From d7bf98b68aed9e1c07f54c9015339373e01e93ed Mon Sep 17 00:00:00 2001 From: avb-is-me <104213687+avb-is-me@users.noreply.github.com> Date: Tue, 27 Feb 2024 00:43:57 +0000 Subject: [PATCH 01/17] adds code samples for list models --- docs/openapi/jan.yaml | 119 ++++++++++++++++++++++++++---------------- 1 file changed, 74 insertions(+), 45 deletions(-) diff --git a/docs/openapi/jan.yaml b/docs/openapi/jan.yaml index 864c80fdf..e58c6a4f2 100644 --- a/docs/openapi/jan.yaml +++ b/docs/openapi/jan.yaml @@ -1,11 +1,11 @@ ---- openapi: 3.0.0 info: title: API Reference description: > # Introduction - Jan API is compatible with the [OpenAI API](https://platform.openai.com/docs/api-reference). + Jan API is compatible with the [OpenAI + API](https://platform.openai.com/docs/api-reference). version: 0.1.8 contact: name: Jan Discord @@ -20,12 +20,12 @@ tags: description: List and describe the various models available in the API. - name: Chat description: > - Given a list of messages comprising a conversation, the model will - return a response. + Given a list of messages comprising a conversation, the model will return + a response. - name: Messages description: > - Messages capture a conversation's content. This can include the - content from LLM responses and other metadata from [chat + Messages capture a conversation's content. This can include the content + from LLM responses and other metadata from [chat completions](/specs/chats). - name: Threads - name: Assistants @@ -49,16 +49,16 @@ paths: summary: | Create chat completion description: > - Creates a model response for the given chat conversation. - Equivalent to OpenAI's create chat completion. + Creates a model response for the given chat conversation. Equivalent + to OpenAI's create chat completion. requestBody: content: application/json: schema: $ref: specs/chat.yaml#/components/schemas/ChatCompletionRequest responses: - "200": + '200': description: OK content: application/json: @@ -100,12 +100,12 @@ paths: - Models summary: List models description: > - Lists the currently available models, and provides basic - information about each one such as the owner and availability. - Equivalent to OpenAI's list model. + Lists the currently available models, and provides basic information + about each one such as the owner and availability. Equivalent + to OpenAI's list model. responses: - "200": + '200': description: OK content: application/json: @@ -113,11 +113,39 @@ paths: $ref: specs/models.yaml#/components/schemas/ListModelsResponse x-codeSamples: - lang: cURL - source: | + source: |- curl -X 'GET' \ 'http://localhost:1337/v1/models' \ -H 'accept: application/json' - "/models/download/{model_id}": + - lang: JavaScript + source: |- + const response = await fetch('http://localhost:1337/v1/models', { + method: 'GET', + headers: {Accept: 'application/json'} + }); + const data = await response.json(); + - lang: Python + source: |- + import requests + + url = 'http://localhost:1337/v1/models' + headers = {'Accept': 'application/json'} + response = requests.get(url, headers=headers) + data = response.json() + - lang: Node.js + source: |- + const fetch = require('node-fetch'); + + const url = 'http://localhost:1337/v1/models'; + const options = { + method: 'GET', + headers: { Accept: 'application/json' } + }; + + fetch(url, options) + .then(res => res.json()) + .then(json => console.log(json)); + /models/download/{model_id}: get: operationId: downloadModel tags: @@ -135,7 +163,7 @@ paths: description: | The ID of the model to use for this request. responses: - "200": + '200': description: OK content: application/json: @@ -147,15 +175,15 @@ paths: curl -X 'GET' \ 'http://localhost:1337/v1/models/download/{model_id}' \ -H 'accept: application/json' - "/models/{model_id}": + /models/{model_id}: get: operationId: retrieveModel tags: - Models summary: Retrieve model description: > - Get a model instance, providing basic information about the model - such as the owner and permissioning. Equivalent to OpenAI's retrieve model. parameters: @@ -168,7 +196,7 @@ paths: description: | The ID of the model to use for this request. responses: - "200": + '200': description: OK content: application/json: @@ -199,7 +227,7 @@ paths: description: | The model id to delete responses: - "200": + '200': description: OK content: application/json: @@ -228,7 +256,7 @@ paths: schema: $ref: specs/threads.yaml#/components/schemas/CreateThreadObject responses: - "200": + '200': description: Thread created successfully content: application/json: @@ -257,7 +285,7 @@ paths: description: | Retrieves a list of all threads available in the system. responses: - "200": + '200': description: List of threads retrieved successfully content: application/json: @@ -285,7 +313,7 @@ paths: source: | curl http://localhost:1337/v1/threads \ -H "Content-Type: application/json" \ - "/threads/{thread_id}": + /threads/{thread_id}: get: operationId: getThread tags: @@ -305,7 +333,7 @@ paths: description: | The ID of the thread to retrieve. responses: - "200": + '200': description: Thread details retrieved successfully content: application/json: @@ -345,7 +373,7 @@ paths: items: $ref: specs/threads.yaml#/components/schemas/ThreadMessageObject responses: - "200": + '200': description: Thread modified successfully content: application/json: @@ -384,7 +412,7 @@ paths: description: | The ID of the thread to be deleted. responses: - "200": + '200': description: Thread deleted successfully content: application/json: @@ -405,7 +433,7 @@ paths: "https://platform.openai.com/docs/api-reference/assistants/listAssistants"> Equivalent to OpenAI's list assistants. responses: - "200": + '200': description: List of assistants retrieved successfully content: application/json: @@ -445,7 +473,7 @@ paths: source: | curl http://localhost:1337/v1/assistants \ -H "Content-Type: application/json" \ - "/assistants/{assistant_id}": + /assistants/{assistant_id}: get: operationId: getAssistant tags: @@ -465,18 +493,19 @@ paths: description: | The ID of the assistant to retrieve. responses: - "200": + '200': description: null content: application/json: schema: - $ref: specs/assistants.yaml#/components/schemas/RetrieveAssistantResponse + $ref: >- + specs/assistants.yaml#/components/schemas/RetrieveAssistantResponse x-codeSamples: - lang: cURL source: | curl http://localhost:1337/v1/assistants/{assistant_id} \ -H "Content-Type: application/json" \ - "/threads/{thread_id}/messages": + /threads/{thread_id}/messages: get: operationId: listMessages tags: @@ -495,7 +524,7 @@ paths: description: | The ID of the thread from which to retrieve messages. responses: - "200": + '200': description: List of messages retrieved successfully content: application/json: @@ -547,7 +576,7 @@ paths: - role - content responses: - "200": + '200': description: Message created successfully content: application/json: @@ -562,7 +591,7 @@ paths: "role": "user", "content": "How does AI work? Explain it in simple terms." }' - "/threads/{thread_id}/messages/{message_id}": + /threads/{thread_id}/messages/{message_id}: get: operationId: retrieveMessage tags: @@ -589,7 +618,7 @@ paths: description: | The ID of the message to retrieve. responses: - "200": + '200': description: OK content: application/json: @@ -598,8 +627,8 @@ paths: x-codeSamples: - lang: cURL source: > - curl http://localhost:1337/v1/threads/{thread_id}/messages/{message_id} - \ + curl + http://localhost:1337/v1/threads/{thread_id}/messages/{message_id} \ -H "Content-Type: application/json" x-webhooks: ModelObject: @@ -621,10 +650,9 @@ x-webhooks: post: summary: The assistant object description: > - Build assistants that can call models and use tools to perform - tasks. Equivalent - to OpenAI's assistants object. + Build assistants that can call models and use tools to perform tasks. + + Equivalent to OpenAI's assistants object. operationId: AssistantObjects tags: - Assistants @@ -651,7 +679,8 @@ x-webhooks: ThreadObject: post: summary: The thread object - description: Represents a thread that contains messages. - + Represents a thread that contains messages. Equivalent to OpenAI's thread object. operationId: ThreadObject From 16357178bf24b7a57166600d41ee6c2f6e6fc549 Mon Sep 17 00:00:00 2001 From: avb-is-me <104213687+avb-is-me@users.noreply.github.com> Date: Tue, 27 Feb 2024 07:50:15 +0000 Subject: [PATCH 02/17] add docs for the model/model_id endpoints --- docs/openapi/jan.yaml | 110 +++++++++++++++++++++++++++++------------- 1 file changed, 77 insertions(+), 33 deletions(-) diff --git a/docs/openapi/jan.yaml b/docs/openapi/jan.yaml index e58c6a4f2..e3f1ff3b1 100644 --- a/docs/openapi/jan.yaml +++ b/docs/openapi/jan.yaml @@ -113,38 +113,10 @@ paths: $ref: specs/models.yaml#/components/schemas/ListModelsResponse x-codeSamples: - lang: cURL - source: |- + source: | curl -X 'GET' \ 'http://localhost:1337/v1/models' \ -H 'accept: application/json' - - lang: JavaScript - source: |- - const response = await fetch('http://localhost:1337/v1/models', { - method: 'GET', - headers: {Accept: 'application/json'} - }); - const data = await response.json(); - - lang: Python - source: |- - import requests - - url = 'http://localhost:1337/v1/models' - headers = {'Accept': 'application/json'} - response = requests.get(url, headers=headers) - data = response.json() - - lang: Node.js - source: |- - const fetch = require('node-fetch'); - - const url = 'http://localhost:1337/v1/models'; - const options = { - method: 'GET', - headers: { Accept: 'application/json' } - }; - - fetch(url, options) - .then(res => res.json()) - .then(json => console.log(json)); /models/download/{model_id}: get: operationId: downloadModel @@ -204,10 +176,47 @@ paths: $ref: specs/models.yaml#/components/schemas/GetModelResponse x-codeSamples: - lang: cURL - source: | - curl -X 'GET' \ - 'http://localhost:1337/v1/models/{model_id}' \ + source: |- + curl -X 'GET' \ + 'http://localhost:1337/v1/models/{model_id}' \ -H 'accept: application/json' + - lang: JavaScript + source: |- + const fetch = require('node-fetch'); + + const modelId = 'mistral-ins-7b-q4'; + + fetch(`http://localhost:1337/v1/models/${modelId}`, { + method: 'GET', + headers: {'accept': 'application/json'} + }) + .then(res => res.json()) + .then(json => console.log(json)); + - lang: Node.js + source: |- + const fetch = require('node-fetch'); + + const modelId = 'mistral-ins-7b-q4'; + + fetch(`http://localhost:1337/v1/models/${modelId}`, { + method: 'GET', + headers: {'accept': 'application/json'} + }) + .then(res => res.json()) + .then(json => console.log(json)); + - lang: Python + source: >- + import requests + + + model_id = 'mistral-ins-7b-q4' + + + response = + requests.get(f'http://localhost:1337/v1/models/{model_id}', + headers={'accept': 'application/json'}) + + print(response.json()) delete: operationId: deleteModel tags: @@ -235,10 +244,45 @@ paths: $ref: specs/models.yaml#/components/schemas/DeleteModelResponse x-codeSamples: - lang: cURL - source: | + source: |- curl -X 'DELETE' \ 'http://localhost:1337/v1/models/{model_id}' \ -H 'accept: application/json' + - lang: JavaScript + source: |- + const fetch = require('node-fetch'); + + const modelId = 'mistral-ins-7b-q4'; + + fetch(`http://localhost:1337/v1/models/${modelId}`, { + method: 'DELETE', + headers: { 'accept': 'application/json' } + }) + .then(res => res.json()) + .then(json => console.log(json)); + - lang: Node.js + source: |- + const fetch = require('node-fetch'); + + const modelId = 'mistral-ins-7b-q4'; + + fetch(`http://localhost:1337/v1/models/${modelId}`, { + method: 'DELETE', + headers: { 'accept': 'application/json' } + }) + .then(res => res.json()) + .then(json => console.log(json)); + - lang: Python + source: >- + import requests + + + model_id = 'mistral-ins-7b-q4' + + + response = + requests.delete(f'http://localhost:1337/v1/models/{model_id}', + headers={'accept': 'application/json'}) /threads: post: operationId: createThread From a6dbcf3a1bcf19ed5a2c7b8fb15fcc19bd02d187 Mon Sep 17 00:00:00 2001 From: avb-is-me <104213687+avb-is-me@users.noreply.github.com> Date: Tue, 27 Feb 2024 07:58:22 +0000 Subject: [PATCH 03/17] adds code snippets for download --- docs/openapi/jan.yaml | 66 ++++++++++++++++++++++--------------------- 1 file changed, 34 insertions(+), 32 deletions(-) diff --git a/docs/openapi/jan.yaml b/docs/openapi/jan.yaml index e58c6a4f2..3c2abcc0f 100644 --- a/docs/openapi/jan.yaml +++ b/docs/openapi/jan.yaml @@ -113,38 +113,10 @@ paths: $ref: specs/models.yaml#/components/schemas/ListModelsResponse x-codeSamples: - lang: cURL - source: |- + source: | curl -X 'GET' \ 'http://localhost:1337/v1/models' \ -H 'accept: application/json' - - lang: JavaScript - source: |- - const response = await fetch('http://localhost:1337/v1/models', { - method: 'GET', - headers: {Accept: 'application/json'} - }); - const data = await response.json(); - - lang: Python - source: |- - import requests - - url = 'http://localhost:1337/v1/models' - headers = {'Accept': 'application/json'} - response = requests.get(url, headers=headers) - data = response.json() - - lang: Node.js - source: |- - const fetch = require('node-fetch'); - - const url = 'http://localhost:1337/v1/models'; - const options = { - method: 'GET', - headers: { Accept: 'application/json' } - }; - - fetch(url, options) - .then(res => res.json()) - .then(json => console.log(json)); /models/download/{model_id}: get: operationId: downloadModel @@ -171,10 +143,40 @@ paths: $ref: specs/models.yaml#/components/schemas/DownloadModelResponse x-codeSamples: - lang: cURL - source: | - curl -X 'GET' \ - 'http://localhost:1337/v1/models/download/{model_id}' \ + source: |- + curl -X 'GET' \ + 'http://localhost:1337/v1/models/download/{model_id}' \ -H 'accept: application/json' + - lang: JavaScript + source: >- + const response = await + fetch('http://localhost:1337/v1/models/download/{model_id}', { + method: 'GET', + headers: {accept: 'application/json'} + }); + + + const data = await response.json(); + - lang: Node.js + source: |- + const fetch = require('node-fetch'); + + fetch('http://localhost:1337/v1/models/download/{model_id}', { + method: 'GET', + headers: {accept: 'application/json'} + }) + .then(res => res.json()) + .then(data => console.log(data)); + - lang: Python + source: >- + import requests + + + response = + requests.get('http://localhost:1337/v1/models/download/{model_id}', + headers={'accept': 'application/json'}) + + data = response.json() /models/{model_id}: get: operationId: retrieveModel From 90a11ea4c4867e6c83afea94ee2f46777f7c8103 Mon Sep 17 00:00:00 2001 From: avb-is-me <104213687+avb-is-me@users.noreply.github.com> Date: Tue, 27 Feb 2024 08:02:23 +0000 Subject: [PATCH 04/17] adds code snippets for chat completeions --- docs/openapi/jan.yaml | 134 +++++++++++++++++++++++++++++++++--------- 1 file changed, 105 insertions(+), 29 deletions(-) diff --git a/docs/openapi/jan.yaml b/docs/openapi/jan.yaml index e58c6a4f2..cf5db102a 100644 --- a/docs/openapi/jan.yaml +++ b/docs/openapi/jan.yaml @@ -93,6 +93,110 @@ paths: "temperature": 0.7, "top_p": 0.95 }' + - lang: JavaScript + source: |- + const data = { + messages: [ + { + content: 'You are a helpful assistant.', + role: 'system' + }, + { + content: 'Hello!', + role: 'user' + } + ], + model: 'tinyllama-1.1b', + stream: true, + max_tokens: 2048, + stop: ['hello'], + frequency_penalty: 0, + presence_penalty: 0, + temperature: 0.7, + top_p: 0.95 + }; + + fetch('http://localhost:1337/v1/chat/completions', { + method: 'POST', + headers: { + 'Content-Type': 'application/json', + 'Accept': 'application/json' + }, + body: JSON.stringify(data) + }) + .then(response => response.json()) + .then(data => console.log(data)); + - lang: Node.js + source: |- + const fetch = require('node-fetch'); + + const data = { + messages: [ + { + content: 'You are a helpful assistant.', + role: 'system' + }, + { + content: 'Hello!', + role: 'user' + } + ], + model: 'tinyllama-1.1b', + stream: true, + max_tokens: 2048, + stop: ['hello'], + frequency_penalty: 0, + presence_penalty: 0, + temperature: 0.7, + top_p: 0.95 + }; + + fetch('http://localhost:1337/v1/chat/completions', { + method: 'POST', + headers: { + 'Content-Type': 'application/json', + 'Accept': 'application/json' + }, + body: JSON.stringify(data) + }) + .then(response => response.json()) + .then(data => console.log(data)); + - lang: Python + source: >- + import requests + + import json + + + data = { + "messages": [ + { + "content": "You are a helpful assistant.", + "role": "system" + }, + { + "content": "Hello!", + "role": "user" + } + ], + "model": "tinyllama-1.1b", + "stream": true, + "max_tokens": 2048, + "stop": [ + "hello" + ], + "frequency_penalty": 0, + "presence_penalty": 0, + "temperature": 0.7, + "top_p": 0.95 + } + + + response = + requests.post('http://localhost:1337/v1/chat/completions', + json=data) + + print(response.json()) /models: get: operationId: listModels @@ -113,38 +217,10 @@ paths: $ref: specs/models.yaml#/components/schemas/ListModelsResponse x-codeSamples: - lang: cURL - source: |- + source: | curl -X 'GET' \ 'http://localhost:1337/v1/models' \ -H 'accept: application/json' - - lang: JavaScript - source: |- - const response = await fetch('http://localhost:1337/v1/models', { - method: 'GET', - headers: {Accept: 'application/json'} - }); - const data = await response.json(); - - lang: Python - source: |- - import requests - - url = 'http://localhost:1337/v1/models' - headers = {'Accept': 'application/json'} - response = requests.get(url, headers=headers) - data = response.json() - - lang: Node.js - source: |- - const fetch = require('node-fetch'); - - const url = 'http://localhost:1337/v1/models'; - const options = { - method: 'GET', - headers: { Accept: 'application/json' } - }; - - fetch(url, options) - .then(res => res.json()) - .then(json => console.log(json)); /models/download/{model_id}: get: operationId: downloadModel From 32a86bd9136be0ac044c561f341b537e591190da Mon Sep 17 00:00:00 2001 From: hieu-jan <150573299+hieu-jan@users.noreply.github.com> Date: Tue, 27 Feb 2024 19:21:10 +0900 Subject: [PATCH 05/17] docs: add newsletter --- .../community/{community.md => community.mdx} | 15 +++++++++++++++ docs/src/containers/Footer/index.js | 4 ++++ 2 files changed, 19 insertions(+) rename docs/docs/community/{community.md => community.mdx} (59%) diff --git a/docs/docs/community/community.md b/docs/docs/community/community.mdx similarity index 59% rename from docs/docs/community/community.md rename to docs/docs/community/community.mdx index 24a87daf0..d4866490e 100644 --- a/docs/docs/community/community.md +++ b/docs/docs/community/community.mdx @@ -29,3 +29,18 @@ keywords: ## Careers - [Jobs](https://janai.bamboohr.com/careers) + +## Newsletter + + diff --git a/docs/src/containers/Footer/index.js b/docs/src/containers/Footer/index.js index 7cd648149..3e62f579a 100644 --- a/docs/src/containers/Footer/index.js +++ b/docs/src/containers/Footer/index.js @@ -86,6 +86,10 @@ const menus = [ path: "https://janai.bamboohr.com/careers", external: true, }, + { + menu: "Newsletter", + path: "/community#newsletter", + } ], }, ]; From 65e5921cd155564b15520de0b6cc835816ab7aad Mon Sep 17 00:00:00 2001 From: hieu-jan <150573299+hieu-jan@users.noreply.github.com> Date: Tue, 27 Feb 2024 23:40:32 +0900 Subject: [PATCH 06/17] docs: update wall of love --- docs/docs/wall-of-love.md | 92 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 91 insertions(+), 1 deletion(-) diff --git a/docs/docs/wall-of-love.md b/docs/docs/wall-of-love.md index f196c90e9..102102739 100644 --- a/docs/docs/wall-of-love.md +++ b/docs/docs/wall-of-love.md @@ -1,3 +1,93 @@ --- title: Wall of Love ❤️ ---- \ No newline at end of file +--- + +## Twitter + +Check out our amazing users and what they are saying about Jan! Please share your love for Jan on Twitter and tag us [@janframework](https://twitter.com/janframework)! We would love to hear from you! + +
+I can confirm https://t.co/Hvrfp0iaf9 is awesome 👌
— Cristian (@cristianmoreno) February 13, 2024
+downloaded this a few weeks ago. amazed by the speed and quality
— siddharth (@siddharthd01) February 13, 2024
+Anyone else out there running LLMs on steam deck? @janframework bringing nerd dreams to life! pic.twitter.com/7XpnBmc8MN
— crossdefault (@crossdefault) January 26, 2024
+If you are like me, always wanting your own ChatGPT and have sufficient coding knowledge, you would watch open sourced @janframework by @0xSage like a "my-own-ai" hawk
— Umesh = EG = Educated Guess - NGI doing AI (@trading_indian) January 11, 2024
Still under development, the architecture is really futuristic. The desktop app for Windows, Mac, Linux are… pic.twitter.com/0HrNquhBsL
+came across @janframework yesterday and it's my fav native Apple Silicon LLM app yet. Love that I can switch to GPT 4 API and offline LLM models seamlessly. Looks promising! https://t.co/gyOX9gHbKQ
— Keith Hawkins (@kph_practice) January 9, 2024
+i just ran some ai models locally on my laptop using @janhq_ and can't believe how easy and cool it is. so, now i can have the same experience as with ChatGPT, but offline and without any data concerns
— Sergey Kaplich (@sergey_kaplich) January 4, 2024
+https://t.co/scBqJ3kIzj Great way to try open source all models, like Mixtral8x7b offline. Love to see
— Chubby♨️ (@kimmonismus) January 4, 2024
@@ -34,6 +34,8 @@ Check out our amazing users and what they are saying about Jan! Please share youI can confirm https://t.co/Hvrfp0iaf9 is awesome 👌
— Cristian (@cristianmoreno) February 13, 2024
https://t.co/scBqJ3kIzj Great way to try open source all models, like Mixtral8x7b offline. Love to see
— Chubby♨️ (@kimmonismus) January 4, 2024
+I can confirm https://t.co/Hvrfp0iaf9 is awesome 👌
— Cristian (@cristianmoreno) February 13, 2024
I can confirm https://t.co/Hvrfp0iaf9 is awesome 👌
— Cristian (@cristianmoreno) February 13, 2024
+downloaded this a few weeks ago. amazed by the speed and quality
— siddharth (@siddharthd01) February 13, 2024
downloaded this a few weeks ago. amazed by the speed and quality
— siddharth (@siddharthd01) February 13, 2024
+Anyone else out there running LLMs on steam deck? @janframework bringing nerd dreams to life! pic.twitter.com/7XpnBmc8MN
— crossdefault (@crossdefault) January 26, 2024
Anyone else out there running LLMs on steam deck? @janframework bringing nerd dreams to life! pic.twitter.com/7XpnBmc8MN
— crossdefault (@crossdefault) January 26, 2024
+If you are like me, always wanting your own ChatGPT and have sufficient coding knowledge, you would watch open sourced @janframework by @0xSage like a "my-own-ai" hawk
— Umesh = EG = Educated Guess - NGI doing AI (@trading_indian) January 11, 2024
Still under development, the architecture is really futuristic. The desktop app for Windows, Mac, Linux are… pic.twitter.com/0HrNquhBsL
If you are like me, always wanting your own ChatGPT and have sufficient coding knowledge, you would watch open sourced @janframework by @0xSage like a "my-own-ai" hawk
— Umesh = EG = Educated Guess - NGI doing AI (@trading_indian) January 11, 2024
Still under development, the architecture is really futuristic. The desktop app for Windows, Mac, Linux are… pic.twitter.com/0HrNquhBsL
+came across @janframework yesterday and it's my fav native Apple Silicon LLM app yet. Love that I can switch to GPT 4 API and offline LLM models seamlessly. Looks promising! https://t.co/gyOX9gHbKQ
— Keith Hawkins (@kph_practice) January 9, 2024
came across @janframework yesterday and it's my fav native Apple Silicon LLM app yet. Love that I can switch to GPT 4 API and offline LLM models seamlessly. Looks promising! https://t.co/gyOX9gHbKQ
— Keith Hawkins (@kph_practice) January 9, 2024
+i just ran some ai models locally on my laptop using @janhq_ and can't believe how easy and cool it is. so, now i can have the same experience as with ChatGPT, but offline and without any data concerns
— Sergey Kaplich (@sergey_kaplich) January 4, 2024
i just ran some ai models locally on my laptop using @janhq_ and can't believe how easy and cool it is. so, now i can have the same experience as with ChatGPT, but offline and without any data concerns
— Sergey Kaplich (@sergey_kaplich) January 4, 2024
+https://t.co/scBqJ3kIzj Great way to try open source all models, like Mixtral8x7b offline. Love to see
— Chubby♨️ (@kimmonismus) January 4, 2024
https://t.co/scBqJ3kIzj Great way to try open source all models, like Mixtral8x7b offline. Love to see
— Chubby♨️ (@kimmonismus) January 4, 2024
jan.exe
Intel
M1/M2
jan.deb
jan.AppImage
From 8b9cd7a8b4320c24431ffaf59c5836d11b04f7a3 Mon Sep 17 00:00:00 2001
From: Van Pham <64197333+Van-QA@users.noreply.github.com>
Date: Wed, 28 Feb 2024 15:25:18 +0700
Subject: [PATCH 14/17] adding new feature for v0.4.7
---
docs/docs/template/QA_script.md | 132 ++++++++++++--------------------
1 file changed, 49 insertions(+), 83 deletions(-)
diff --git a/docs/docs/template/QA_script.md b/docs/docs/template/QA_script.md
index bba667bcd..9c7eeaf18 100644
--- a/docs/docs/template/QA_script.md
+++ b/docs/docs/template/QA_script.md
@@ -1,8 +1,8 @@
-# [Release Version] QA Script
+# Regression test
-**Release Version:** v0.4.6
+**Release Version:** v0.4.7
-**Operating System:**
+**Operating System:** MacOS
---
@@ -10,78 +10,64 @@
### 1. Users install app
-- [ ] :key: Test for clear user installation instructions.
-- [ ] :key: Verify that the installation path is correct for each OS.
- [ ] Check that the installation package is not corrupted and passes all security checks.
-- [ ] Validate that the app is correctly installed in the default or user-specified directory.
-- [ ] Ensure that all necessary dependencies are installed along with the app.
-- [ ] :key: :rocket: Confirm that the app launches successfully after installation.
+- [ ] :key: Confirm that the app launches successfully after installation.
### 2. Users update app
-- [ ] :key: Test that the updated version includes the new features or fixes outlined in the update notes.
- [ ] :key: Validate that the update does not corrupt user data or settings.
- [ ] :key: Confirm that the app restarts or prompts the user to restart after an update.
-
-### 3. Users uninstall app
-
-- [ ] :key::warning: Check that the uninstallation process removes the app successfully from the system.
-- [ ] Clean the Jan root directory and open the app to check if it creates all the necessary folders, especially models and extensions.
- [ ] When updating the app, check if the `/models` directory has any JSON files that change according to the update.
- [ ] Verify if updating the app also updates extensions correctly (test functionality changes, support notifications for necessary tests with each version related to extensions update).
-### 4. Users close app
+### 3. Users uninstall / close app
- [ ] :key: Ensure that after closing the app, all models are unloaded.
+- [ ] :key::warning: Check that the uninstallation process removes the app successfully from the system.
+- [ ] Clean the Jan root directory and open the app to check if it creates all the necessary folders, especially models and extensions.
+
## B. Overview
-### 1. Users use shortcut keys
+### 1. Shortcut key, memory usage / CPU usage
- [ ] :key: Test each shortcut key to confirm it works as described (My models, navigating, opening, closing, etc.).
-
-### 2. Users check the memory usage and CPU usage
-
- [ ] :key: Ensure that the interface presents the correct numbers for memory and CPU usage.
-### 3. Users check the `active model`
+### 2. Users check the `active model`
- [ ] :key: Verify that the app correctly displays the state of the loading model (e.g., loading, ready, error).
- [ ] :key: Confirm that the app allows users to switch between models if multiple are available.
- [ ] Check that the app provides feedback or instructions if the model fails to load.
+- [ ] Verify the troubleshooting assistant correctly capture hardware / log info #1784
## C. Thread
### 1. Users can chat with Jan, the default assistant
-- [ ] Verify that the input box for messages is present and functional.
-- [ ] :key: Check if typing a message and hitting `Send` results in the message appearing in the chat window.
-- [ ] :key: Confirm that Jan, the default assistant, replies to user inputs.
+- [ ] :key: Verify sending a message enables users to receive responses from model.
- [ ] :key: Ensure that the conversation thread is maintained without any loss of data upon sending multiple messages.
+- [ ] Users should be able to edit msg and the assistant will re-generate the answer based on the edited version of the message.
- [ ] Test for the ability to send different types of messages (e.g., text, emojis, code blocks).
-- [ ] :key: Validate the scroll functionality in the chat window for lengthy conversations.
-- [ ] Check if the user can copy the response.
-- [ ] Check if the user can delete responses.
-- [ ] :key: Check the `clear message` button works.
-- [ ] :key: Check the `delete entire chat` works.
-- [ ] Check if deleting all the chat retains the system prompt.
- [ ] Check the output format of the AI (code blocks, JSON, markdown, ...).
+- [ ] :key: Validate the scroll functionality in the chat window for lengthy conversations.
+- [ ] Check if the user can copy / delete the response.
+- [ ] :key: Check the `clear message` / `delete entire chat` button works.
+- [ ] Check if deleting all the chat retains the system prompt.
- [ ] :key: Validate that there is appropriate error handling and messaging if the assistant fails to respond.
- [ ] Test assistant's ability to maintain context over multiple exchanges.
-- [ ] :key: Check the `create new chat` button works correctly
+- [ ] :key: Check the `create new chat` button, and new conversation will have an automatically generated thread title based on users msg.
- [ ] Confirm that by changing `models` mid-thread the app can still handle it.
- [ ] Check the `regenerate` button renews the response (single / multiple times).
- [ ] Check the `Instructions` update correctly after the user updates it midway (mid-thread).
### 2. Users can customize chat settings like model parameters via both the GUI & thread.json
-- [ ] :key: Confirm that the Threads settings options are accessible.
- [ ] Test the functionality to adjust model parameters (e.g., Temperature, Top K, Top P) from the GUI and verify they are reflected in the chat behavior.
- [ ] :key: Ensure that changes can be saved and persisted between sessions.
- [ ] Validate that users can access and modify the thread.json file.
- [ ] :key: Check that changes made in thread.json are correctly applied to the chat session upon reload or restart.
- [ ] Check the maximum and minimum limits of the adjustable parameters and how they affect the assistant's responses.
-- [ ] :key: Validate user permissions for those who can change settings and persist them.
- [ ] :key: Ensure that users switch between threads with different models, the app can handle it.
### 3. Model dropdown
@@ -89,25 +75,16 @@
- [ ] Model size should display (for both installed and imported models)
### 4. Users can click on a history thread
-- [ ] Test the ability to click on any thread in the history panel.
-- [ ] :key: Verify that clicking a thread brings up the past conversation in the main chat window.
-- [ ] :key: Ensure that the selected thread is highlighted or otherwise indicated in the history panel.
- [ ] Confirm that the chat window displays the entire conversation from the selected history thread without any missing messages.
- [ ] :key: Check the performance and accuracy of the history feature when dealing with a large number of threads.
- [ ] Validate that historical threads reflect the exact state of the chat at that time, including settings.
- [ ] :key: Verify the ability to delete or clean old threads.
-- [ ] :key: Confirm that changing the title of the thread updates correctly.
+- [ ] Confirm that changing the title of the thread updates correctly.
### 5. Users can config instructions for the assistant.
-- [ ] Ensure there is a clear interface to input or change instructions for the assistant.
- [ ] Test if the instructions set by the user are being followed by the assistant in subsequent conversations.
- [ ] :key: Validate that changes to instructions are updated in real time and do not require a restart of the application or session.
-- [ ] :key: Confirm that the assistant's behavior changes in accordance with the new instructions provided.
- [ ] :key: Check for the ability to reset instructions to default or clear them completely.
-- [ ] :key: Test the feature that allows users to save custom sets of instructions for different scenarios.
-- [ ] Validate that instructions can be saved with descriptive names for easy retrieval.
-- [ ] :key: Check if the assistant can handle conflicting instructions and how it resolves them.
-- [ ] Ensure that instruction configurations are documented for user reference.
- [ ] :key: RAG - Users can import documents and the system should process queries about the uploaded file, providing accurate and appropriate responses in the conversation thread.
@@ -115,7 +92,6 @@
### 1. Users can discover recommended models (Jan ships with a few preconfigured model.json files)
-- [ ] :key: Verify that recommended models are displayed prominently on the main page.
- [ ] :key: Ensure that each model's recommendations are consistent with the user’s activity and preferences.
- [ ] Test the functionality of any filters that refine model recommendations.
@@ -123,7 +99,6 @@
- [ ] Display the best model for their RAM at the top.
- [ ] :key: Ensure that models are labeled with RAM requirements and compatibility.
-- [ ] :warning: Test that the platform provides alternative recommendations for models not suitable due to RAM limitations.
- [ ] :key: Check the download model functionality and validate if the cancel download feature works correctly.
### 3. Users can download models via a HuggingFace URL (coming soon)
@@ -132,22 +107,21 @@
- [ ] :key: Check the progress bar reflects the right process.
- [ ] Validate the error handling for invalid or inaccessible URLs.
-### 4. Users can add a new model to the Hub
+### 4. Users can import new models to the Hub
-- [ ] :key: Have clear instructions so users can do their own.
+- [ ] :key: Ensure import successfully via drag / drop or upload GGUF.
+- [ ] :key: Verify Move model binary file / Keep Original Files & Symlink option are working
+- [ ] :warning: Ensure it raises clear errors for users to fix the problem while adding a new model.
+- [ ] Users can add more info to the imported model / edit name
- [ ] :key: Ensure the new model updates after restarting the app.
-- [ ] :warning:Ensure it raises clear errors for users to fix the problem while adding a new model.
### 5. Users can use the model as they want
-- [ ] :key: Check `start` button response exactly what it does.
-- [ ] :key: Check `stop` button response exactly what it does.
-- [ ] :key: Check `delete` button response exactly what it does.
+- [ ] :key: Check `start` / `stop` / `delete` button response exactly what it does.
- [ ] Check if starting another model stops the other model entirely.
-- [ ] Check the `Explore models` navigate correctly to the model panel.
+- [x] :rocket: Check the `Explore models` navigate correctly to the model panel.
- [ ] :key: Check when deleting a model it will delete all the files on the user's computer.
- [ ] :warning:The recommended tags should present right for the user's hardware.
-- [ ] Assess that the descriptions of models are accurate and informative.
### 6. Users can Integrate With a Remote Server
- [ ] :key: Import openAI GPT model https://jan.ai/guides/using-models/integrate-with-remote-server/ and the model displayed in Hub / Thread dropdown
@@ -166,53 +140,45 @@
- [ ] :key: Test the 'Start' action for a model to ensure it initiates and the system resource usage reflects this change.
- [ ] :key: Verify the 'Stop' action for a model to confirm it ceases operation and frees up the system resources accordingly.
-- [ ] :key: Check the functionality that allows starting a model based on available system resources.
-- [ ] :key: Validate that the system prevents starting a new model if it exceeds safe resource utilization thresholds.
-- [ ] Ensure that the system provides warnings or recommendations when resource utilization is high before starting new models.
-- [ ] Test the ease of accessing model settings from the system monitor for resource management.
- [ ] Confirm that any changes in model status (start/stop) are logged or reported to the user for transparency.
## F. Settings
-### 1. Users can set color themes and dark/ light modes
+### 1. Appearance
-- [ ] Verify that the theme setting is easily accessible in the `Appearance` tab.
-- [ ] :key: Check that the theme change is reflected immediately upon selection.
- [ ] :key: Test the `Light`, `Dark`, and `System` theme settings to ensure they are functioning as expected.
- [ ] Confirm that the application saves the theme preference and persists it across sessions.
- [ ] Validate that all elements of the UI are compatible with the theme changes and maintain legibility and contrast.
-### 2. Users change the extensions [TBU]
+### 2. Extensions [TBU]
- [ ] Confirm that the `Extensions` tab lists all available plugins.
-- [ ] :key: Test the toggle switch for each plugin to ensure it enables or disables the plugin correctly.
-- [ ] Verify that plugin changes take effect without needing to restart the application unless specified.
-- [ ] :key: Check that the plugin's status (`Installed the latest version`) updates accurately after any changes.
-- [ ] Validate the `Manual Installation` process by selecting and installing a plugin file.
-- [ ] Test for proper error handling and user feedback when a plugin installation fails.
+- [x] :key: Test the toggle switch for each plugin to ensure it enables or disables the plugin correctly.
+- [x] Verify that plugin changes take effect without needing to restart the application unless specified.
+- [x] :key: Check that the plugin's status (`Installed the latest version`) updates accurately after any changes.
+- [x] Validate the `Manual Installation` process by selecting and installing a plugin file.
+- [x] Test for proper error handling and user feedback when a plugin installation fails.
-### 3. Users change the advanced settings
+### 3. Users can add custom plugins via manual installation [TBU]
+
+- [x] Verify that the `Manual Installation` option is clearly visible and accessible in the `Extensions` section.
+- [x] Test the functionality of the `Select` button within the `Manual Installation` area.
+- [x] :warning: Check that the file picker dialog allows for the correct plugin file types (e.g., .tgz).
+- [x] :key: Validate that the selected plugin file installs correctly and the plugin becomes functional.
+- [x] Ensure that there is a progress indicator or confirmation message once the installation is complete.
+- [x] Confirm that if the installation is interrupted or fails, the user is given a clear error message.
+- [x] :key: Test that the application prevents the installation of incompatible or corrupt plugin files.
+- [x] :key: Check that the user can uninstall or disable custom plugins as easily as pre-installed ones.
+- [x] Verify that the application's performance remains stable after the installation of custom plugins.
+
+### 4. Advanced settings
- [ ] :key: Test the `Experimental Mode` toggle to confirm it enables or disables experimental features as intended.
- [ ] :key: Check the functionality of `Open App Directory` to ensure it opens the correct folder in the system file explorer.
-- [ ] Validate that changes in advanced settings are applied immediately or provide appropriate instructions if a restart is needed.
-- [ ] Test the application's stability when experimental features are enabled.
-
-### 4. Users can add custom plugins via manual installation [TBU]
-
-- [ ] Verify that the `Manual Installation` option is clearly visible and accessible in the `Extensions` section.
-- [ ] Test the functionality of the `Select` button within the `Manual Installation` area.
-- [ ] :warning: Check that the file picker dialog allows for the correct plugin file types (e.g., .tgz).
-- [ ] :key: Validate that the selected plugin file installs correctly and the plugin becomes functional.
-- [ ] Ensure that there is a progress indicator or confirmation message once the installation is complete.
-- [ ] Confirm that if the installation is interrupted or fails, the user is given a clear error message.
-- [ ] :key: Test that the application prevents the installation of incompatible or corrupt plugin files.
-- [ ] :key: Check that the user can uninstall or disable custom plugins as easily as pre-installed ones.
-- [ ] Verify that the application's performance remains stable after the installation of custom plugins.
-
-### 5. Advanced Settings
-- [ ] Attemp to test downloading model from hub using **HTTP Proxy** [guideline](https://github.com/janhq/jan/pull/1562)
- [ ] Users can move **Jan data folder**
+- [ ] Validate that changes in advanced settings are applied immediately or provide appropriate instructions if a restart is needed.
+- [ ] Attemp to test downloading model from hub using **HTTP Proxy** [guideline](https://github.com/janhq/jan/pull/1562)
+- [ ] Logs that are older than 7 days or exceed 1MB in size will be automatically cleared upon starting the application.
- [ ] Users can click on Reset button to **factory reset** app settings to its original state & delete all usage data.
## G. Local API server
From 44d9f5b7b91105a45764bd7da8a4ed86ff313ce1 Mon Sep 17 00:00:00 2001
From: Faisal Amir
jan.exe
Intel
M1/M2
jan.deb
jan.AppImage