Archives
/
langchain
mirror of https://github.com/hwchase17/langchain
2
0
Fork 1
Code Issues Packages Projects Releases Wiki Activity

Chatbots use case (#8554)

Browse Source 
Co-authored-by: Bagatur <baskaryan@gmail.com>
pull/8759/head
Lance Martin 1 year ago committed by GitHub
parent 115a77142a
commit be638ad77d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 727 additions and 502 deletions
Show Stats Download Patch File Download Diff File

BIN
docs/docs_skeleton/static/img/chat_use_case.png
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 93 KiB

BIN
docs/docs_skeleton/static/img/chat_use_case_2.png
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 102 KiB

727
docs/extras/use_cases/chatbots.ipynb
Unescape Escape View File

@ -0,0 +1,727 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "ee7f95e4",
"metadata": {},
"source": [
"# Chatbots\n",
"\n",
"[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/chatbots/chatbots.ipynb)\n",
"\n",
"## Use case\n",
"\n",
"Chatbots are one of the central LLM use-cases. The core features of chatbots are that they can have long-running conversations and have access to information that users want to know about.\n",
"\n",
"Aside from basic prompting and LLMs, memory and retrieval are the core components of a chatbot. Memory allows a chatbot to remember past interactions, and retrieval provides a chatbot with up-to-date, domain-specific information."
]
},
{
"cell_type": "markdown",
"id": "56615b45",
"metadata": {},
"source": [
"![Image description](/img/chat_use_case.png)"
]
},
{
"cell_type": "markdown",
"id": "ff48f490",
"metadata": {},
"source": [
"## Overview\n",
"\n",
"The chat model interface is based around messages rather than raw text. Several components are important to consider for chat:\n",
"\n",
"* `chat model`: See [here](/docs/integrations/chat) for a list of chat model integrations and [here](/docs/modules/model_io/models/chat) for documentation on the chat model interface in LangChain. You can use `LLMs` (see [here](/docs/modules/model_io/models/llms)) for chatbots as well, but chat models have a more conversational tone and natively support a message interface.\n",
"* `prompt template`: Prompt templates make it easy to assemble prompts that combine default messages, user input, chat history, and (optionally) additional retrieved context.\n",
"* `memory`: [See here](/docs/modules/memory/) for in-depth documentation on memory types\n",
"* `retriever` (optional): [See here](/docs/modules/data_connection/retrievers) for in-depth documentation on retrieval systems. These are useful if you want to build a chatbot with domain-specific knowledge.\n",
"\n",
"## Quickstart\n",
"\n",
"Here's a quick preview of how we can create chatbot interfaces. First let's install some dependencies and set the required credentials:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5070a1fd",
"metadata": {},
"outputs": [],
"source": [
"!pip install langchain openai \n",
"\n",
"# Set env var OPENAI_API_KEY or load from a .env file:\n",
"# import dotenv\n",
"# dotenv.load_env()"
]
},
{
"cell_type": "markdown",
"id": "88197b95",
"metadata": {},
"source": [
"With a plain chat model, we can get chat completions by [passing one or more messages](/docs/modules/model_io/models/chat) to the model.\n",
"\n",
"The chat model will respond with a message."
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "5b0d84ae",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content=\"J'adore la programmation.\", additional_kwargs={}, example=False)"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.schema import (\n",
" AIMessage,\n",
" HumanMessage,\n",
" SystemMessage\n",
")\n",
"from langchain.chat_models import ChatOpenAI\n",
"\n",
"chat = ChatOpenAI()\n",
"chat([HumanMessage(content=\"Translate this sentence from English to French: I love programming.\")])"
]
},
{
"cell_type": "markdown",
"id": "7935d9a5",
"metadata": {},
"source": [
"And if we pass in a list of messages:"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "afd27a9f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content=\"J'adore la programmation.\", additional_kwargs={}, example=False)"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"messages = [\n",
" SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
" HumanMessage(content=\"I love programming.\")\n",
"]\n",
"chat(messages)"
]
},
{
"cell_type": "markdown",
"id": "c7a1d169",
"metadata": {},
"source": [
"We can then wrap our chat model in a `ConversationChain`, which has built-in memory for remembering past user inputs and model outputs."
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "fdb05d74",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Je adore la programmation.'"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.chains import ConversationChain \n",
" \n",
"conversation = ConversationChain(llm=chat) \n",
"conversation.run(\"Translate this sentence from English to French: I love programming.\") "
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "d801a173",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Ich liebe Programmieren.'"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation.run(\"Translate it to German.\") "
]
},
{
"cell_type": "markdown",
"id": "9e86788c",
"metadata": {},
"source": [
"## Memory \n",
"\n",
"As we mentioned above, the core component of chatbots is the memory system. One of the simplest and most commonly used forms of memory is `ConversationBufferMemory`:\n",
"* This memory allows for storing of messages in a `buffer`\n",
"* When called in a chain, it returns all of the messages it has stored\n",
"\n",
"LangChain comes with many other types of memory, too. [See here](/docs/modules/memory/) for in-depth documentation on memory types.\n",
"\n",
"For now let's take a quick look at ConversationBufferMemory. We can manually add a few chat messages to the memory like so:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "1380a4ea",
"metadata": {},
"outputs": [],
"source": [
"from langchain.memory import ConversationBufferMemory\n",
"\n",
"memory = ConversationBufferMemory()\n",
"memory.chat_memory.add_user_message(\"hi!\")\n",
"memory.chat_memory.add_ai_message(\"whats up?\")"
]
},
{
"cell_type": "markdown",
"id": "a3d5d1f8",
"metadata": {},
"source": [
"And now we can load from our memory. The key method exposed by all `Memory` classes is `load_memory_variables`. This takes in any initial chain input and returns a list of memory variables which are added to the chain input. \n",
"\n",
"Since this simple memory type doesn't actually take into account the chain input when loading memory, we can pass in an empty input for now:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "982467e7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': 'Human: hi!\\nAI: whats up?'}"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({})"
]
},
{
"cell_type": "markdown",
"id": "7c1b20d4",
"metadata": {},
"source": [
"We can also keep a sliding window of the most recent `k` interactions using `ConversationBufferWindowMemory`."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "f72b9ff7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': 'Human: not much you\\nAI: not much'}"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.memory import ConversationBufferWindowMemory\n",
"\n",
"memory = ConversationBufferWindowMemory(k=1)\n",
"memory.save_context({\"input\": \"hi\"}, {\"output\": \"whats up\"})\n",
"memory.save_context({\"input\": \"not much you\"}, {\"output\": \"not much\"})\n",
"memory.load_memory_variables({})"
]
},
{
"cell_type": "markdown",
"id": "7b84f90a",
"metadata": {},
"source": [
"`ConversationSummaryMemory` is an extension of this theme.\n",
"\n",
"It creates a summary of the conversation over time. \n",
"\n",
"This memory is most useful for longer conversations where the full message history would consume many tokens."
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "ca2596ed",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.memory import ConversationSummaryMemory\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"memory = ConversationSummaryMemory(llm=llm)\n",
"memory.save_context({\"input\": \"hi\"},{\"output\": \"whats up\"})\n",
"memory.save_context({\"input\": \"im working on better docs for chatbots\"},{\"output\": \"oh, that sounds like a lot of work\"})\n",
"memory.save_context({\"input\": \"yes, but it's worth the effort\"},{\"output\": \"agreed, good docs are important!\"})"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "060f69b7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': '\\nThe human greets the AI, to which the AI responds. The human then mentions they are working on better docs for chatbots, to which the AI responds that it sounds like a lot of work. The human agrees that it is worth the effort, and the AI agrees that good docs are important.'}"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({})"
]
},
{
"cell_type": "markdown",
"id": "4bf036f6",
"metadata": {},
"source": [
"`ConversationSummaryBufferMemory` extends this a bit further:\n",
"\n",
"It uses token length rather than number of interactions to determine when to flush interactions."
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "38b42728",
"metadata": {},
"outputs": [],
"source": [
"from langchain.memory import ConversationSummaryBufferMemory\n",
"memory = ConversationSummaryBufferMemory(llm=llm, max_token_limit=10)\n",
"memory.save_context({\"input\": \"hi\"}, {\"output\": \"whats up\"})\n",
"memory.save_context({\"input\": \"not much you\"}, {\"output\": \"not much\"})"
]
},
{
"cell_type": "markdown",
"id": "ff0db09f",
"metadata": {},
"source": [
"## Conversation \n",
"\n",
"We can unpack what goes under the hood with `ConversationChain`. \n",
"\n",
"We can specify our memory, `ConversationSummaryMemory` and we can specify the prompt. "
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "fccd6995",
"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;3mSystem: You are a nice chatbot having a conversation with a human.\n",
"Human: hi\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'question': 'hi',\n",
" 'chat_history': [HumanMessage(content='hi', additional_kwargs={}, example=False),\n",
" AIMessage(content='Hello! How can I assist you today?', additional_kwargs={}, example=False)],\n",
" 'text': 'Hello! How can I assist you today?'}"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.prompts import (\n",
" ChatPromptTemplate,\n",
" MessagesPlaceholder,\n",
" SystemMessagePromptTemplate,\n",
" HumanMessagePromptTemplate,\n",
")\n",
"from langchain.chains import LLMChain\n",
"\n",
"# LLM\n",
"llm = ChatOpenAI()\n",
"\n",
"# Prompt \n",
"prompt = ChatPromptTemplate(\n",
" messages=[\n",
" SystemMessagePromptTemplate.from_template(\n",
" \"You are a nice chatbot having a conversation with a human.\"\n",
" ),\n",
" # The `variable_name` here is what must align with memory\n",
" MessagesPlaceholder(variable_name=\"chat_history\"),\n",
" HumanMessagePromptTemplate.from_template(\"{question}\")\n",
" ]\n",
")\n",
"\n",
"# Notice that we `return_messages=True` to fit into the MessagesPlaceholder\n",
"# Notice that `\"chat_history\"` aligns with the MessagesPlaceholder name\n",
"memory = ConversationBufferMemory(memory_key=\"chat_history\",return_messages=True)\n",
"conversation = LLMChain(\n",
" llm=llm,\n",
" prompt=prompt,\n",
" verbose=True,\n",
" memory=memory\n",
")\n",
"\n",
"# Notice that we just pass in the `question` variables - `chat_history` gets populated by memory\n",
"conversation({\"question\": \"hi\"})"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "eb0cadfd",
"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;3mSystem: You are a nice chatbot having a conversation with a human.\n",
"Human: hi\n",
"AI: Hello! How can I assist you today?\n",
"Human: Translate this sentence from English to French: I love programming.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'question': 'Translate this sentence from English to French: I love programming.',\n",
" 'chat_history': [HumanMessage(content='hi', additional_kwargs={}, example=False),\n",
" AIMessage(content='Hello! How can I assist you today?', additional_kwargs={}, example=False),\n",
" HumanMessage(content='Translate this sentence from English to French: I love programming.', additional_kwargs={}, example=False),\n",
" AIMessage(content='Sure! The translation of \"I love programming\" from English to French is \"J\\'adore programmer.\"', additional_kwargs={}, example=False)],\n",
" 'text': 'Sure! The translation of \"I love programming\" from English to French is \"J\\'adore programmer.\"'}"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation({\"question\": \"Translate this sentence from English to French: I love programming.\"})"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "c56d6219",
"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;3mSystem: You are a nice chatbot having a conversation with a human.\n",
"Human: hi\n",
"AI: Hello! How can I assist you today?\n",
"Human: Translate this sentence from English to French: I love programming.\n",
"AI: Sure! The translation of \"I love programming\" from English to French is \"J'adore programmer.\"\n",
"Human: Now translate the sentence to German.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"{'question': 'Now translate the sentence to German.',\n",
" 'chat_history': [HumanMessage(content='hi', additional_kwargs={}, example=False),\n",
" AIMessage(content='Hello! How can I assist you today?', additional_kwargs={}, example=False),\n",
" HumanMessage(content='Translate this sentence from English to French: I love programming.', additional_kwargs={}, example=False),\n",
" AIMessage(content='Sure! The translation of \"I love programming\" from English to French is \"J\\'adore programmer.\"', additional_kwargs={}, example=False),\n",
" HumanMessage(content='Now translate the sentence to German.', additional_kwargs={}, example=False),\n",
" AIMessage(content='Certainly! The translation of \"I love programming\" from English to German is \"Ich liebe das Programmieren.\"', additional_kwargs={}, example=False)],\n",
" 'text': 'Certainly! The translation of \"I love programming\" from English to German is \"Ich liebe das Programmieren.\"'}"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation({\"question\": \"Now translate the sentence to German.\"})"
]
},
{
"cell_type": "markdown",
"id": "43858489",
"metadata": {},
"source": [
"We can see the chat history preserved in the prompt using the [LangSmith trace](https://smith.langchain.com/public/dce34c57-21ca-4283-9020-a8e0d78a59de/r).\n",
"\n",
"![Image description](/img/chat_use_case_2.png)"
]
},
{
"cell_type": "markdown",
"id": "3f35cc16",
"metadata": {},
"source": [
"## Chat Retrieval\n",
"\n",
"Now, suppose we want to [chat with documents](https://twitter.com/mayowaoshin/status/1640385062708424708?s=20) or some other source of knowledge.\n",
"\n",
"This is popular use case, combining chat with [document retrieval](/docs/use_cases/question_answering).\n",
"\n",
"It allows us to chat with specific information that the model was not trained on."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1a01e7b5",
"metadata": {},
"outputs": [],
"source": [
"!pip install tiktoken chromadb"
]
},
{
"cell_type": "markdown",
"id": "88e220de",
"metadata": {},
"source": [
"Load a blog post."
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "1b99b36c",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import WebBaseLoader\n",
"\n",
"loader = WebBaseLoader(\"https://lilianweng.github.io/posts/2023-06-23-agent/\")\n",
"data = loader.load()"
]
},
{
"cell_type": "markdown",
"id": "3662ce79",
"metadata": {},
"source": [
"Split and store this in a vector."
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "058f1541",
"metadata": {},
"outputs": [],
"source": [
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
"\n",
"text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
"all_splits = text_splitter.split_documents(data)\n",
"\n",
"from langchain.embeddings import OpenAIEmbeddings\n",
"from langchain.vectorstores import Chroma\n",
"\n",
"vectorstore = Chroma.from_documents(documents=all_splits, embedding=OpenAIEmbeddings())"
]
},
{
"cell_type": "markdown",
"id": "603d9441",
"metadata": {},
"source": [
"Create our memory, as before, but's let's use `ConversationSummaryMemory`."
]
},
{
"cell_type": "code",
"execution_count": 37,
"id": "f89fd3f5",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationSummaryMemory(llm=llm,memory_key=\"chat_history\",return_messages=True)"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "28503423",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.chains import ConversationalRetrievalChain\n",
"\n",
"llm = ChatOpenAI()\n",
"retriever = vectorstore.as_retriever()\n",
"qa = ConversationalRetrievalChain.from_llm(llm, retriever=retriever, memory=memory)"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "a9c3bd5e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'question': 'How do agents use Task decomposition?',\n",
" 'chat_history': [SystemMessage(content='', additional_kwargs={})],\n",
" 'answer': 'Agents can use task decomposition in several ways:\\n\\n1. Simple prompting: Agents can use Language Model based prompting to break down tasks into subgoals. For example, by providing prompts like \"Steps for XYZ\" or \"What are the subgoals for achieving XYZ?\", the agent can generate a sequence of smaller steps that lead to the completion of the overall task.\\n\\n2. Task-specific instructions: Agents can be given task-specific instructions to guide their planning process. For example, if the task is to write a novel, the agent can be instructed to \"Write a story outline.\" This provides a high-level structure for the task and helps in breaking it down into smaller components.\\n\\n3. Human inputs: Agents can also take inputs from humans to decompose tasks. This can be done through direct communication or by leveraging human expertise. Humans can provide guidance and insights to help the agent break down complex tasks into manageable subgoals.\\n\\nOverall, task decomposition allows agents to break down large tasks into smaller, more manageable subgoals, enabling them to plan and execute complex tasks efficiently.'}"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"qa(\"How do agents use Task decomposition?\")"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "a29a7713",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'question': 'What are the various ways to implemet memory to support it?',\n",
" 'chat_history': [SystemMessage(content='The human asks how agents use task decomposition. The AI explains that agents can use task decomposition in several ways, including simple prompting, task-specific instructions, and human inputs. Task decomposition allows agents to break down large tasks into smaller, more manageable subgoals, enabling them to plan and execute complex tasks efficiently.', additional_kwargs={})],\n",
" 'answer': 'There are several ways to implement memory to support task decomposition:\\n\\n1. Long-Term Memory Management: This involves storing and organizing information in a long-term memory system. The agent can retrieve past experiences, knowledge, and learned strategies to guide the task decomposition process.\\n\\n2. Internet Access: The agent can use internet access to search for relevant information and gather resources to aid in task decomposition. This allows the agent to access a vast amount of information and utilize it in the decomposition process.\\n\\n3. GPT-3.5 Powered Agents: The agent can delegate simple tasks to GPT-3.5 powered agents. These agents can perform specific tasks or provide assistance in task decomposition, allowing the main agent to focus on higher-level planning and decision-making.\\n\\n4. File Output: The agent can store the results of task decomposition in files or documents. This allows for easy retrieval and reference during the execution of the task.\\n\\nThese memory resources help the agent in organizing and managing information, making informed decisions, and effectively decomposing complex tasks into smaller, manageable subgoals.'}"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"qa(\"What are the various ways to implemet memory to support it?\")"
]
},
{
"cell_type": "markdown",
"id": "d5e8d5f4",
"metadata": {},
"source": [
"Again, we can use the [LangSmith trace](https://smith.langchain.com/public/18460363-0c70-4c72-81c7-3b57253bb58c/r) to explore the prompt structure.\n",
"\n",
"### Going deeper \n",
"\n",
"* Agents, such as the [conversational retrieval agent](/docs/use_cases/question_answering/how_to/conversational_retrieval_agents), can be used for retrieval when necessary while also holding a conversation.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1ff8925f-4c21-4680-a9cd-3670ad4852b3",
"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
}

20
docs/extras/use_cases/chatbots/index.mdx
Unescape Escape View File

@ -1,20 +0,0 @@
---
sidebar_position: 4
---
# Chatbots
Since language models are good at producing text, that makes them ideal for creating chatbots.
Aside from the base prompts/LLMs, an important concept to know for Chatbots is `memory`.
Most chat based applications rely on remembering what happened in previous interactions, which `memory` is designed to help with.
The following resources exist:
- [ChatGPT Clone](/docs/modules/agents/how_to/chatgpt_clone.html): A notebook walking through how to recreate a ChatGPT-like experience with LangChain.
- [Conversation Agent](/docs/modules/agents/agent_types/chat_conversation_agent.html): A notebook walking through how to create an agent optimized for conversation.
Additional related resources include:
- [Memory concepts and examples](/docs/modules/memory/): Explanation of key concepts related to memory along with how-to's and examples.
More end-to-end examples include:
- [Voice Assistant](./voice_assistant.html): A notebook walking through how to create a voice assistant using LangChain.

482
docs/extras/use_cases/chatbots/voice_assistant.ipynb
Unescape Escape View File

@ -1,482 +0,0 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Voice Assistant\n",
"\n",
"This chain creates a clone of ChatGPT with a few modifications to make it a voice assistant. \n",
"It uses the `pyttsx3` and `speech_recognition` libraries to convert text to speech and speech to text respectively. The prompt template is also changed to make it more suitable for voice assistant use."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"from langchain import OpenAI, LLMChain, PromptTemplate\n",
"from langchain.memory import ConversationBufferWindowMemory\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"{history}\n",
"Human: {human_input}\n",
"Assistant:\"\"\"\n",
"\n",
"prompt = PromptTemplate(input_variables=[\"history\", \"human_input\"], template=template)\n",
"\n",
"\n",
"chatgpt_chain = LLMChain(\n",
" llm=OpenAI(temperature=0),\n",
" prompt=prompt,\n",
" verbose=True,\n",
" memory=ConversationBufferWindowMemory(k=2),\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"import speech_recognition as sr\n",
"import pyttsx3\n",
"\n",
"engine = pyttsx3.init()\n",
"\n",
"\n",
"def listen():\n",
" r = sr.Recognizer()\n",
" with sr.Microphone() as source:\n",
" print(\"Calibrating...\")\n",
" r.adjust_for_ambient_noise(source, duration=5)\n",
" # optional parameters to adjust microphone sensitivity\n",
" # r.energy_threshold = 200\n",
" # r.pause_threshold=0.5\n",
"\n",
" print(\"Okay, go!\")\n",
" while 1:\n",
" text = \"\"\n",
" print(\"listening now...\")\n",
" try:\n",
" audio = r.listen(source, timeout=5, phrase_time_limit=30)\n",
" print(\"Recognizing...\")\n",
" # whisper model options are found here: https://github.com/openai/whisper#available-models-and-languages\n",
" # other speech recognition models are also available.\n",
" text = r.recognize_whisper(\n",
" audio,\n",
" model=\"medium.en\",\n",
" show_dict=True,\n",
" )[\"text\"]\n",
" except Exception as e:\n",
" unrecognized_speech_text = (\n",
" f\"Sorry, I didn't catch that. Exception was: {e}s\"\n",
" )\n",
" text = unrecognized_speech_text\n",
" print(text)\n",
"\n",
" response_text = chatgpt_chain.predict(human_input=text)\n",
" print(response_text)\n",
" engine.say(response_text)\n",
" engine.runAndWait()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Calibrating...\n",
"Okay, go!\n",
"listening now...\n",
"Recognizing...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\jaden\\AppData\\Roaming\\Python\\Python310\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" Hello, Assistant. What's going on?\n",
"\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"\n",
"Human: Hello, Assistant. What's going on?\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Hi there! It's great to hear from you. I'm doing well. How can I help you today?\n",
"listening now...\n",
"Recognizing...\n",
" That's cool. Isn't that neat? Yeah, I'm doing great.\n",
"\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Hello, Assistant. What's going on?\n",
"AI: Hi there! It's great to hear from you. I'm doing well. How can I help you today?\n",
"Human: That's cool. Isn't that neat? Yeah, I'm doing great.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" That's great to hear! What can I do for you today?\n",
"listening now...\n",
"Recognizing...\n",
" Thank you.\n",
"\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Hello, Assistant. What's going on?\n",
"AI: Hi there! It's great to hear from you. I'm doing well. How can I help you today?\n",
"Human: That's cool. Isn't that neat? Yeah, I'm doing great.\n",
"AI: That's great to hear! What can I do for you today?\n",
"Human: Thank you.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" You're welcome! Is there anything else I can help you with?\n",
"listening now...\n",
"Recognizing...\n",
" I'd like to learn more about neural networks.\n",
"\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: That's cool. Isn't that neat? Yeah, I'm doing great.\n",
"AI: That's great to hear! What can I do for you today?\n",
"Human: Thank you.\n",
"AI: You're welcome! Is there anything else I can help you with?\n",
"Human: I'd like to learn more about neural networks.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Sure! Neural networks are a type of artificial intelligence that use a network of interconnected nodes to process data and make decisions. They are used in a variety of applications, from image recognition to natural language processing. Neural networks are often used to solve complex problems that are too difficult for traditional algorithms.\n",
"listening now...\n",
"Recognizing...\n",
" Tell me a fun fact about neural networks.\n",
"\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Thank you.\n",
"AI: You're welcome! Is there anything else I can help you with?\n",
"Human: I'd like to learn more about neural networks.\n",
"AI: Sure! Neural networks are a type of artificial intelligence that use a network of interconnected nodes to process data and make decisions. They are used in a variety of applications, from image recognition to natural language processing. Neural networks are often used to solve complex problems that are too difficult for traditional algorithms.\n",
"Human: Tell me a fun fact about neural networks.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Neural networks are inspired by the way the human brain works. They are composed of interconnected nodes that process data and make decisions, just like neurons in the brain. Neural networks can learn from their mistakes and improve their performance over time, just like humans do.\n",
"listening now...\n",
"Recognizing...\n",
" Tell me about a brand new discovered bird species.\n",
"\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: I'd like to learn more about neural networks.\n",
"AI: Sure! Neural networks are a type of artificial intelligence that use a network of interconnected nodes to process data and make decisions. They are used in a variety of applications, from image recognition to natural language processing. Neural networks are often used to solve complex problems that are too difficult for traditional algorithms.\n",
"Human: Tell me a fun fact about neural networks.\n",
"AI: Neural networks are inspired by the way the human brain works. They are composed of interconnected nodes that process data and make decisions, just like neurons in the brain. Neural networks can learn from their mistakes and improve their performance over time, just like humans do.\n",
"Human: Tell me about a brand new discovered bird species.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" A new species of bird was recently discovered in the Amazon rainforest. The species, called the Spix's Macaw, is a small, blue parrot that is believed to be extinct in the wild. It is the first new species of bird to be discovered in the Amazon in over 100 years.\n",
"listening now...\n",
"Recognizing...\n",
" Tell me a children's story about the importance of honesty and trust.\n",
"\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Tell me a fun fact about neural networks.\n",
"AI: Neural networks are inspired by the way the human brain works. They are composed of interconnected nodes that process data and make decisions, just like neurons in the brain. Neural networks can learn from their mistakes and improve their performance over time, just like humans do.\n",
"Human: Tell me about a brand new discovered bird species.\n",
"AI: A new species of bird was recently discovered in the Amazon rainforest. The species, called the Spix's Macaw, is a small, blue parrot that is believed to be extinct in the wild. It is the first new species of bird to be discovered in the Amazon in over 100 years.\n",
"Human: Tell me a children's story about the importance of honesty and trust.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Once upon a time, there was a young boy named Jack who lived in a small village. Jack was always honest and trustworthy, and his friends and family knew they could always count on him. One day, Jack was walking through the forest when he stumbled upon a magical tree. The tree told Jack that if he was honest and trustworthy, he would be rewarded with a special gift. Jack was so excited, and he promised to always be honest and trustworthy. Sure enough, the tree rewarded Jack with a beautiful golden apple. From that day forward, Jack was always honest and trustworthy, and he was rewarded with many more magical gifts. The moral of the story is that honesty and trust are the most important things in life.\n",
"listening now...\n",
"Recognizing...\n",
" Wow, Assistant, that was a really good story. Congratulations!\n",
"\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Tell me about a brand new discovered bird species.\n",
"AI: A new species of bird was recently discovered in the Amazon rainforest. The species, called the Spix's Macaw, is a small, blue parrot that is believed to be extinct in the wild. It is the first new species of bird to be discovered in the Amazon in over 100 years.\n",
"Human: Tell me a children's story about the importance of honesty and trust.\n",
"AI: Once upon a time, there was a young boy named Jack who lived in a small village. Jack was always honest and trustworthy, and his friends and family knew they could always count on him. One day, Jack was walking through the forest when he stumbled upon a magical tree. The tree told Jack that if he was honest and trustworthy, he would be rewarded with a special gift. Jack was so excited, and he promised to always be honest and trustworthy. Sure enough, the tree rewarded Jack with a beautiful golden apple. From that day forward, Jack was always honest and trustworthy, and he was rewarded with many more magical gifts. The moral of the story is that honesty and trust are the most important things in life.\n",
"Human: Wow, Assistant, that was a really good story. Congratulations!\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Thank you! I'm glad you enjoyed it.\n",
"listening now...\n",
"Recognizing...\n",
" Thank you.\n",
"\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Tell me a children's story about the importance of honesty and trust.\n",
"AI: Once upon a time, there was a young boy named Jack who lived in a small village. Jack was always honest and trustworthy, and his friends and family knew they could always count on him. One day, Jack was walking through the forest when he stumbled upon a magical tree. The tree told Jack that if he was honest and trustworthy, he would be rewarded with a special gift. Jack was so excited, and he promised to always be honest and trustworthy. Sure enough, the tree rewarded Jack with a beautiful golden apple. From that day forward, Jack was always honest and trustworthy, and he was rewarded with many more magical gifts. The moral of the story is that honesty and trust are the most important things in life.\n",
"Human: Wow, Assistant, that was a really good story. Congratulations!\n",
"AI: Thank you! I'm glad you enjoyed it.\n",
"Human: Thank you.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" You're welcome!\n",
"listening now...\n",
"Recognizing...\n",
" Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way? Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way?\n",
"\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Wow, Assistant, that was a really good story. Congratulations!\n",
"AI: Thank you! I'm glad you enjoyed it.\n",
"Human: Thank you.\n",
"AI: You're welcome!\n",
"Human: Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way? Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way?\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Yes, there are several online brands that offer photo editing and other creative tools without the need to download any software. Adobe Photoshop Express, Pixlr, and Fotor are some of the most popular online photo editing tools. Freq is an online music production platform that allows users to create and share music without downloading any software.\n",
"listening now...\n",
"Recognizing...\n",
" Our whole process of awesome is free.\n",
"\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Thank you.\n",
"AI: You're welcome!\n",
"Human: Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way? Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way?\n",
"AI: Yes, there are several online brands that offer photo editing and other creative tools without the need to download any software. Adobe Photoshop Express, Pixlr, and Fotor are some of the most popular online photo editing tools. Freq is an online music production platform that allows users to create and share music without downloading any software.\n",
"Human: Our whole process of awesome is free.\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" That's great! It's always nice to have access to free tools and resources.\n",
"listening now...\n",
"Recognizing...\n",
" No, I meant to ask, are those options that you mentioned free? No, I meant to ask, are those options that you mentioned free?\n",
"\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",
"Assistant is aware that human input is being transcribed from audio and as such there may be some errors in the transcription. It will attempt to account for some words being swapped with similar-sounding words or phrases. Assistant will also keep responses concise, because human attention spans are more limited over the audio channel since it takes time to listen to a response.\n",
"\n",
"Human: Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way? Do you know of online brands like Photoshop and Freq that you don't have to download in some sort of way?\n",
"AI: Yes, there are several online brands that offer photo editing and other creative tools without the need to download any software. Adobe Photoshop Express, Pixlr, and Fotor are some of the most popular online photo editing tools. Freq is an online music production platform that allows users to create and share music without downloading any software.\n",
"Human: Our whole process of awesome is free.\n",
"AI: That's great! It's always nice to have access to free tools and resources.\n",
"Human: No, I meant to ask, are those options that you mentioned free? No, I meant to ask, are those options that you mentioned free?\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
" Yes, the online brands I mentioned are all free to use. Adobe Photoshop Express, Pixlr, and Fotor are all free to use, and Freq is a free music production platform.\n",
"listening now...\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[6], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m listen(\u001b[39mNone\u001b[39;49;00m)\n",
"Cell \u001b[1;32mIn[5], line 20\u001b[0m, in \u001b[0;36mlisten\u001b[1;34m(command_queue)\u001b[0m\n\u001b[0;32m 18\u001b[0m \u001b[39mprint\u001b[39m(\u001b[39m'\u001b[39m\u001b[39mlistening now...\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[0;32m 19\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m---> 20\u001b[0m audio \u001b[39m=\u001b[39m r\u001b[39m.\u001b[39;49mlisten(source, timeout\u001b[39m=\u001b[39;49m\u001b[39m5\u001b[39;49m, phrase_time_limit\u001b[39m=\u001b[39;49m\u001b[39m30\u001b[39;49m)\n\u001b[0;32m 21\u001b[0m \u001b[39m# audio = r.record(source,duration = 5)\u001b[39;00m\n\u001b[0;32m 22\u001b[0m \u001b[39mprint\u001b[39m(\u001b[39m'\u001b[39m\u001b[39mRecognizing...\u001b[39m\u001b[39m'\u001b[39m)\n",
"File \u001b[1;32mc:\\ProgramData\\miniconda3\\envs\\lang\\lib\\site-packages\\speech_recognition\\__init__.py:523\u001b[0m, in \u001b[0;36mRecognizer.listen\u001b[1;34m(self, source, timeout, phrase_time_limit, snowboy_configuration)\u001b[0m\n\u001b[0;32m 520\u001b[0m \u001b[39mif\u001b[39;00m phrase_time_limit \u001b[39mand\u001b[39;00m elapsed_time \u001b[39m-\u001b[39m phrase_start_time \u001b[39m>\u001b[39m phrase_time_limit:\n\u001b[0;32m 521\u001b[0m \u001b[39mbreak\u001b[39;00m\n\u001b[1;32m--> 523\u001b[0m buffer \u001b[39m=\u001b[39m source\u001b[39m.\u001b[39;49mstream\u001b[39m.\u001b[39;49mread(source\u001b[39m.\u001b[39;49mCHUNK)\n\u001b[0;32m 524\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mlen\u001b[39m(buffer) \u001b[39m==\u001b[39m \u001b[39m0\u001b[39m: \u001b[39mbreak\u001b[39;00m \u001b[39m# reached end of the stream\u001b[39;00m\n\u001b[0;32m 525\u001b[0m frames\u001b[39m.\u001b[39mappend(buffer)\n",
"File \u001b[1;32mc:\\ProgramData\\miniconda3\\envs\\lang\\lib\\site-packages\\speech_recognition\\__init__.py:199\u001b[0m, in \u001b[0;36mMicrophone.MicrophoneStream.read\u001b[1;34m(self, size)\u001b[0m\n\u001b[0;32m 198\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mread\u001b[39m(\u001b[39mself\u001b[39m, size):\n\u001b[1;32m--> 199\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mpyaudio_stream\u001b[39m.\u001b[39;49mread(size, exception_on_overflow\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m)\n",
"File \u001b[1;32mc:\\ProgramData\\miniconda3\\envs\\lang\\lib\\site-packages\\pyaudio\\__init__.py:570\u001b[0m, in \u001b[0;36mPyAudio.Stream.read\u001b[1;34m(self, num_frames, exception_on_overflow)\u001b[0m\n\u001b[0;32m 567\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_is_input:\n\u001b[0;32m 568\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mIOError\u001b[39;00m(\u001b[39m\"\u001b[39m\u001b[39mNot input stream\u001b[39m\u001b[39m\"\u001b[39m,\n\u001b[0;32m 569\u001b[0m paCanNotReadFromAnOutputOnlyStream)\n\u001b[1;32m--> 570\u001b[0m \u001b[39mreturn\u001b[39;00m pa\u001b[39m.\u001b[39;49mread_stream(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_stream, num_frames,\n\u001b[0;32m 571\u001b[0m exception_on_overflow)\n",
"\u001b[1;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"listen(None)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "lang",
"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": "3.10.10"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
Write Preview
Loading…
Cancel
Save