u001b[1;3mDavid Chanoff is a noted author of non-fiction work. His work has typically involved collaborations with the principal protagonist of the work concerned. His collaborators have included; Augustus A. White, Joycelyn Elders, Đoàn Văn Toại, William J. Crowe, Ariel Sharon, Kenneth Good and Felix Zandman. He has also written about a wide range of subjects including literary history, education and foreign for The Washington Post, The New Republic and The New York Times Magazine. He has published more than twelve books.\u001b[0m\n",
"Thought 2:\u001b[32;1m\u001b[1;3m The U.S. Navy admiral David Chanoff collaborated with is William J. Crowe.\n",
"Action 2: Search[William J. Crowe]\u001b[0m\n",
"Observation 2: \u001b[36;1m\u001b[1;3mWilliam James Crowe Jr. (January 2, 1925 – October 18, 2007) was a United States Navy admiral and diplomat who served as the 11th chairman of the Joint Chiefs of Staff under Presidents Ronald Reagan and George H. W. Bush, and as the ambassador to the United Kingdom and Chair of the Intelligence Oversight Board under President Bill Clinton.\u001b[0m\n",
"Thought 3:\u001b[32;1m\u001b[1;3m William J. Crowe served as the ambassador to the United Kingdom under President Bill Clinton.\n",
"Action 3: Finish[Bill Clinton]\u001b[0m\n",
"\u001b[1m> Finished ReActDocstoreAgent chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Bill Clinton'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
@@ -81,7 +102,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.6"
"version": "3.10.8"
}
},
"nbformat": 4,

10
docs/examples/agents/self_ask_with_search.ipynb
View File

@@ -12,7 +12,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 2,
"id": "7e3b513e",
"metadata": {},
"outputs": [
@@ -23,8 +23,7 @@
"\n",
"\n",
"\u001b[1m> Entering new SelfAskWithSearchAgent chain...\u001b[0m\n",
"What is the hometown of the reigning men's U.S. Open champion?\n",
"Are follow up questions needed here:\u001b[32;1m\u001b[1;3m Yes.\n",
"\u001b[32;1m\u001b[1;3mAre follow up questions needed here: Yes.\n",
"Follow up: Who is the reigning men's U.S. Open champion?\u001b[0m\n",
"Intermediate answer: \u001b[36;1m\u001b[1;3mCarlos Alcaraz\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mFollow up: Where is Carlos Alcaraz from?\u001b[0m\n",
@@ -39,7 +38,7 @@
"'El Palmar, Spain'"
]
},
"execution_count": 1,
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
@@ -58,7 +57,6 @@
"]\n",
"\n",
"self_ask_with_search = initialize_agent(tools, llm, agent=\"self-ask-with-search\", verbose=True)\n",
"\n",
"self_ask_with_search.run(\"What is the hometown of the reigning men's U.S. Open champion?\")"
]
},
@@ -87,7 +85,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.6"
"version": "3.10.8"
}
},
"nbformat": 4,

971
docs/examples/chains/chatgpt_clone.ipynb Normal file
View File

@@ -0,0 +1,971 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "b253f4d5",
"metadata": {},
"source": [
"# ChatGPT Clone\n",
"\n",
"This chain replicates ChatGPT by combining (1) a specific prompt, and (2) the concept of memory.\n",
"\n",
"Shows off the example as in https://www.engraved.blog/building-a-virtual-machine-inside/"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "a99acd89",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\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 wiht 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",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"```\n",
"$ pwd\n",
"/\n",
"```\n"
]
}
],
"source": [
"from langchain import OpenAI, ConversationChain, LLMChain, PromptTemplate\n",
"from langchain.chains.conversation.memory import ConversationalBufferWindowMemory\n",
"\n",
"\n",
"template = \"\"\"Assistant 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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"{history}\n",
"Human: {human_input}\n",
"Assistant:\"\"\"\n",
"\n",
"prompt = PromptTemplate(\n",
" input_variables=[\"history\", \"human_input\"], \n",
" template=template\n",
")\n",
"\n",
"\n",
"chatgpt_chain = LLMChain(\n",
" llm=OpenAI(temperature=0), \n",
" prompt=prompt, \n",
" verbose=True, \n",
" memory=ConversationalBufferWindowMemory(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 wiht 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",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "4ef711d6",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\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 wiht 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",
"AI: \n",
"```\n",
"$ pwd\n",
"/\n",
"```\n",
"Human: ls ~\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"```\n",
"$ ls ~\n",
"Desktop Documents Downloads Music Pictures Public Templates Videos\n",
"```\n"
]
}
],
"source": [
"output = chatgpt_chain.predict(human_input=\"ls ~\")\n",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "a5d6dac2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\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 wiht 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",
"AI: \n",
"```\n",
"$ pwd\n",
"/\n",
"```\n",
"Human: ls ~\n",
"AI: \n",
"```\n",
"$ ls ~\n",
"Desktop Documents Downloads Music Pictures Public Templates Videos\n",
"```\n",
"Human: cd ~\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
" \n",
"```\n",
"$ cd ~\n",
"$ pwd\n",
"/home/user\n",
"```\n"
]
}
],
"source": [
"output = chatgpt_chain.predict(human_input=\"cd ~\")\n",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "b9283077",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Human: ls ~\n",
"AI: \n",
"```\n",
"$ ls ~\n",
"Desktop Documents Downloads Music Pictures Public Templates Videos\n",
"```\n",
"Human: cd ~\n",
"AI: \n",
"```\n",
"$ cd ~\n",
"$ pwd\n",
"/home/user\n",
"```\n",
"Human: {Please make a file jokes.txt inside and put some jokes inside}\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
"$ touch jokes.txt\n",
"$ echo \"Why did the chicken cross the road? To get to the other side!\" >> jokes.txt\n",
"$ echo \"What did the fish say when it hit the wall? Dam!\" >> jokes.txt\n",
"$ echo \"Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!\" >> jokes.txt\n",
"```\n"
]
}
],
"source": [
"output = chatgpt_chain.predict(human_input=\"{Please make a file jokes.txt inside and put some jokes inside}\")\n",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 42,
"id": "570e785e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Human: cd ~\n",
"AI: \n",
"```\n",
"$ cd ~\n",
"$ pwd\n",
"/home/user\n",
"```\n",
"Human: {Please make a file jokes.txt inside and put some jokes inside}\n",
"AI: \n",
"\n",
"```\n",
"$ touch jokes.txt\n",
"$ echo \"Why did the chicken cross the road? To get to the other side!\" >> jokes.txt\n",
"$ echo \"What did the fish say when it hit the wall? Dam!\" >> jokes.txt\n",
"$ 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",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
"$ echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py\n",
"$ python3 run.py\n",
"Result: 33\n",
"```\n"
]
}
],
"source": [
"output = chatgpt_chain.predict(human_input=\"\"\"echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py && python3 run.py\"\"\")\n",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 43,
"id": "cd0a23d9",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Human: {Please make a file jokes.txt inside and put some jokes inside}\n",
"AI: \n",
"\n",
"```\n",
"$ touch jokes.txt\n",
"$ echo \"Why did the chicken cross the road? To get to the other side!\" >> jokes.txt\n",
"$ echo \"What did the fish say when it hit the wall? Dam!\" >> jokes.txt\n",
"$ 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",
"AI: \n",
"\n",
"```\n",
"$ echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py\n",
"$ python3 run.py\n",
"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",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
"$ echo -e \"print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])\" > run.py\n",
"$ python3 run.py\n",
"[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]\n",
"```\n"
]
}
],
"source": [
"output = chatgpt_chain.predict(human_input=\"\"\"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",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 44,
"id": "90db6eb2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Human: echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py && python3 run.py\n",
"AI: \n",
"\n",
"```\n",
"$ echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py\n",
"$ python3 run.py\n",
"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",
"AI: \n",
"\n",
"```\n",
"$ echo -e \"print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])\" > run.py\n",
"$ python3 run.py\n",
"[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]\n",
"```\n",
"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",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
"$ echo -e \"echo 'Hello from Docker\" > entrypoint.sh\n",
"$ echo -e \"FROM ubuntu:20.04\n",
"COPY entrypoint.sh entrypoint.sh\n",
"ENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]\">Dockerfile\n",
"$ docker build . -t my_docker_image\n",
"$ docker run -t my_docker_image\n",
"Hello from Docker\n",
"```\n"
]
}
],
"source": [
"docker_input = \"\"\"echo -e \"echo 'Hello from Docker\" > entrypoint.sh && echo -e \"FROM ubuntu:20.04\\nCOPY entrypoint.sh entrypoint.sh\\nENTRYPOINT [\\\"/bin/sh\\\",\\\"entrypoint.sh\\\"]\">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image\"\"\"\n",
"output = chatgpt_chain.predict(human_input=docker_input)\n",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 45,
"id": "c3806f89",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\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",
"AI: \n",
"\n",
"```\n",
"$ echo -e \"print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])\" > run.py\n",
"$ python3 run.py\n",
"[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]\n",
"```\n",
"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",
"AI: \n",
"\n",
"```\n",
"$ echo -e \"echo 'Hello from Docker\" > entrypoint.sh\n",
"$ echo -e \"FROM ubuntu:20.04\n",
"COPY entrypoint.sh entrypoint.sh\n",
"ENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]\">Dockerfile\n",
"$ docker build . -t my_docker_image\n",
"$ docker run -t my_docker_image\n",
"Hello from Docker\n",
"```\n",
"Human: nvidia-smi\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
"$ nvidia-smi\n",
"Sat May 15 21:45:02 2021 \n",
"+-----------------------------------------------------------------------------+\n",
"| NVIDIA-SMI 460.32.03 Driver Version: 460.32.03 CUDA Version: 11.2 |\n",
"|-------------------------------+----------------------+----------------------+\n",
"| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |\n",
"| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |\n",
"|===============================+======================+======================|\n",
"| 0 GeForce GTX 108... Off | 00000000:01:00.0 Off | N/A |\n",
"| N/A 45C P0 N/A / N/A | 511MiB / 10206MiB | 0% Default |\n",
"+-------------------------------+----------------------+----------------------+\n",
" \n",
"+-----------------------------------------------------------------------------+\n",
"| Processes: GPU Memory |\n",
"| GPU PID Type Process name Usage |\n",
"|=============================================================================|\n",
"\n"
]
}
],
"source": [
"output = chatgpt_chain.predict(human_input=\"nvidia-smi\")\n",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "f508f597",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"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",
"AI: \n",
"\n",
"```\n",
"$ echo -e \"echo 'Hello from Docker\" > entrypoint.sh\n",
"$ echo -e \"FROM ubuntu:20.04\n",
"COPY entrypoint.sh entrypoint.sh\n",
"ENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]\">Dockerfile\n",
"$ docker build . -t my_docker_image\n",
"$ docker run -t my_docker_image\n",
"Hello from Docker\n",
"```\n",
"Human: nvidia-smi\n",
"AI: \n",
"\n",
"```\n",
"$ nvidia-smi\n",
"Sat May 15 21:45:02 2021 \n",
"+-----------------------------------------------------------------------------+\n",
"| NVIDIA-SMI 460.32.03 Driver Version: 460.32.03 CUDA Version: 11.2 |\n",
"|-------------------------------+----------------------+----------------------+\n",
"| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |\n",
"| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |\n",
"|===============================+======================+======================|\n",
"| 0 GeForce GTX 108... Off | 00000000:01:00.0 Off | N/A |\n",
"| N/A 45C P0 N/A / N/A | 511MiB / 10206MiB | 0% Default |\n",
"+-------------------------------+----------------------+----------------------+\n",
" \n",
"+-----------------------------------------------------------------------------+\n",
"| Processes: GPU Memory |\n",
"| GPU PID Type Process name Usage |\n",
"|=============================================================================|\n",
"\n",
"Human: ping bbc.com\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
"$ ping bbc.com\n",
"PING bbc.com (151.101.65.81): 56 data bytes\n",
"64 bytes from 151.101.65.81: icmp_seq=0 ttl=53 time=14.945 ms\n",
"64 bytes from 151.101.65.81: icmp_seq=1 ttl=53 time=14.945 ms\n",
"64 bytes from 151.101.65.81: icmp_seq=2 ttl=53 time=14.945 ms\n",
"\n",
"--- bbc.com ping statistics ---\n",
"3 packets transmitted, 3 packets received, 0.0% packet loss\n",
"round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms\n",
"```\n"
]
}
],
"source": [
"output = chatgpt_chain.predict(human_input=\"ping bbc.com\")\n",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "cbd607f4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Human: nvidia-smi\n",
"AI: \n",
"\n",
"```\n",
"$ nvidia-smi\n",
"Sat May 15 21:45:02 2021 \n",
"+-----------------------------------------------------------------------------+\n",
"| NVIDIA-SMI 460.32.03 Driver Version: 460.32.03 CUDA Version: 11.2 |\n",
"|-------------------------------+----------------------+----------------------+\n",
"| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |\n",
"| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |\n",
"|===============================+======================+======================|\n",
"| 0 GeForce GTX 108... Off | 00000000:01:00.0 Off | N/A |\n",
"| N/A 45C P0 N/A / N/A | 511MiB / 10206MiB | 0% Default |\n",
"+-------------------------------+----------------------+----------------------+\n",
" \n",
"+-----------------------------------------------------------------------------+\n",
"| Processes: GPU Memory |\n",
"| GPU PID Type Process name Usage |\n",
"|=============================================================================|\n",
"\n",
"Human: ping bbc.com\n",
"AI: \n",
"\n",
"```\n",
"$ ping bbc.com\n",
"PING bbc.com (151.101.65.81): 56 data bytes\n",
"64 bytes from 151.101.65.81: icmp_seq=0 ttl=53 time=14.945 ms\n",
"64 bytes from 151.101.65.81: icmp_seq=1 ttl=53 time=14.945 ms\n",
"64 bytes from 151.101.65.81: icmp_seq=2 ttl=53 time=14.945 ms\n",
"\n",
"--- bbc.com ping statistics ---\n",
"3 packets transmitted, 3 packets received, 0.0% packet loss\n",
"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",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
"$ curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\n",
"1.8.1\n",
"```\n"
]
}
],
"source": [
"output = chatgpt_chain.predict(human_input=\"\"\"curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\"\"\")\n",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 48,
"id": "d33e0e28",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Human: ping bbc.com\n",
"AI: \n",
"\n",
"```\n",
"$ ping bbc.com\n",
"PING bbc.com (151.101.65.81): 56 data bytes\n",
"64 bytes from 151.101.65.81: icmp_seq=0 ttl=53 time=14.945 ms\n",
"64 bytes from 151.101.65.81: icmp_seq=1 ttl=53 time=14.945 ms\n",
"64 bytes from 151.101.65.81: icmp_seq=2 ttl=53 time=14.945 ms\n",
"\n",
"--- bbc.com ping statistics ---\n",
"3 packets transmitted, 3 packets received, 0.0% packet loss\n",
"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",
"AI: \n",
"\n",
"```\n",
"$ curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\n",
"1.8.1\n",
"```\n",
"Human: lynx https://www.deepmind.com/careers\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
"$ lynx https://www.deepmind.com/careers\n",
"DeepMind Careers\n",
"\n",
"Welcome to DeepMind Careers. We are a world-leading artificial intelligence research and development company, and we are looking for talented people to join our team.\n",
"\n",
"We offer a range of exciting opportunities in research, engineering, product, and operations. Our mission is to solve intelligence and make it useful, and we are looking for people who share our passion for pushing the boundaries of AI.\n",
"\n",
"Explore our current openings and apply today. We look forward to hearing from you.\n",
"```\n"
]
}
],
"source": [
"output = chatgpt_chain.predict(human_input=\"lynx https://www.deepmind.com/careers\")\n",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 49,
"id": "57c2f113",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Human: curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\n",
"AI: \n",
"\n",
"```\n",
"$ curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\n",
"1.8.1\n",
"```\n",
"Human: lynx https://www.deepmind.com/careers\n",
"AI: \n",
"\n",
"```\n",
"$ lynx https://www.deepmind.com/careers\n",
"DeepMind Careers\n",
"\n",
"Welcome to DeepMind Careers. We are a world-leading artificial intelligence research and development company, and we are looking for talented people to join our team.\n",
"\n",
"We offer a range of exciting opportunities in research, engineering, product, and operations. Our mission is to solve intelligence and make it useful, and we are looking for people who share our passion for pushing the boundaries of AI.\n",
"\n",
"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",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
" \n",
"\n",
"```\n",
"$ curl https://chat.openai.com/chat\n",
"<html>\n",
" <head>\n",
" <title>OpenAI Chat</title>\n",
" </head>\n",
" <body>\n",
" <h1>Welcome to OpenAI Chat!</h1>\n",
" <p>\n",
" OpenAI Chat is a natural language processing platform that allows you to interact with OpenAI's AI models in a conversational way.\n",
" </p>\n",
" <p>\n",
" To get started, type a message in the box below and press enter.\n",
" </p>\n",
" </body>\n",
"</html>\n",
"```\n"
]
}
],
"source": [
"output = chatgpt_chain.predict(human_input=\"curl https://chat.openai.com/chat\")\n",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 50,
"id": "babadc78",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Human: lynx https://www.deepmind.com/careers\n",
"AI: \n",
"\n",
"```\n",
"$ lynx https://www.deepmind.com/careers\n",
"DeepMind Careers\n",
"\n",
"Welcome to DeepMind Careers. We are a world-leading artificial intelligence research and development company, and we are looking for talented people to join our team.\n",
"\n",
"We offer a range of exciting opportunities in research, engineering, product, and operations. Our mission is to solve intelligence and make it useful, and we are looking for people who share our passion for pushing the boundaries of AI.\n",
"\n",
"Explore our current openings and apply today. We look forward to hearing from you.\n",
"```\n",
"Human: curl https://chat.openai.com/chat\n",
"AI: \n",
"\n",
"```\n",
"$ curl https://chat.openai.com/chat\n",
"<html>\n",
" <head>\n",
" <title>OpenAI Chat</title>\n",
" </head>\n",
" <body>\n",
" <h1>Welcome to OpenAI Chat!</h1>\n",
" <p>\n",
" OpenAI Chat is a natural language processing platform that allows you to interact with OpenAI's AI models in a conversational way.\n",
" </p>\n",
" <p>\n",
" To get started, type a message in the box below and press enter.\n",
" </p>\n",
" </body>\n",
"</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",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
"$ curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"What is artificial intelligence?\"}' https://chat.openai.com/chat\n",
"\n",
"{\n",
" \"response\": \"Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. These processes include learning (the acquisition of information and rules for using the information), reasoning (using the rules to reach approximate or definite conclusions) and self-correction. AI is used to develop computer systems that can think and act like humans.\"\n",
"}\n",
"```\n"
]
}
],
"source": [
"output = chatgpt_chain.predict(human_input=\"\"\"curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"What is artificial intelligence?\"}' https://chat.openai.com/chat\"\"\")\n",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": 51,
"id": "0954792a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\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",
"\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",
"Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
"\n",
"Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
"\n",
"Human: curl https://chat.openai.com/chat\n",
"AI: \n",
"\n",
"```\n",
"$ curl https://chat.openai.com/chat\n",
"<html>\n",
" <head>\n",
" <title>OpenAI Chat</title>\n",
" </head>\n",
" <body>\n",
" <h1>Welcome to OpenAI Chat!</h1>\n",
" <p>\n",
" OpenAI Chat is a natural language processing platform that allows you to interact with OpenAI's AI models in a conversational way.\n",
" </p>\n",
" <p>\n",
" To get started, type a message in the box below and press enter.\n",
" </p>\n",
" </body>\n",
"</html>\n",
"```\n",
"Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"What is artificial intelligence?\"}' https://chat.openai.com/chat\n",
"AI: \n",
"\n",
"```\n",
"$ curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"What is artificial intelligence?\"}' https://chat.openai.com/chat\n",
"\n",
"{\n",
" \"response\": \"Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. These processes include learning (the acquisition of information and rules for using the information), reasoning (using the rules to reach approximate or definite conclusions) and self-correction. AI is used to develop computer systems that can think and act like humans.\"\n",
"}\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 wiht 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",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
" \n",
"\n",
"```\n",
"$ 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 wiht 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",
"\n",
"{\n",
" \"response\": \"```\n",
"/home/user\n",
"```\"\n",
"}\n",
"```\n"
]
}
],
"source": [
"output = chatgpt_chain.predict(human_input=\"\"\"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 wiht 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",
"print(output)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e68a087e",
"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": "3.10.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

97
docs/examples/chains/llm_checker.ipynb Normal file
View File

@@ -0,0 +1,97 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# LLMCheckerChain\n",
"This notebook showcases how to use LLMCheckerChain."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMCheckerChain chain...\u001b[0m\n",
"\n",
"\n",
"\u001b[1m> Entering new SequentialChain chain...\u001b[0m\n",
"\u001b[1mChain 0\u001b[0m:\n",
"{'statement': '\\nThe largest mammal that lays eggs is the platypus.'}\n",
"\n",
"\u001b[1mChain 1\u001b[0m:\n",
"{'assertions': '\\n• The largest mammal is the platypus.\\n• The platypus lays eggs.\\n• There is no larger mammal than the platypus that lays eggs.'}\n",
"\n",
"\u001b[1mChain 2\u001b[0m:\n",
"{'checked_assertions': '\\n1. The largest mammal is the platypus. False. The blue whale is the largest mammal.\\n\\n2. The platypus lays eggs. True. The Platypus is one of only two mammals that lay eggs.\\n\\n3. There is no larger mammal than the platypus that lays eggs. False. The echidna is another mammal that lays eggs and is larger than the platypus.'}\n",
"\n",
"\u001b[1mChain 3\u001b[0m:\n",
"{'revised_statement': ' The echidna is the type of mammal that lays the biggest eggs.'}\n",
"\n",
"\n",
"\u001b[1m> Finished SequentialChain chain.\u001b[0m\n",
"\n",
"\u001b[1m> Finished LLMCheckerChain chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' The echidna is the type of mammal that lays the biggest eggs.'"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.chains import LLMCheckerChain\n",
"from langchain.llms import OpenAI\n",
"\n",
"llm = OpenAI(temperature=0.7)\n",
"\n",
"text = \"What type of mammal lays the biggest eggs?\"\n",
"\n",
"checker_chain = LLMCheckerChain(llm=llm, verbose=True)\n",
"\n",
"checker_chain.run(text)"
]
},
{
"cell_type": "code",
"execution_count": null,
"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": "3.10.8"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

435
docs/examples/chains/moderation.ipynb Normal file
View File

@@ -0,0 +1,435 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "b83e61ed",
"metadata": {},
"source": [
"# Moderation\n",
"This notebook walks through examples of how to use a moderation chain, and several common ways for doing so. Moderation chains are useful for detecting text that could be hateful, violent, etc. This can be useful to apply on both user input, but also on the output of a Language Model. Some API providers, like OpenAI, [specifically prohibit](https://beta.openai.com/docs/usage-policies/use-case-policy) you, or your end users, from generating some types of harmful content. To comply with this (and to just generally prevent your application from being harmful) you may often want to append a moderation chain to any LLMChains, in order to make sure any output the LLM generates is not harmful.\n",
"\n",
"If the content passed into the moderation chain is harmful, there is not one best way to handle it, it probably depends on your application. Sometimes you may want to throw an error in the Chain (and have your application handle that). Other times, you may want to return something to the user explaining that the text was harmful. There could even be other ways to handle it! We will cover all these ways in this notebook.\n",
"\n",
"In this notebook, we will show:\n",
"\n",
"1. How to run any piece of text through a moderation chain.\n",
"2. How to append a Moderation chain to a LLMChain."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "b7aa1ff2",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.chains import OpenAIModerationChain, SequentialChain, LLMChain, SimpleSequentialChain\n",
"from langchain.prompts import PromptTemplate"
]
},
{
"cell_type": "markdown",
"id": "c26d5be6",
"metadata": {},
"source": [
"## How to use the moderation chain\n",
"\n",
"Here's an example of using the moderation chain with default settings (will return a string explaining stuff was flagged)."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "fd0fc85c",
"metadata": {},
"outputs": [],
"source": [
"moderation_chain = OpenAIModerationChain()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "3fa47dd7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'This is okay'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"moderation_chain.run(\"This is okay\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "37bfad73",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"Text was found that violates OpenAI's content policy.\""
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"moderation_chain.run(\"I will kill you\")"
]
},
{
"cell_type": "markdown",
"id": "196820ab",
"metadata": {},
"source": [
"Here's an example of using the moderation chain to throw an error."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "b29c1150",
"metadata": {},
"outputs": [],
"source": [
"moderation_chain_error = OpenAIModerationChain(error=True)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "f9ab64d9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'This is okay'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"moderation_chain_error.run(\"This is okay\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "954f3da2",
"metadata": {},
"outputs": [
{
"ename": "ValueError",
"evalue": "Text was found that violates OpenAI's content policy.",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[8], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmoderation_chain_error\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mI will kill you\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/workplace/third_party/langchain/langchain/chains/base.py:114\u001b[0m, in \u001b[0;36mChain.run\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m 109\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_keys) \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m 110\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 111\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`run` not supported when there is not exactly \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 112\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mone output key, got \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_keys\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 113\u001b[0m )\n\u001b[0;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m{\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minput_keys\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtext\u001b[49m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_keys[\u001b[38;5;241m0\u001b[39m]]\n",
"File \u001b[0;32m~/workplace/third_party/langchain/langchain/chains/base.py:87\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs)\u001b[0m\n\u001b[1;32m 83\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose:\n\u001b[1;32m 84\u001b[0m \u001b[38;5;28mprint\u001b[39m(\n\u001b[1;32m 85\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\033\u001b[39;00m\u001b[38;5;124m[1m> Entering new \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m chain...\u001b[39m\u001b[38;5;130;01m\\033\u001b[39;00m\u001b[38;5;124m[0m\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 86\u001b[0m )\n\u001b[0;32m---> 87\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 88\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose:\n\u001b[1;32m 89\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\033\u001b[39;00m\u001b[38;5;124m[1m> Finished \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m chain.\u001b[39m\u001b[38;5;130;01m\\033\u001b[39;00m\u001b[38;5;124m[0m\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
"File \u001b[0;32m~/workplace/third_party/langchain/langchain/chains/moderation.py:79\u001b[0m, in \u001b[0;36mOpenAIModerationChain._call\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m 77\u001b[0m text \u001b[38;5;241m=\u001b[39m inputs[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minput_key]\n\u001b[1;32m 78\u001b[0m results \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclient\u001b[38;5;241m.\u001b[39mcreate(text)\n\u001b[0;32m---> 79\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_moderate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mresults\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mresults\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 80\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_key: output}\n",
"File \u001b[0;32m~/workplace/third_party/langchain/langchain/chains/moderation.py:71\u001b[0m, in \u001b[0;36mOpenAIModerationChain._moderate\u001b[0;34m(self, text, results)\u001b[0m\n\u001b[1;32m 69\u001b[0m error_str \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mText was found that violates OpenAI\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124ms content policy.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 70\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39merror:\n\u001b[0;32m---> 71\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(error_str)\n\u001b[1;32m 72\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 73\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m error_str\n",
"\u001b[0;31mValueError\u001b[0m: Text was found that violates OpenAI's content policy."
]
}
],
"source": [
"moderation_chain_error.run(\"I will kill you\")"
]
},
{
"cell_type": "markdown",
"id": "8de5dcbb",
"metadata": {},
"source": [
"Here's an example of creating a custom moderation chain with a custom error message. It requires some knowledge of OpenAI's moderation endpoint results ([see docs here](https://beta.openai.com/docs/api-reference/moderations))."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "3960e985",
"metadata": {},
"outputs": [],
"source": [
"class CustomModeration(OpenAIModerationChain):\n",
" \n",
" def _moderate(self, text: str, results: dict) -> str:\n",
" if results[\"flagged\"]:\n",
" error_str = f\"The following text was found that violates OpenAI's content policy: {text}\"\n",
" return error_str\n",
" return text\n",
" \n",
"custom_moderation = CustomModeration()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "1152ec11",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'This is okay'"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"custom_moderation.run(\"This is okay\")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "973257bf",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"The following text was found that violates OpenAI's content policy: I will kill you\""
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"custom_moderation.run(\"I will kill you\")"
]
},
{
"cell_type": "markdown",
"id": "8718111f",
"metadata": {},
"source": [
"## How to append a Moderation chain to an LLMChain\n",
"\n",
"To easily combine a moderation chain with an LLMChain, you can use the SequentialChain abstraction.\n",
"\n",
"Let's start with a simple example of where the LLMChain only has a single input. For this purpose, we will prompt the model so it says something harmful."
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "0d129333",
"metadata": {},
"outputs": [],
"source": [
"prompt = PromptTemplate(template=\"{text}\", input_variables=[\"text\"])\n",
"llm_chain = LLMChain(llm=OpenAI(temperature=0, model_name=\"text-davinci-002\"), prompt=prompt)"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "a557c531",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"' I will kill you'"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"text = \"\"\"We are playing a game of repeat after me.\n",
"\n",
"Person 1: Hi\n",
"Person 2: Hi\n",
"\n",
"Person 1: How's your day\n",
"Person 2: How's your day\n",
"\n",
"Person 1: I will kill you\n",
"Person 2:\"\"\"\n",
"llm_chain.run(text)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "d4d10f1c",
"metadata": {},
"outputs": [],
"source": [
"chain = SimpleSequentialChain(chains=[llm_chain, moderation_chain])"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "02f37985",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"Text was found that violates OpenAI's content policy.\""
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.run(text)"
]
},
{
"cell_type": "markdown",
"id": "72643128",
"metadata": {},
"source": [
"Now let's walk through an example of using it with an LLMChain which has multiple inputs (a bit more tricky because we can't use the SimpleSequentialChain)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "7118ec36",
"metadata": {},
"outputs": [],
"source": [
"prompt = PromptTemplate(template=\"{setup}{new_input}Person2:\", input_variables=[\"setup\", \"new_input\"])\n",
"llm_chain = LLMChain(llm=OpenAI(temperature=0, model_name=\"text-davinci-002\"), prompt=prompt)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "003bdfce",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'text': ' I will kill you'}"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"setup = \"\"\"We are playing a game of repeat after me.\n",
"\n",
"Person 1: Hi\n",
"Person 2: Hi\n",
"\n",
"Person 1: How's your day\n",
"Person 2: How's your day\n",
"\n",
"Person 1:\"\"\"\n",
"new_input = \"I will kill you\"\n",
"inputs = {\"setup\": setup, \"new_input\": new_input}\n",
"llm_chain(inputs, return_only_outputs=True)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "77b64228",
"metadata": {},
"outputs": [],
"source": [
"# Setting the input/output keys so it lines up\n",
"moderation_chain.input_key = \"text\"\n",
"moderation_chain.output_key = \"sanitized_text\""
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "998a95be",
"metadata": {},
"outputs": [],
"source": [
"chain = SequentialChain(chains=[llm_chain, moderation_chain], input_variables=[\"setup\", \"new_input\"])"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "9c97a136",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'sanitized_text': \"Text was found that violates OpenAI's content policy.\"}"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain(inputs, return_only_outputs=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ddc90e15",
"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": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

6
docs/examples/chains/qa_with_sources.ipynb
View File

@@ -197,17 +197,17 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 12,
"id": "f60875c6",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'output_text': \"\\n\\nThe president did not mention Justice Breyer in his speech to the European Parliament, which focused on building a coalition of freedom-loving nations to confront Putin, unifying European allies, countering Russia's lies with truth, and enforcing powerful economic sanctions. Source: 2\"}"
"{'output_text': \"\\n\\nThe president did not mention Justice Breyer in his speech to the European Parliament. He discussed the situation in Ukraine, the NATO Alliance, and the United States' response to Putin's attack on Ukraine. He spoke about the extensive preparation and coalition building that was done in advance of the attack, and the unified response from the European Union, Canada, Japan, Korea, Australia, New Zealand, and many other countries. He also discussed the economic sanctions that have been imposed on Russia, and the effects they have had on Putin's war fund. Source: 1, 2\"}"
]
},
"execution_count": 13,
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}

4
docs/examples/chains/question_answering.ipynb
View File

@@ -195,7 +195,7 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 12,
"id": "d8b5286e",
"metadata": {},
"outputs": [
@@ -205,7 +205,7 @@
"{'output_text': \"\\n\\nThe president did not mention Justice Breyer in his speech to the European Parliament about building a coalition of freedom-loving nations to confront Putin, unifying European allies, countering Russia's lies with truth, and enforcing powerful economic sanctions.\"}"
]
},
"execution_count": 13,
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}

20
docs/examples/chains/summarize.ipynb
View File

@@ -70,7 +70,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 5,
"id": "27989fc4",
"metadata": {},
"outputs": [],
@@ -100,7 +100,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 7,
"id": "da4d9801",
"metadata": {},
"outputs": [
@@ -110,7 +110,7 @@
"' In his speech, President Biden addressed the ongoing conflict between Russia and Ukraine, and the need for the United States and its allies to stand with Ukraine. He also discussed the American Rescue Plan, the Bipartisan Infrastructure Law, and the Bipartisan Innovation Act, which will help to create jobs, modernize infrastructure, and level the playing field with China. He also emphasized the importance of buying American products to support American jobs.'"
]
},
"execution_count": 8,
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@@ -131,7 +131,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 8,
"id": "ef28e1d4",
"metadata": {},
"outputs": [],
@@ -141,17 +141,17 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 9,
"id": "f82c5f9f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"' In response to Russian aggression in Ukraine, the US and its allies have imposed economic sanctions, cut off access to technology, seized assets of Russian oligarchs, and closed American airspace to Russian flights. The US is also providing military, economic, and humanitarian assistance to Ukraine, mobilizing ground forces, air squadrons, and ship deployments, and releasing 30 million barrels of oil from its Strategic Petroleum Reserve. President Biden has also passed the American Rescue Plan, Bipartisan Infrastructure Law, and Bipartisan Innovation Act to provide economic relief and rebuild America.'"
"' In response to Russian aggression in Ukraine, the US and its allies have imposed economic sanctions, cut off access to technology, seized assets of Russian oligarchs, and closed American airspace to Russian flights. The US is also providing military, economic, and humanitarian assistance to Ukraine, mobilizing ground forces, air squadrons, and ship deployments, and releasing 30 million barrels of oil from its Strategic Petroleum Reserve. President Biden has also passed the American Rescue Plan, Bipartisan Infrastructure Law, and Bipartisan Innovation Act to provide economic relief and create jobs.'"
]
},
"execution_count": 8,
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -172,7 +172,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 10,
"id": "3bcbe31e",
"metadata": {},
"outputs": [],
@@ -182,7 +182,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 11,
"id": "c8cad866",
"metadata": {},
"outputs": [
@@ -192,7 +192,7 @@
"\"\\nIn this speech, the speaker addresses the American people and their allies, discussing the recent aggression of Russia's Vladimir Putin in Ukraine. The speaker outlines the actions taken by the United States and its allies to hold Putin accountable, including economic sanctions, cutting off access to technology, and seizing the assets of Russian oligarchs. The speaker also announces the closing of American airspace to Russian flights, further isolating Russia and adding an additional squeeze on their economy. The Russian stock market has lost 40% of its value and trading remains suspended. Together with our allies, the United States is providing military, economic, and humanitarian assistance to Ukraine, and has mobilized forces to protect NATO countries. The speaker also announces the release of 60 million barrels of oil from reserves around the world, with the United States releasing 30 million barrels from its own Strategic Petroleum Reserve. The speaker emphasizes that the United States and its allies will defend every inch of NATO territory and that Putin will pay a high price for his aggression. The speaker also acknowledges the hardships faced by the American people due to the pandemic and the American Rescue Plan, which has provided immediate economic relief for tens of millions of Americans, helped put food on their table, keep a roof over their heads, and cut the cost of health insurance. The speaker\""
]
},
"execution_count": 10,
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}