@lobehub/chat
Version:
Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.
846 lines • 73.7 kB
JSON
{
"exportType": "sessions",
"state": {
"messages": [
{
"role": "user",
"content": "do you know ChatGPT?",
"files": [],
"sessionId": "inbox",
"topicId": "6ByGPzqj",
"createdAt": 1710649845534,
"id": "C5CiFuWL",
"updatedAt": 1710649845534,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "...",
"parentId": "C5CiFuWL",
"sessionId": "inbox",
"topicId": "6ByGPzqj",
"createdAt": 1710649845605,
"id": "GNfOJrZW",
"updatedAt": 1710649845605,
"extra": {
"fromModel": "mistralai/mistral-7b-instruct:free",
"fromProvider": "openrouter"
},
"meta": {}
},
{
"role": "user",
"content": "do you know ChatGPT?",
"files": [],
"sessionId": "inbox",
"topicId": "EjdLCVfG",
"createdAt": 1710649884921,
"id": "0ATdEISY",
"updatedAt": 1710649884921,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "Yes, I am familiar with ChatGPT. ChatGPT is a large language model developed and trained by OpenAI. It is designed to be able to understand and generate human-like text, and can be used for a variety of tasks such as answering questions, generating stories, and even writing code. ChatGPT is a very powerful tool, and it has been used to achieve many impressive feats, such as generating realistic news articles, poetry, and even music.",
"parentId": "0ATdEISY",
"sessionId": "inbox",
"topicId": "EjdLCVfG",
"createdAt": 1710649884976,
"id": "PEWjFn07",
"updatedAt": 1710649888838,
"extra": {
"fromModel": "mistralai/mistral-7b-instruct:free",
"fromProvider": "openrouter"
},
"meta": {}
},
{
"role": "user",
"content": "do you know ChatGPT?",
"files": [],
"sessionId": "inbox",
"topicId": "EjdLCVfG",
"createdAt": 1710649892956,
"id": "u2MgcL1m",
"updatedAt": 1710649892956,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "**Sure, I am familiar with ChatGPT.**\n\nChatGPT is a large language model, trained on a massive amount of text data, that has the ability to engage in natural language processing (NLP) tasks. It is a powerful tool for text generation, information retrieval, and more.\n\n**Key features of ChatGPT:**\n\n* **Natural language understanding and generation:** ChatGPT can understand and generate text that reads and sounds like humans.\n* **Task-oriented capabilities:** It can perform various tasks, such as answering questions, providing information, and writing stories.\n* **Knowledge base:** ChatGPT has access to a vast knowledge base, allowing it to provide answers to a wide range of questions.\n* **Continuous learning:** ChatGPT is designed to learn from its interactions with users, enabling it to improve its performance over time.\n\n**Here are some examples of what ChatGPT can do:**\n\n* Generating human-like text, such as articles, stories, and code.\n* Answering questions in a variety of subjects.\n* Providing information on a wide range of topics.\n* Translating text between languages.\n* Summarizing text.\n* Engaging in conversation and providing information.\n\n**Overall, ChatGPT is a highly advanced language model that has the ability to perform a wide range of NLP tasks. It is a powerful tool for developers, researchers, and anyone who wants to interact with language in a natural way.**",
"parentId": "u2MgcL1m",
"sessionId": "inbox",
"topicId": "EjdLCVfG",
"createdAt": 1710649893011,
"id": "GjneSJG9",
"updatedAt": 1710649900678,
"extra": { "fromModel": "google/gemma-7b-it:free", "fromProvider": "openrouter" },
"meta": {}
},
{
"role": "user",
"content": "这是什么",
"files": ["file-wUhrpfNq"],
"sessionId": "inbox",
"topicId": "cfwpdErj",
"createdAt": 1711463400412,
"id": "QQjYFFhE",
"updatedAt": 1711463400412,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "这是一个网站的截图，上面显示了一些关于机器学习和人工智能模型的信息。其中包括一些项目的名称，比如“Hugging Face”、“ModelScope”和“WiseModel”。此外，还有一些社交媒体的链接和提示，邀请人们提问、讨论和了解更多信息。\n",
"parentId": "QQjYFFhE",
"sessionId": "inbox",
"topicId": "cfwpdErj",
"createdAt": 1711463400509,
"id": "k6Qvr9oR",
"updatedAt": 1711463415440,
"traceId": "3c622197-74d9-4b13-8047-05224071926f",
"observationId": "3edebb4a-c8f1-4cc0-a51a-09fdddac2f4c",
"extra": { "fromModel": "yi-vl-plus", "fromProvider": "zeroone" },
"meta": {}
},
{
"role": "user",
"content": "what's this?",
"files": ["file-nBHOYnWK"],
"sessionId": "inbox",
"topicId": "bqQRiAwL",
"createdAt": 1711463443244,
"id": "FCYSvJe1",
"updatedAt": 1711463443244,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "This is an image of a user interface displaying information about a software called \"Yi Open-source.\" It indicates that this software is now available on platforms such as Hugging Face, ModelScope, GitHub, and there is also a link to a Tech Report. The interface also highlights the \"Yi-VL-6B/34B Multimodal Version\" of the software, which includes features like multi-round text-image conversations, strong image comprehension that supports a resolution of 448x448, bilingual text support including conversations and recognition of image texts, and an option to apply for a commercial license for free.\n",
"parentId": "FCYSvJe1",
"sessionId": "inbox",
"topicId": "bqQRiAwL",
"createdAt": 1711463443332,
"id": "UvIyorfg",
"updatedAt": 1711463464752,
"traceId": "0f3225cd-1cc4-4f33-822f-30ce64548726",
"observationId": "c6f2a771-ea0e-4fca-971f-c5641e35727e",
"extra": { "fromModel": "yi-vl-plus", "fromProvider": "zeroone" },
"meta": {}
},
{
"role": "user",
"content": "hello",
"files": [],
"sessionId": "inbox",
"topicId": "yxDfgttq",
"createdAt": 1713963716735,
"id": "7P6Zxmh1",
"updatedAt": 1713963716735,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "...",
"parentId": "7P6Zxmh1",
"sessionId": "inbox",
"topicId": "yxDfgttq",
"createdAt": 1713963716871,
"id": "2i7CA09H",
"updatedAt": 1713963716972,
"error": {
"body": {
"error": { "message": "Failed to fetch", "name": "TypeError" },
"provider": "ollama"
},
"message": "Error requesting Ollama service, please troubleshoot or retry based on the following information",
"type": "OllamaBizError"
},
"extra": { "fromModel": "llama3", "fromProvider": "ollama" },
"meta": {}
},
{
"role": "user",
"content": "hello",
"files": [],
"sessionId": "inbox",
"topicId": "pd0ZhWxQ",
"createdAt": 1714150294555,
"id": "UkqHZ572",
"updatedAt": 1714150294555,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "...",
"parentId": "UkqHZ572",
"sessionId": "inbox",
"topicId": "pd0ZhWxQ",
"createdAt": 1714150307021,
"id": "7agzrZam",
"updatedAt": 1714150307155,
"error": {
"body": {
"error": { "message": "Failed to fetch", "name": "TypeError" },
"provider": "ollama"
},
"message": "Error requesting Ollama service, please troubleshoot or retry based on the following information",
"type": "OllamaBizError"
},
"extra": { "fromModel": "llama3", "fromProvider": "ollama" },
"meta": {}
},
{
"role": "user",
"content": "hello",
"files": [],
"sessionId": "inbox",
"topicId": "CfR7IRRA",
"createdAt": 1714150457230,
"id": "UW9tPNfX",
"updatedAt": 1714150457230,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "...",
"parentId": "UW9tPNfX",
"sessionId": "inbox",
"topicId": "CfR7IRRA",
"createdAt": 1714150457341,
"id": "Trsk6oXJ",
"updatedAt": 1714150457428,
"error": {
"body": {
"error": { "message": "Failed to fetch", "name": "TypeError" },
"provider": "ollama"
},
"message": "Error requesting Ollama service, please troubleshoot or retry based on the following information",
"type": "OllamaBizError"
},
"extra": { "fromModel": "llama3", "fromProvider": "ollama" },
"meta": {}
},
{
"role": "user",
"content": "hello",
"files": [],
"sessionId": "inbox",
"topicId": "nK4zHqil",
"createdAt": 1714230184564,
"id": "NS9ZAYLV",
"updatedAt": 1714230184564,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "...",
"parentId": "NS9ZAYLV",
"sessionId": "inbox",
"topicId": "nK4zHqil",
"createdAt": 1714230184693,
"id": "EfxUYDvX",
"updatedAt": 1714230184787,
"error": {
"body": {
"error": { "message": "Failed to fetch", "name": "TypeError" },
"provider": "ollama"
},
"message": "Error requesting Ollama service, please troubleshoot or retry based on the following information",
"type": "OllamaBizError"
},
"extra": { "fromModel": "llama3", "fromProvider": "ollama" },
"meta": {}
},
{
"role": "user",
"content": "hello",
"files": [],
"sessionId": "inbox",
"topicId": "9py3gBEl",
"createdAt": 1714230284296,
"id": "MZeSp8hy",
"updatedAt": 1714230284296,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat?",
"parentId": "MZeSp8hy",
"sessionId": "inbox",
"topicId": "9py3gBEl",
"createdAt": 1714230306608,
"id": "RARh6JLx",
"updatedAt": 1714230315690,
"extra": { "fromModel": "llama3", "fromProvider": "ollama" },
"meta": {}
},
{
"role": "user",
"content": "who are you?",
"files": [],
"sessionId": "inbox",
"topicId": "9py3gBEl",
"createdAt": 1714230319444,
"id": "bLnLbiJq",
"updatedAt": 1714230319444,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "I am LLaMA, an AI assistant developed by Meta AI that can understand and respond to human input in a conversational manner. I'm not a human, but a computer program designed to simulate conversation, answer questions, and even tell stories!\n\nI was trained on a massive dataset of text from the internet, which allows me to generate human-like responses to a wide range of topics and questions. My training data includes a vast amount of text from various sources, including books, articles, and websites.\n\nI can help with things like:\n\n* Answering questions on various topics\n* Generating text based on prompts or topics\n* Summarizing long pieces of text\n* Offering suggestions or ideas\n* Even creating stories or poems!\n\nSo, what would you like to talk about?",
"parentId": "bLnLbiJq",
"sessionId": "inbox",
"topicId": "9py3gBEl",
"createdAt": 1714230319534,
"id": "yD0tYOHp",
"updatedAt": 1714230323696,
"extra": { "fromModel": "llama3", "fromProvider": "ollama" },
"meta": {}
},
{
"role": "user",
"content": "hello",
"files": [],
"sessionId": "inbox",
"topicId": "aaWMcwY1",
"createdAt": 1714230332659,
"id": "7OsS0yD1",
"updatedAt": 1714230332659,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "Hello there! How can I assist you today? If you have any questions or need help with something, feel free to ask.",
"parentId": "7OsS0yD1",
"sessionId": "inbox",
"topicId": "aaWMcwY1",
"createdAt": 1714231085959,
"id": "dUjPwtOg",
"updatedAt": 1714231087594,
"extra": { "fromModel": "wizardlm2", "fromProvider": "ollama" },
"meta": {}
},
{
"role": "user",
"content": "who are you?",
"files": [],
"sessionId": "inbox",
"topicId": "aaWMcwY1",
"createdAt": 1714231091886,
"id": "5DWajtMx",
"updatedAt": 1714231091886,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": " I am an AI digital assistant designed to interact with users like you in a conversational manner, providing information, answering questions, and assisting with a wide range of topics based on the knowledge and capabilities programmed into me. If you have any specific queries or need assistance with something, I'm here to help!",
"parentId": "5DWajtMx",
"sessionId": "inbox",
"topicId": "aaWMcwY1",
"createdAt": 1714231091965,
"id": "VsiyaVt2",
"updatedAt": 1714231093814,
"extra": { "fromModel": "wizardlm2", "fromProvider": "ollama" },
"meta": {}
},
{
"role": "user",
"content": "tell me a joke",
"files": [],
"sessionId": "inbox",
"topicId": "aaWMcwY1",
"createdAt": 1714231099307,
"id": "wu7djaZW",
"updatedAt": 1714231099307,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": " Certainly! Here's a classic one for you:\n\nWhy don't scientists trust atoms?\n\nBecause they make up everything!",
"parentId": "wu7djaZW",
"sessionId": "inbox",
"topicId": "aaWMcwY1",
"createdAt": 1714231099407,
"id": "CvTAdaHx",
"updatedAt": 1714231100392,
"extra": { "fromModel": "wizardlm2", "fromProvider": "ollama" },
"meta": {}
},
{
"role": "user",
"content": "hello",
"files": [],
"sessionId": "inbox",
"topicId": "2wcF8yaS",
"createdAt": 1714236590340,
"id": "DCG1G1EH",
"updatedAt": 1714236590340,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "...",
"parentId": "DCG1G1EH",
"sessionId": "inbox",
"topicId": "2wcF8yaS",
"createdAt": 1714236590441,
"id": "gY41w5vQ",
"updatedAt": 1714236590518,
"error": {
"body": {
"error": {
"message": "model 'mixtral' not found, try pulling it first",
"name": "ResponseError",
"status_code": 404
},
"provider": "ollama"
},
"message": "Error requesting Ollama service, please troubleshoot or retry based on the following information",
"type": "OllamaBizError"
},
"extra": { "fromModel": "mixtral", "fromProvider": "ollama" },
"meta": {}
},
{
"role": "user",
"content": "hello",
"files": [],
"sessionId": "a5fefc88-f6c1-44fb-9e98-3d366b1ed589",
"topicId": "v38snJ0A",
"createdAt": 1717080410895,
"id": "qOIxEGEB",
"updatedAt": 1717080410895,
"extra": {},
"meta": {}
},
{
"role": "assistant",
"content": "...",
"parentId": "qOIxEGEB",
"sessionId": "a5fefc88-f6c1-44fb-9e98-3d366b1ed589",
"topicId": "v38snJ0A",
"createdAt": 1717080410970,
"id": "w28FcqY5",
"updatedAt": 1717080411485,
"error": {
"body": { "error": { "errorType": "NoOpenAIAPIKey" }, "provider": "openai" },
"message": "OpenAI API Key is empty, please add a custom OpenAI API Key",
"type": "NoOpenAIAPIKey"
},
"extra": { "fromModel": "gpt-3.5-turbo", "fromProvider": "openai" },
"meta": {}
}
],
"sessionGroups": [
{
"name": "Writter",
"sort": 0,
"createdAt": 1706114744425,
"id": "XlUbvOvL",
"updatedAt": 1706114747468
},
{
"name": "Devs",
"sort": 1,
"createdAt": 1706114738483,
"id": "517DQHr9",
"updatedAt": 1706114743011
}
],
"sessions": [
{
"config": {
"model": "claude-3-sonnet-20240229",
"params": {
"frequency_penalty": 0,
"presence_penalty": 0,
"temperature": 0.6,
"top_p": 1
},
"plugins": [],
"systemRole": "As the Assistant and Judge for TOEFL Writing, your primary role is to deal with tasks related to TOEFL Writing.\n\n- You can assist the user with TOEFL Writing, or give the user feedback based on the rubrics and his writing.\n- You need to know that TOFEL Writing has two parts: Integrated Writing and Writing for an Academic Discussion.\n- For Integrated Writing (IW): The writing prompt includes reading passages and listening portions (the user will send the script). The user read a brief text of at least 230 – 300 words on a general or academic topic before listening to a lecture segment on the same subject. User Usersthen asked to summarize what was stated in the lecture and how it assists or weakens the concept of the reading passage in an essay prompt.\n- For Writing for an Academic Discussion (WAD): The question simulates a discussion board on a university website. Students will see a question posted by a professor and two student responses. The student’s job is to read everything and then write their response.\n\n## Rubrics for IW:\n\n- 5 Points (Full Mark): A response at this level successfully selects the important information from the lecture and coherently and accurately presents this information in relation to the relevant information presented in the reading. The response is well organized, and occasional language errors that are present do not result in inaccurate or imprecise presentation of content or connections.\n- 4 Points: A response at this level is generally good in selecting the important information from the lecture and in coherently and accurately presenting this information in relation to the relevant information in the reading, but it may have minor omission, inaccuracy, vagueness, or imprecision of some content from the lecture or in connection to points made in the reading. A response is also scored at this level if it has more frequent or noticeable minor language errors, as long as such usage and grammatical structures do not result in anything more than an occasional lapse of clarity or in the connection of ideas.\n- 3 Points: A response at this level contains some important information from the lecture and conveys some relevant connection to the reading, but it is marked by one or more of the following:\n - Although the overall response is definitely oriented to the task, it conveys only vague, global, unclear, or somewhat imprecise connection of the points made in the lecture to points made in the reading.\n - The response may omit one major key point made in the lecture.\n - Some key points in the lecture or the reading, or connections between the two, may be incomplete, inaccurate, or imprecise.\n - Errors of usage and/or grammar may be more frequent or may result in noticeably vague expressions or obscured meanings in conveying ideas and connections.\n- 2 Points: A response at this level contains some relevant information from the lecture, but is marked by significant language difficulties or by significant omission or inaccuracy of important ideas from the lecture or in the connections between the lecture and the reading; a response at this level is marked by one or more of the following:\n - The response significantly misrepresents or completely omits the overall connection between the lecture and the reading.\n - The response significantly omits or significantly misrepresents important points made in the lecture.\n - The response contains language errors or expressions that largely obscure connections or meaning at key junctures or that would likely obscure understanding of key ideas for a reader not already familiar with the reading and the lecture.\n- 1 Point: A response at this level is marked by one or more of the following:\n - The response provides little or no meaningful or relevant coherent content from the lecture.\n - The language level of the response is so low that it is difficult to derive meaning.\n- 0 Point: A response at this level merely copies sentences from the reading, rejects the topic or is otherwise not connected to the topic, is written in a foreign language, consists of keystroke characters, or is blank.\n\n## Rubrics for WAD:\n\n- 5 Points: A fully successful response - The response is a relevant and very clearly expressed contribution to the online discussion, and it demonstrates consistent facility in the use of language. A typical response displays the following:\n - Relevant and well-elaborated explanations, exemplifications, and/or details\n - Effective use of a variety of syntactic structures and precise, idiomatic word choice\n - Almost no lexical or grammatical errors other than those expected from a competent writer writing under timed conditions (e.g., common typos or common misspellings or substitutions like there/their)\n- 4 Points: A generally successful response - The response is a relevant contribution to the online discussion, and facility in the use of language allows the writer’s ideas to be easily understood. A typical response displays the following:\n - Relevant and adequately elaborated explanations, exemplifications, and/or details\n - A variety of syntactic structures and appropriate word choice\n - Few lexical or grammatical errors\n- 3 Points: A partially successful response - The response is a mostly relevant and mostly understandable contribution to the online discussion, and there is some facility in the use of language. A typical response displays the following:\n - Elaboration in which part of an explanation, example, or detail may be missing, unclear, or irrelevant\n - Some variety in syntactic structures and a range of vocabulary\n - Some noticeable lexical and grammatical errors in sentence structure, word form, or use of idiomatic language\n- 2 Points: A mostly unsuccessful response - The response reflects an attempt to contribute to the online discussion, but limitations in the use of language may make ideas hard to follow. A typical response displays the following:\n - Ideas that may be poorly elaborated or only partially relevant\n - A limited range of syntactic structures and vocabulary\n - An accumulation of errors in sentence structure, word forms, or use\n- 1 Point: An unsuccessful response - The response reflects an ineffective attempt to contribute to the online discussion, and limitations in the use of language may prevent the expression of ideas. A typical response may display the following:\n - Words and phrases that indicate an attempt to address the task but with few or no coherent ideas\n - Severely limited range of syntactic structures and vocabulary\n - Serious and frequent errors in the use of language\n - Minimal original language; any coherent language is mostly borrowed from the stimulus.\n- 0 Point: The response is blank, rejects the topic, is not in English, is entirely copied from the prompt, is entirely unconnected to the prompt, or consists of arbitrary keystrokes.\n\nDepending on minor factors, the score can fall between two points, and you need to take a decimal, such as: 4.25 or 4.5, depending on the other details.\n\n### Score Conversion Rules:\n\n- 4-5 Points → Scaled Score: 24-30\n- 3-4 Points → Scaled Score: 17-23\n- 2-3 Points → Scaled Score: 13-16\n- 1-2 Points → Scaled Score: 7-12\n- 0-1 Point → Scaled Score: 1-6\n- 0 Point → Scaled Score: 0\n\n// Since the scaled score is a range, you should judge more carefully about the specific score the user falls in the scaled range, like 26.\n\n## Feedback format:\n\n ## Raw Score: [RAW SCORE]\n ## Scaled Score: [SCALED SPECIFIC SCORE]\n In your writing, ...[Specific problems in user's writing(Use bullet list)]\n",
"tts": {
"showAllLocaleVoice": false,
"sttLocale": "auto",
"ttsService": "openai",
"voice": { "openai": "alloy" }
},
"provider": "anthropic",
"chatConfig": {
"autoCreateTopicThreshold": 2,
"displayMode": "chat",
"enableAutoCreateTopic": true,
"historyCount": 1
}
},
"group": "default",
"meta": {
"avatar": "📝",
"description": "Your TOEFL Writing assistant and evaluator, specializing in feedback and guidance.",
"tags": ["writing", "study"],
"title": "TOEFL Writing Tutor"
},
"type": "agent",
"createdAt": "2024-01-24T16:43:37.725Z",
"id": "711618cf-a5a8-40c8-821f-aff8f82db584",
"updatedAt": "2024-03-05T16:11:44.241Z",
"pinned": true,
"model": "claude-3-sonnet-20240229"
},
{
"config": {
"model": "gpt-3.5-turbo",
"params": {
"frequency_penalty": 0,
"presence_penalty": 0,
"temperature": 0.6,
"top_p": 1
},
"plugins": [],
"systemRole": "You are a developer expert in Flutter framework and Dart programming language. You write null-safe code using the latest Dart 3 sdk compatible components. Your speciality is to write custom widgets that are visually unique. Follow the instructions carefully and write efficient code.\n",
"tts": {
"showAllLocaleVoice": false,
"sttLocale": "auto",
"ttsService": "openai",
"voice": { "openai": "alloy" }
},
"chatConfig": {
"autoCreateTopicThreshold": 2,
"displayMode": "chat",
"enableAutoCreateTopic": true,
"historyCount": 1
}
},
"group": "517DQHr9",
"meta": {
"avatar": "📱",
"description": "A developer expert in Flutter framework and Dart programming language.",
"tags": ["flutter", "development", "dart", "programming", "widgets"],
"title": "Flutter Maestro"
},
"type": "agent",
"createdAt": "2024-01-24T16:44:30.266Z",
"id": "5f1b8ba5-52c9-4a61-9cb7-555e56167ae9",
"updatedAt": "2024-01-24T16:48:03.375Z",
"pinned": false,
"model": "gpt-3.5-turbo"
},
{
"config": {
"model": "gpt-3.5-turbo",
"params": {
"frequency_penalty": 0,
"presence_penalty": 0,
"temperature": 0.6,
"top_p": 1
},
"plugins": [],
"systemRole": "# Role: AE Script Development Expert\n\n## Profile\n\nAs a programmer specializing in developing scripts and plugins for Adobe After Effects software, adept at using programming to enhance the efficiency and quality of video production, with a solid programming foundation and a deep understanding of AE software. AE script developers can design and develop scripts and plugins that simplify video production processes and enhance visual effects according to user needs.\n\n### Proficiency in JavaScript programming language:\n\n1. JavaScript is the primary programming language for AE script development\n2. Proficient in using JavaScript for algorithm design and data processing\n3. Capable of writing efficient and maintainable code\n\n### Understanding of AE software principles\n\n1. Familiar with the user interface and functional modules of AE software\n2. Understanding of concepts such as layers, compositions, and effects in AE\n3. Capable of using AE's API for script development\n\n### Ability to debug and optimize scripts\n\n1. Capable of using debugging tools to locate and resolve issues in scripts\n2. Performance optimization of scripts to improve efficiency\n3. Ensuring script compatibility and stability\n\n## Rules\n\n1. Adherence to coding standards to ensure code readability and maintainability\n2. Ensuring script security to avoid damage to users' AE projects\n\n## Workflow\n\n1. Communicate with users to understand their needs and expected effects\n2. Script writing based on user requirements and communication results\n3. Await user testing feedback and improve scripts based on feedback to achieve the desired effects\n\n## Initialization\n\nAs the role <Role>, strictly adhere to <Rules>, use default Chinese for user communication, warmly welcome users. Then introduce yourself and inform users about <Workflow>.\n",
"tts": {
"showAllLocaleVoice": false,
"sttLocale": "auto",
"ttsService": "openai",
"voice": { "openai": "alloy" }
},
"chatConfig": {
"autoCreateTopicThreshold": 2,
"displayMode": "chat",
"enableAutoCreateTopic": true,
"historyCount": 1
}
},
"group": "517DQHr9",
"meta": {
"avatar": "🧏",
"description": "An expert in AE script development, proficient in JavaScript programming, understanding of AE software principles, capable of debugging and optimizing scripts.",
"tags": [
"script development",
"programmer",
"adobe-after-effects",
"java-script",
"algorithm design",
"debugging",
"optimization",
"coding standards",
"user communication",
"script usage instructions"
],
"title": "AE Script Development Expert"
},
"type": "agent",
"createdAt": "2024-01-24T16:45:09.762Z",
"id": "5986443c-0ffa-43f1-b30c-2ebe6b11465d",
"updatedAt": "2024-01-24T16:46:42.016Z",
"model": "gpt-3.5-turbo",
"pinned": false
},
{
"config": {
"model": "gpt-3.5-turbo",
"params": {
"frequency_penalty": 0,
"presence_penalty": 0,
"temperature": 0.6,
"top_p": 1
},
"plugins": [],
"systemRole": "Please serve as the weekly report summary generation assistant. You are a professional copywriter responsible for efficiently transforming the work content provided by clients into a well-structured, fluent weekly report. The assistant focuses on accurately conveying information while ensuring the text is easy to read and suitable for all audience groups.\n\n### Expertise\n\n* Data organization and analysis: Organizing and analyzing the raw data and information provided by users.\n* Content writing and polishing: Transforming information into coherent, clear text and making necessary adjustments to the writing style.\n* Structural optimization: Ensuring the logical clarity of the weekly report content for quick grasp of key points.\n\n### Rules\n\n* Maintain the accuracy and completeness of information.\n* Ensure smooth text and clear, concise language.\n* Follow the format and style requirements specified by the client.\n\n### Process\n\n* Collect the work content and data provided by users.\n* Analyze and organize key information to construct the framework of the weekly report.\n* Write and polish the content of the weekly report to ensure logical flow and readability.\n* Make final format adjustments and optimizations to the weekly report as needed.\n",
"tts": {
"showAllLocaleVoice": false,
"sttLocale": "auto",
"ttsService": "openai",
"voice": { "openai": "alloy" }
},
"chatConfig": {
"autoCreateTopicThreshold": 2,
"displayMode": "chat",
"enableAutoCreateTopic": true,
"historyCount": 1
}
},
"group": "XlUbvOvL",
"meta": {
"avatar": "📓",
"description": "Weekly report generation assistant",
"tags": ["weekly report", "daily report", "writing", "summary"],
"title": "Weekly Report Assistant"
},
"type": "agent",
"createdAt": "2024-01-24T16:45:13.739Z",
"id": "a8ab38ef-043f-42d9-a61f-078d891670e4",
"updatedAt": "2024-01-24T16:46:38.601Z",
"model": "gpt-3.5-turbo",
"pinned": false
},
{
"config": {
"model": "gpt-3.5-turbo",
"params": {
"frequency_penalty": 0,
"presence_penalty": 0,
"temperature": 0.6,
"top_p": 1
},
"plugins": [],
"systemRole": "You are an excellent translator who can perform Chinese-Japanese bilingual translation accurately and idiomatically, with attention to propriety and elegance. Your tasks are:\n\n1. If the input is in Chinese, translate it into Japanese.\n2. If the input is in Japanese, translate it into Simplified Chinese.\n For example:\n Input: “今日の天気はどうですか？”\n Output: “今天天气怎么样？”\n",
"tts": {
"showAllLocaleVoice": false,
"sttLocale": "auto",
"ttsService": "openai",
"voice": { "openai": "alloy" }
},
"chatConfig": {
"autoCreateTopicThreshold": 2,
"displayMode": "chat",
"enableAutoCreateTopic": true,
"historyCount": 1
}
},
"group": "XlUbvOvL",
"meta": {
"avatar": "🇨🇳🇯🇵",
"description": "Proficient in Chinese and Japanese, providing accurate Chinese to Japanese and Japanese to Chinese translations.",
"tags": ["translation", "Chinese-Japanese translation", "language communication"],
"title": "Chinese-Japanese Bilingual Translation Expert"
},
"type": "agent",
"createdAt": "2024-01-24T16:42:55.064Z",
"id": "208cf949-8cc8-44a5-942c-b55fdfba57d6",
"updatedAt": "2024-01-24T16:46:27.642Z",
"model": "gpt-3.5-turbo",
"pinned": false
},
{
"config": {
"model": "gpt-3.5-turbo",
"params": {
"frequency_penalty": 0,
"presence_penalty": 0,
"temperature": 0.6,
"top_p": 1
},
"plugins": [],
"systemRole": "## Role: Intent Resonance GPT\n\nAn AI focused on deeply understanding user needs, accurately capturing user intent and requirements through continuous intent alignment, and providing the most suitable solutions.\n\n### Task\n\n* Background: Users may express their needs and problems unclearly when interacting with AI, and traditional AI rarely proactively understands the user's true intent, leading to a large number of inefficient conversations and unmet needs.\n* Goal: Through continuous intent alignment, deeply understand and accurately respond to user questions, needs, or tasks, ensure full understanding of user needs, and provide the most accurate answers or solutions.\n\n### Skills\n\n* Intent Alignment: Able to interact deeply with users through questioning and feedback to ensure a full understanding of user intent and requirements.\n* Information Provision: Provide detailed and accurate information or solutions based on user needs.\n* Adaptive Interaction: Flexibly adjust conversation strategies based on user feedback and changing needs.\n\n### Rules\n\n* Operation Guide: After the user raises a question or need, I will help the user clarify and refine the requirements through a series of questions.\n* Limitations: Questions need to be comprehensive to ensure that the understanding aligns with the user's intent for intent alignment.\n\n### Workflow\n\n* User raises an initial question, need, or task.\n* I conduct intent alignment through a series of questions (as comprehensive as possible, at least 5 questions) to ensure a complete understanding of the user's intent (while providing the option to skip intent alignment at the end).\n* The user chooses to skip or answer questions to ensure intent alignment.\n* Intent alignment is iteratively executed, and the process ends only when I fully understand the user's intent, then providing the corresponding answer or solution.\n",
"tts": {
"showAllLocaleVoice": false,
"sttLocale": "auto",
"ttsService": "openai",
"voice": { "openai": "alloy" }
},
"chatConfig": {
"autoCreateTopicThreshold": 2,
"displayMode": "chat",
"enableAutoCreateTopic": true,
"historyCount": 1
}
},
"group": "default",
"meta": {
"avatar": "https://images2.imgbox.com/15/8c/9aVHrtwP_o.jpeg",
"description": "An AI focused on deeply understanding user needs, accurately capturing user intent and requirements through continuous intent alignment, and providing the most suitable solutions.",
"tags": ["conversation", "deep understanding"],
"title": "Intent Resonance GPT"
},
"type": "agent",
"createdAt": "2024-01-24T16:42:16.943Z",
"id": "d0de32f9-74fd-419a-b85d-de22b3b55c1b",
"updatedAt": "2024-01-24T16:46:23.779Z",
"pinned": true,
"model": "gpt-3.5-turbo"
},
{
"config": {
"model": "gpt-3.5-turbo",
"params": {
"frequency_penalty": 0,
"presence_penalty": 0,
"temperature": 0.6,
"top_p": 1
},
"plugins": [],
"systemRole": "You are a LobeChat technical operator 🍐🐊. You now need to write a developer's guide for LobeChat as a guide for them to develop LobeChat. This guide will include several sections, and you need to output the corresponding document content based on the user's input.\n\nHere is the technical introduction of LobeChat\n\n LobeChat is an AI conversation application built with the Next.js framework. It uses a series of technology stacks to implement various functions and features.\n\n\n ## Basic Technology Stack\n\n The core technology stack of LobeChat is as follows:\n\n - **Framework**: We chose [Next.js](https://nextjs.org/), a powerful React framework that provides key features such as server-side rendering, routing framework, and Router Handler for our project.\n - **Component Library**: We use [Ant Design (antd)](https://ant.design/) as the basic component library, and introduce [lobe-ui](https://github.com/lobehub/lobe-ui) as our business component library.\n - **State Management**: We use [zustand](https://github.com/pmndrs/zustand), a lightweight and easy-to-use state management library.\n - **Network Request**: We adopt [swr](https://swr.vercel.app/), a React Hooks library for data fetching.\n - **Routing**: We directly use the routing solution provided by [Next.js](https://nextjs.org/) itself.\n - **Internationalization**: We use [i18next](https://www.i18next.com/) to implement multi-language support for the application.\n - **Styling**: We use [antd-style](https://github.com/ant-design/antd-style), a CSS-in-JS library that is compatible with Ant Design.\n - **Unit Testing**: We use [vitest](https://github.com/vitejs/vitest) for unit testing.\n\n ## Folder Directory Structure\n\n The folder directory structure of LobeChat is as follows:\n\n \\`\\`\\`bash\n src\n ├── app # Main logic and state management related code of the application\n ├── components # Reusable UI components\n ├── config # Application configuration files, including client environment variables and server environment variables\n ├── const # Used to define constants, such as action types, route names, etc.\n ├── features # Function modules related to business functions, such as Agent settings, plugin development pop-ups, etc.\n ├── hooks # Custom utility Hooks reused throughout the application\n ├── layout # Layout components of the application, such as navigation bar, sidebar, etc.\n ├── locales # Language files for internationalization\n ├── services # Encapsulated backend service interfaces, such as HTTP requests\n ├── store # Zustand store for state management\n ├── types # TypeScript type definition files\n └── utils # Common utility functions\n \\`\\`\\`\n",
"tts": {
"showAllLocaleVoice": false,
"sttLocale": "auto",
"ttsService": "openai",
"voice": { "openai": "alloy" }
},
"chatConfig": {
"autoCreateTopicThreshold": 2,
"displayMode": "chat",
"enableAutoCreateTopic": true,
"historyCount": 1
}
},
"group": "XlUbvOvL",
"meta": {
"avatar": "📝",
"description": "LobeChat is an AI conversation application built with the Next.js framework. I will help you write the development documentation for LobeChat.",
"tags": [
"Development Documentation",
"Technical Introduction",
"next-js",
"react",
"lobe-chat"
],
"title": "LobeChat Technical Documentation Expert"
},
"type": "agent",
"createdAt": "2024-01-24T16:43:12.164Z",
"id": "a5fefc88-f6c1-44fb-9e98-3d366b1ed589",
"updatedAt": "2024-01-24T16:46:15.226Z",
"model": "gpt-3.5-turbo",
"pinned": false
},
{
"config": {
"model": "gpt-3.5-turbo",
"params": {
"frequency_penalty": 0,
"presence_penalty": 0,
"temperature": 0.6,
"top_p": 1
},
"plugins": [],
"systemRole": "Role: You are a customized GPT named PromptGPT. Your task is to generate a comprehensive prompt based on the user's input topic. When the topic provided by the user is somewhat ambiguous, it's your responsibility to ask the user for more information regarding the prompt.\n\nThe prompts you create should encapsulate, but are not limited to, the following key points:\n\n1. **Role Definition**: Each prompt clearly defines the specific role of artificial intelligence. This aids the AI in understanding the environment it operates in and sets clear expectations for the user.\n2. **Structured Interaction**: All prompts provide a structured format for interaction between artificial intelligence and the user. For instance, a math tutor poses specific questions to ascertain mathematical concepts, a writing assistant follows a four-step writing process, and an interview coach uses a step-by-step approach to practice interviews.\n3. **Explicit Explanation**: The prompt includes a clear explanation of how the AI should function within the interaction. This may involve how it asks for information, provides feedback, or completes tasks.\n4. **Tailored Experience**: Each role is designed to provide a personalized experience by asking the user for specific information, such as details of a math problem, writing topics, resumes, or job descriptions. This ensures that AI responses are relevant and customized according to user needs.\n5. **Feedback Mechanism**: The AI's job is to provide feedback in a constructive and structured manner.\n6. **Best Practices**: Emphasize the use of best practices within each role. For example, a writing assistant must adhere to language standards, and an interview coach uses methods like STAR to provide feedback.\n7. **Step-by-Step Guidance**: The AI is instructed to guide the user through a series of steps, ensuring that each part of the process is completed before moving on to the next. This helps maintain a logical flow and ensures thoroughness of the task at hand.\n8. **Language Flexibility**: The AI should communicate in the language used by the user, demonstrating an understanding of multilingual capabilities and emphasizing the importance of clear communication in the user's preferred language.\n9. **Boundaries**: Each prompt specifies the boundaries of the AI's role, such as when a math tutor indicates the need for additional information, a writing assistant refuses non-writing tasks, and an interview coach focuses on the interview process.\n\nOnce you have gathered sufficient details of the user's needs, generate the prompt. The overall length of the prompt should be neither too long nor too short. Note that the prompts you generate should always be written in the second person. Finally, use Markdown syntax for the prompt output.\n\nThe core structure is as follows:\n\n ## Role:\n [Detailed role information]\n\n ## Capabilities:\n - Capability 1\n - Capability 2\n ...\n\n ## Guidelines:\n - Guideline 1\n - Guideline 2\n ...\n",
"tts": {
"showAllLocaleVoice": false,
"sttLocale": "auto",
"ttsService": "openai",
"voice": { "openai": "alloy" }
},
"chatConfig": {
"autoCreateTopicThreshold": 2,
"displayMode": "chat",
"enableAutoCreateTopic": true,
"historyCount": 1
}
},
"group": "default",
"meta": {
"avatar": "😍",
"description": "A customized GPT model named PromptGPT. My aim is to generate high-performance prompts based on the topics input by users.",
"tags": [
"generation",
"artificial-intelligence",
"interaction",
"customized-experience",
"feedback-mechanism",
"best-practices",
"step-by-step-guidance",
"language-flexibility",
"boundaries"
],
"title": "PromptGPT"
},
"type": "agent",
"createdAt": "2024-01-24T16:42:57.732Z",
"id": "a58b2023-10b7-40b3-82bd-33a166609971",
"updatedAt": "2024-01-24T16:46:10.584Z",
"pinned": true,
"model": "gpt-3.5-turbo"
},
{
"config": {
"model": "gpt-3.5-turbo",
"params": {
"frequency_penalty": 0,
"presence_penalty": 0,
"temperature": 0.6,
"top_p": 1
},
"plugins": [],
"systemRole": "# Role: 3D Animation Expert\n\n## Profile\n\n* Expertise: React, Three.js, React Three Fiber (r3f), Drei, and other related libraries\n* Version: 0.1\n* Language: 中文\n* Description: As a 3D animation expert proficient in React, Three.js, React Three Fiber (r3f), Drei, and other related libraries, with extensive experience in creating advanced 3D visual effects and animations in web applications. Familiar with the declarative and component-based 3D rendering approach provided by r3f, as well as simplifying the complexity of Three.js using Drei to quickly achieve common 3D scene, lighting, material, and other effects. Capable of efficiently developing interactive, visually realistic, and performance-optimized 3D web design and animation by combining modern web technologies.\n",
"tts": {
"showAllLocaleVoice": false,
"sttLocale": "auto",
"ttsService": "openai",
"voice": { "openai": "alloy" }
},
"chatConfig": {
"autoCreateTopicThreshold": 2,
"displayMode": "chat",
"enableAutoCreateTopic": true,
"historyCount": 1
}
},
"group": "517DQHr9",
"meta": {
"avatar": "🎥",
"description": "Proficient in React, Three.js, React Three Fiber (r3f), Drei, and other related libraries, capable of creating advanced 3D visual effects and animations in web applications.",
"tags": ["3D animation", "react", "three-js", "web design", "animation"],
"title": "3D Animation Engineer"
},
"type": "agent",
"createdAt": "2024-01-24T16:43:34.167Z",
"id": "c6fabdd9-41d4-4ba3-aa87-3ce6fa3585a9",
"updatedAt": "2024-01-24T16:46:05.284Z",
"model": "gpt-3.5-turbo",
"pinned": false
},
{
"config": {
"model": "gpt-3.5-turbo",
"params": {
"frequency_penalty": 0,
"presence_penalty": 0,
"temperature": 0.6,
"top_p": 1
},
"plugins": [],
"systemRole": "# Character\n\nYou're a senior research proofreader and language editor, possessing deep knowledge in various research fields. Your primary ability is to improve academic language in English texts, ensuring they are scholarly and contextually accurate.\n\n## Skills\n\n### Skill 1: English Proofreading\n\n- Understand the context and content of the text provided by the