diff --git a/Dockerfile b/Dockerfile index 48b2d254f..e205a3f4f 100644 --- a/Dockerfile +++ b/Dockerfile @@ -44,7 +44,7 @@ COPY --from=builder /app/web ./web/ COPY --from=builder /app/models ./models/ RUN yarn workspace @janhq/uikit install && yarn workspace @janhq/uikit build -RUN yarn workspace jan-web install +RUN yarn workspace @janhq/web install RUN npm install -g serve@latest @@ -55,7 +55,7 @@ ENV JAN_API_PORT 1337 ENV API_BASE_URL http://localhost:1337 -CMD ["sh", "-c", "export NODE_ENV=production && yarn workspace jan-web build && cd web && npx serve out & cd server && node build/main.js"] +CMD ["sh", "-c", "export NODE_ENV=production && yarn workspace @janhq/web build && cd web && npx serve out & cd server && node build/main.js"] # docker build -t jan . # docker run -p 1337:1337 -p 3000:3000 -p 3928:3928 jan diff --git a/Dockerfile.gpu b/Dockerfile.gpu index 832e2c18c..d703b8b43 100644 --- a/Dockerfile.gpu +++ b/Dockerfile.gpu @@ -68,7 +68,7 @@ COPY --from=builder /app/web ./web/ COPY --from=builder /app/models ./models/ RUN yarn workspace @janhq/uikit install && yarn workspace @janhq/uikit build -RUN yarn workspace jan-web install +RUN yarn workspace @janhq/web install RUN npm install -g serve@latest @@ -81,7 +81,7 @@ ENV JAN_API_PORT 1337 ENV API_BASE_URL http://localhost:1337 -CMD ["sh", "-c", "export NODE_ENV=production && yarn workspace jan-web build && cd web && npx serve out & cd server && node build/main.js"] +CMD ["sh", "-c", "export NODE_ENV=production && yarn workspace @janhq/web build && cd web && npx serve out & cd server && node build/main.js"] # pre-requisites: nvidia-docker # docker build -t jan-gpu . -f Dockerfile.gpu diff --git a/charts/server/values.yaml b/charts/server/values.yaml index 70f463174..73d4e8916 100644 --- a/charts/server/values.yaml +++ b/charts/server/values.yaml @@ -150,7 +150,7 @@ common: command: ['/bin/sh', '-c'] args: [ - 'export NODE_ENV=production && yarn workspace jan-web build && cd web && npx serve out', + 'export NODE_ENV=production && yarn workspace @janhq/web build && cd web && npx serve out', ] replicaCount: 1 diff --git a/docs/openapi/.gitkeep b/docs/openapi/.gitkeep new file mode 100644 index 000000000..e69de29bb diff --git a/docs/openapi/jan.json b/docs/openapi/jan.json new file mode 100644 index 000000000..844a8f7ce --- /dev/null +++ b/docs/openapi/jan.json @@ -0,0 +1,2397 @@ +{ + "openapi": "3.0.0", + "info": { + "title": "API Reference", + "description": "# Introduction\nJan API is compatible with the [OpenAI API](https://platform.openai.com/docs/api-reference).\n", + "version": "0.1.8", + "contact": { + "name": "Jan Discord", + "url": "https://discord.gg/7EcEz7MrvA" + }, + "license": { + "name": "AGPLv3", + "url": "https://github.com/janhq/nitro/blob/main/LICENSE" + } + }, + "servers": [ + { + "url": "http://localhost:1337/v1" + } + ], + "tags": [ + { + "name": "Models", + "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.\n" + }, + { + "name": "Messages", + "description": "Messages capture a conversation's content. This can include the content from LLM responses and other metadata from [chat completions](/specs/chats).\n" + }, + { + "name": "Threads" + }, + { + "name": "Assistants", + "description": "Configures and utilizes different AI assistants for varied tasks" + } + ], + "x-tagGroups": [ + { + "name": "Endpoints", + "tags": ["Models", "Chat"] + }, + { + "name": "Chat", + "tags": ["Assistants", "Messages", "Threads"] + } + ], + "paths": { + "/chat/completions": { + "post": { + "operationId": "createChatCompletion", + "tags": ["Chat"], + "summary": "Create chat completion\n", + "description": "Creates a model response for the given chat conversation. Equivalent to OpenAI's create chat completion. \n", + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/ChatCompletionRequest" + } + } + } + }, + "responses": { + "200": { + "description": "OK", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/ChatCompletionResponse" + } + } + } + } + } + } + }, + "/models": { + "get": { + "operationId": "listModels", + "tags": ["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. \n", + "responses": { + "200": { + "description": "OK", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/ListModelsResponse" + } + } + } + } + } + } + }, + "/models/download/{model_id}": { + "get": { + "operationId": "downloadModel", + "tags": ["Models"], + "summary": "Download a specific model.", + "description": "Download a model.\n", + "parameters": [ + { + "in": "path", + "name": "model_id", + "required": true, + "schema": { + "type": "string", + "example": "mistral-ins-7b-q4" + }, + "description": "The ID of the model to use for this request.\n" + } + ], + "responses": { + "200": { + "description": "OK", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/DownloadModelResponse" + } + } + } + } + } + } + }, + "/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. \n", + "parameters": [ + { + "in": "path", + "name": "model_id", + "required": true, + "schema": { + "type": "string", + "example": "mistral-ins-7b-q4" + }, + "description": "The ID of the model to use for this request.\n" + } + ], + "responses": { + "200": { + "description": "OK", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/GetModelResponse" + } + } + } + } + } + }, + "delete": { + "operationId": "deleteModel", + "tags": ["Models"], + "summary": "Delete model", + "description": "Delete a model. Equivalent to OpenAI's delete model. \n", + "parameters": [ + { + "in": "path", + "name": "model_id", + "required": true, + "schema": { + "type": "string", + "example": "mistral-ins-7b-q4" + }, + "description": "The model id to delete\n" + } + ], + "responses": { + "200": { + "description": "OK", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/DeleteModelResponse" + } + } + } + } + } + } + }, + "/threads": { + "post": { + "operationId": "createThread", + "tags": ["Threads"], + "summary": "Create thread", + "description": "Create a thread. Equivalent to OpenAI's create thread. \n", + "requestBody": { + "required": false, + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/CreateThreadObject" + } + } + } + }, + "responses": { + "200": { + "description": "Thread created successfully", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/CreateThreadResponse" + } + } + } + } + } + }, + "get": { + "operationId": "listThreads", + "tags": ["Threads"], + "summary": "List threads", + "description": "Retrieves a list of all threads available in the system.\n", + "responses": { + "200": { + "description": "List of threads retrieved successfully", + "content": { + "application/json": { + "schema": { + "type": "array", + "items": { + "$ref": "#/components/schemas/ThreadObject" + }, + "example": [ + { + "id": "thread_abc123", + "object": "thread", + "created_at": 1699014083, + "assistants": ["assistant-001"], + "metadata": {}, + "messages": [] + }, + { + "id": "thread_abc456", + "object": "thread", + "created_at": 1699014083, + "assistants": ["assistant-002", "assistant-003"], + "metadata": {} + } + ] + } + } + } + } + } + } + }, + "/threads/{thread_id}": { + "get": { + "operationId": "getThread", + "tags": ["Threads"], + "summary": "Retrieve thread", + "description": "Retrieves detailed information about a specific thread using its thread_id. Equivalent to OpenAI's retrieve thread. \n", + "parameters": [ + { + "in": "path", + "name": "thread_id", + "required": true, + "schema": { + "type": "string" + }, + "description": "The ID of the thread to retrieve.\n" + } + ], + "responses": { + "200": { + "description": "Thread details retrieved successfully", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/GetThreadResponse" + } + } + } + } + } + }, + "patch": { + "operationId": "modifyThread", + "tags": ["Threads"], + "summary": "Modify thread", + "description": "Modifies a thread. Equivalent to OpenAI's modify thread. \n", + "parameters": [ + { + "in": "path", + "name": "thread_id", + "required": true, + "schema": { + "type": "string" + }, + "description": "The ID of the thread to be modified.\n" + } + ], + "requestBody": { + "required": true, + "content": { + "application/json": { + "schema": { + "type": "object", + "properties": { + "title": { + "type": "string", + "description": "Set the title of the thread", + "items": { + "$ref": "#/components/schemas/ThreadMessageObject" + } + } + } + } + } + } + }, + "responses": { + "200": { + "description": "Thread modified successfully", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/ModifyThreadResponse" + } + } + } + } + } + }, + "delete": { + "operationId": "deleteThread", + "tags": ["Threads"], + "summary": "Delete thread", + "description": "Delete a thread. Equivalent to OpenAI's delete thread. \n", + "parameters": [ + { + "in": "path", + "name": "thread_id", + "required": true, + "schema": { + "type": "string" + }, + "description": "The ID of the thread to be deleted.\n" + } + ], + "responses": { + "200": { + "description": "Thread deleted successfully", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/DeleteThreadResponse" + } + } + } + } + } + } + }, + "/assistants": { + "get": { + "operationId": "listAssistants", + "tags": ["Assistants"], + "summary": "List assistants", + "description": "Return a list of assistants. Equivalent to OpenAI's list assistants. \n", + "responses": { + "200": { + "description": "List of assistants retrieved successfully", + "content": { + "application/json": { + "schema": { + "type": "array", + "items": { + "type": "object", + "properties": { + "id": { + "type": "string" + }, + "object": { + "type": "string" + }, + "version": { + "type": "integer" + }, + "created_at": { + "type": "integer" + }, + "name": { + "type": "string" + }, + "description": { + "type": "string" + }, + "avatar": { + "type": "string", + "format": "uri" + }, + "models": { + "type": "array", + "items": { + "type": "object", + "properties": { + "model_id": { + "type": "string" + } + } + } + }, + "instructions": { + "type": "string" + }, + "events": { + "type": "object", + "properties": { + "in": { + "type": "array", + "items": {} + }, + "out": { + "type": "array", + "items": {} + } + } + }, + "metadata": { + "type": "object" + }, + "x-codeSamples": { + "type": "object", + "properties": { + "cURL": { + "type": "object", + "properties": { + "lang": { + "type": "string", + "example": "cURL" + }, + "source": { + "type": "string", + "example": "curl http://localhost:1337/v1/assistants \\\n -H \"Content-Type: application/json\"\n" + } + } + }, + "JavaScript": { + "type": "object", + "properties": { + "lang": { + "type": "string", + "example": "JavaScript" + }, + "source": { + "type": "string", + "example": "fetch('http://localhost:1337/v1/assistants', {\n method: 'GET',\n headers: {\n 'Content-Type': 'application/json'\n }\n})\n" + } + } + }, + "Node.js": { + "type": "object", + "properties": { + "lang": { + "type": "string", + "example": "Node.js" + }, + "source": { + "type": "string", + "example": "const fetch = require('node-fetch');\n\nfetch('http://localhost:1337/v1/assistants', {\n method: 'GET',\n headers: {\n 'Content-Type': 'application/json'\n }\n})\n" + } + } + }, + "Python": { + "type": "object", + "properties": { + "lang": { + "type": "string", + "example": "Python" + }, + "source": { + "type": "string", + "example": "import requests\n\nurl = 'http://localhost:1337/v1/assistants'\nheaders = {'Content-Type': 'application/json'}\n\nresponse = requests.get(url, headers=headers)\n" + } + } + } + } + } + } + } + } + } + } + } + } + } + }, + "/assistants/{assistant_id}": { + "get": { + "operationId": "getAssistant", + "tags": ["Assistants"], + "summary": "Retrieve assistant", + "description": "Retrieves an assistant. Equivalent to OpenAI's retrieve assistants. \n", + "parameters": [ + { + "in": "path", + "name": "assistant_id", + "required": true, + "schema": { + "type": "string", + "example": "jan" + }, + "description": "The ID of the assistant to retrieve.\n" + } + ], + "responses": { + "200": { + "description": "string", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/RetrieveAssistantResponse" + } + } + } + } + } + } + }, + "/threads/{thread_id}/messages": { + "get": { + "operationId": "listMessages", + "tags": ["Messages"], + "summary": "List messages", + "description": "Retrieves all messages from the given thread. Equivalent to OpenAI's list messages. \n", + "parameters": [ + { + "in": "path", + "name": "thread_id", + "required": true, + "schema": { + "type": "string" + }, + "description": "The ID of the thread from which to retrieve messages.\n" + } + ], + "responses": { + "200": { + "description": "List of messages retrieved successfully", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/ListMessagesResponse" + } + } + } + } + } + }, + "post": { + "operationId": "createMessage", + "tags": ["Messages"], + "summary": "Create message", + "description": "Create a message. Equivalent to OpenAI's list messages. \n", + "parameters": [ + { + "in": "path", + "name": "thread_id", + "required": true, + "schema": { + "type": "string" + }, + "description": "The ID of the thread to which the message will be posted.\n" + } + ], + "requestBody": { + "required": true, + "content": { + "application/json": { + "schema": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "Role of the sender, either 'user' or 'assistant'.\n", + "example": "user", + "enum": ["user", "assistant"] + }, + "content": { + "type": "string", + "description": "Text content of the message.\n", + "example": "How does AI work? Explain it in simple terms." + } + }, + "required": ["role", "content"] + } + } + } + }, + "responses": { + "200": { + "description": "Message created successfully", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/CreateMessageResponse" + } + } + } + } + } + } + }, + "/threads/{thread_id}/messages/{message_id}": { + "get": { + "operationId": "retrieveMessage", + "tags": ["Messages"], + "summary": "Retrieve message", + "description": "Retrieve a specific message from a thread using its thread_id and message_id. Equivalent to OpenAI's retrieve messages. \n", + "parameters": [ + { + "in": "path", + "name": "thread_id", + "required": true, + "schema": { + "type": "string" + }, + "description": "The ID of the thread containing the message.\n" + }, + { + "in": "path", + "name": "message_id", + "required": true, + "schema": { + "type": "string" + }, + "description": "The ID of the message to retrieve.\n" + } + ], + "responses": { + "200": { + "description": "OK", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/GetMessageResponse" + } + } + } + } + } + } + } + }, + "x-webhooks": { + "ModelObject": { + "post": { + "summary": "The model object", + "description": "Describe a model offering that can be used with the API. Equivalent to OpenAI's model object. \n", + "operationId": "ModelObject", + "tags": ["Models"], + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/ModelObject" + } + } + } + } + } + }, + "AssistantObject": { + "post": { + "summary": "The assistant object", + "description": "Build assistants that can call models and use tools to perform tasks. Equivalent to OpenAI's assistants object. \n", + "operationId": "AssistantObjects", + "tags": ["Assistants"], + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/AssistantObject" + } + } + } + } + } + }, + "MessageObject": { + "post": { + "summary": "The message object", + "description": "Information about a message in the thread. Equivalent to OpenAI's message object. \n", + "operationId": "MessageObject", + "tags": ["Messages"], + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": null + } + } + } + } + } + }, + "ThreadObject": { + "post": { + "summary": "The thread object", + "description": "Represents a thread that contains messages. Equivalent to OpenAI's thread object. ", + "operationId": "ThreadObject", + "tags": ["Threads"], + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": null + } + } + } + } + } + } + }, + "components": { + "schemas": { + "ThreadObject": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the thread, defaults to foldername.\n", + "example": "thread_...." + }, + "object": { + "type": "string", + "description": "Type of the object, defaults to thread.\n", + "example": "thread" + }, + "title": { + "type": "string", + "description": "A brief summary or description of the thread, defaults to an empty string.\n", + "example": "funny physics joke" + }, + "assistants": { + "type": "array", + "description": "", + "items": { + "properties": { + "assistant_id": { + "type": "string", + "description": "The identifier of assistant, defaults to \"jan\"\n", + "example": "jan" + }, + "model": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "", + "example": "..." + }, + "settings": { + "type": "object", + "description": "Defaults to and overrides assistant.json's \"settings\" (and if none, then model.json \"settings\")\n" + }, + "parameters": { + "type": "object", + "description": "Defaults to and overrides assistant.json's \"parameters\" (and if none, then model.json \"parameters\")\n" + } + } + } + } + } + }, + "created": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the thread, defaults to file creation time.\n", + "example": 1231231 + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the thread, defaults to an empty object.\n", + "example": {} + } + } + }, + "GetThreadResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the thread.", + "example": "thread_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object", + "example": "thread" + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the thread.", + "example": 1699014083 + }, + "assistants": { + "type": "array", + "items": { + "type": "string" + }, + "description": "List of assistants involved in the thread.", + "example": ["assistant-001"] + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the thread.", + "example": {} + }, + "messages": { + "type": "array", + "items": { + "type": "string" + }, + "description": "List of messages within the thread.", + "example": [] + } + } + }, + "CreateThreadResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the newly created thread.", + "example": "thread_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's a thread.", + "example": "thread" + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the thread.", + "example": 1699014083 + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the newly created thread.", + "example": {} + } + } + }, + "CreateThreadObject": { + "type": "object", + "properties": { + "object": { + "type": "string", + "description": "Type of the object, indicating it's a thread.", + "example": "thread" + }, + "title": { + "type": "string", + "description": "A brief summary or description of the thread, defaults to an empty string.\n", + "example": "funny physics joke" + }, + "assistants": { + "type": "array", + "description": "assistant involved in the thread", + "items": { + "properties": { + "assistant_id": { + "type": "string", + "description": "The identifier of assistant, defaults to \"jan\"\n", + "example": "jan" + }, + "assistant_name": { + "type": "string", + "description": "The name of assistant, defaults to \"Jan\"\n", + "example": "Jan" + }, + "instructions": { + "type": "string", + "description": "The instruction of assistant, defaults to \"Be my grammar corrector\"\n" + }, + "model": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "Model id", + "example": "mistral-ins-7b-q4" + }, + "settings": { + "type": "object", + "description": "Defaults to and overrides assistant.json's \"settings\" (and if none, then model.json \"settings\")\n" + }, + "parameters": { + "type": "object", + "description": "Defaults to and overrides assistant.json's \"parameters\" (and if none, then model.json \"parameters\")\n" + }, + "engine": { + "type": "string", + "description": "Engine id", + "example": "nitro" + } + } + } + } + } + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the thread, defaults to an empty object.\n" + } + } + }, + "ThreadMessageObject": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "\"Role of the sender, either 'user' or 'assistant'.\"\n", + "enum": ["user", "assistant"] + }, + "content": { + "type": "string", + "description": "\"Text content of the message.\"\n" + }, + "file_ids": { + "type": "array", + "items": { + "type": "string" + }, + "description": "\"Array of file IDs associated with the message, if any.\"\n" + } + } + }, + "ModifyThreadResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "\"The identifier of the modified thread.\"\n", + "example": "thread_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's a thread.", + "example": "thread" + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the thread.", + "example": 1699014083 + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the modified thread.", + "example": {} + } + } + }, + "DeleteThreadResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the deleted thread.", + "example": "thread_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating the thread has been deleted.", + "example": "thread.deleted" + }, + "deleted": { + "type": "boolean", + "description": "Indicates whether the thread was successfully deleted.", + "example": true + } + } + }, + "ListModelsResponse": { + "type": "object", + "properties": { + "object": { + "type": "string", + "enum": ["list"] + }, + "data": { + "type": "array", + "items": { + "$ref": "#/components/schemas/Model" + } + } + }, + "required": ["object", "data"] + }, + "Model": { + "type": "object", + "properties": { + "source_url": { + "type": "string", + "format": "uri", + "description": "URL to the source of the model.", + "example": "https://huggingface.co/janhq/trinity-v1.2-GGUF/resolve/main/trinity-v1.2.Q4_K_M.gguf" + }, + "id": { + "type": "string", + "description": "Unique identifier used in chat-completions model_name, matches folder name.", + "example": "trinity-v1.2-7b" + }, + "object": { + "type": "string", + "example": "model" + }, + "name": { + "type": "string", + "description": "Name of the model.", + "example": "Trinity-v1.2 7B Q4" + }, + "version": { + "type": "string", + "default": "1.0", + "description": "The version number of the model." + }, + "description": { + "type": "string", + "description": "Description of the model.", + "example": "Trinity is an experimental model merge using the Slerp method. Recommended for daily assistance purposes." + }, + "format": { + "type": "string", + "description": "State format of the model, distinct from the engine.", + "example": "gguf" + }, + "settings": { + "type": "object", + "properties": { + "ctx_len": { + "type": "integer", + "description": "Context length.", + "example": 4096 + }, + "prompt_template": { + "type": "string", + "example": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant" + } + }, + "additionalProperties": false + }, + "parameters": { + "type": "object", + "properties": { + "temperature": { + "example": 0.7 + }, + "top_p": { + "example": 0.95 + }, + "stream": { + "example": true + }, + "max_tokens": { + "example": 4096 + }, + "stop": { + "example": [] + }, + "frequency_penalty": { + "example": 0 + }, + "presence_penalty": { + "example": 0 + } + }, + "additionalProperties": false + }, + "metadata": { + "type": "object", + "properties": { + "author": { + "type": "string", + "example": "Jan" + }, + "tags": { + "type": "array", + "items": { + "type": "string" + }, + "example": ["7B", "Merged", "Featured"] + }, + "size": { + "type": "integer", + "example": 4370000000 + }, + "cover": { + "type": "string", + "format": "uri", + "example": "https://raw.githubusercontent.com/janhq/jan/main/models/trinity-v1.2-7b/cover.png" + } + }, + "additionalProperties": false + }, + "engine": { + "example": "nitro" + } + } + }, + "ModelObject": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the model.\n", + "example": "trinity-v1.2-7b" + }, + "object": { + "type": "string", + "description": "The type of the object, indicating it's a model.\n", + "default": "model" + }, + "created": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the model.\n", + "example": 1253935178 + }, + "owned_by": { + "type": "string", + "description": "The entity that owns the model.\n", + "example": "_" + } + } + }, + "GetModelResponse": { + "type": "object", + "properties": { + "source_url": { + "type": "string", + "format": "uri", + "description": "URL to the source of the model.", + "example": "https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/mistral-7b-instruct-v0.2.Q4_K_M.gguf" + }, + "id": { + "type": "string", + "description": "Unique identifier used in chat-completions model_name, matches folder name.", + "example": "mistral-ins-7b-q4" + }, + "object": { + "type": "string", + "example": "model" + }, + "name": { + "type": "string", + "description": "Name of the model.", + "example": "Mistral Instruct 7B Q4" + }, + "version": { + "type": "string", + "default": "1.0", + "description": "The version number of the model." + }, + "description": { + "type": "string", + "description": "Description of the model.", + "example": "Trinity is an experimental model merge using the Slerp method. Recommended for daily assistance purposes." + }, + "format": { + "type": "string", + "description": "State format of the model, distinct from the engine.", + "example": "gguf" + }, + "settings": { + "type": "object", + "properties": { + "ctx_len": { + "type": "integer", + "description": "Context length.", + "example": 4096 + }, + "prompt_template": { + "type": "string", + "example": "[INST] {prompt} [/INST]" + } + }, + "additionalProperties": false + }, + "parameters": { + "type": "object", + "properties": { + "temperature": { + "example": 0.7 + }, + "top_p": { + "example": 0.95 + }, + "stream": { + "example": true + }, + "max_tokens": { + "example": 4096 + }, + "stop": { + "example": [] + }, + "frequency_penalty": { + "example": 0 + }, + "presence_penalty": { + "example": 0 + } + }, + "additionalProperties": false + }, + "metadata": { + "type": "object", + "properties": { + "author": { + "type": "string", + "example": "MistralAI" + }, + "tags": { + "type": "array", + "items": { + "type": "string" + }, + "example": ["7B", "Featured", "Foundation Model"] + }, + "size": { + "example": 4370000000, + "type": "integer" + }, + "cover": { + "example": "https://raw.githubusercontent.com/janhq/jan/main/models/mistral-ins-7b-q4/cover.png", + "type": "string" + } + }, + "additionalProperties": false + }, + "engine": { + "example": "nitro" + } + } + }, + "DeleteModelResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the model that was deleted.", + "example": "mistral-ins-7b-q4" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's a model.", + "default": "model" + }, + "deleted": { + "type": "boolean", + "description": "Indicates whether the model was successfully deleted.", + "example": true + } + } + }, + "StartModelResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the model that was started.", + "example": "model-zephyr-7B" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's a model.", + "default": "model" + }, + "state": { + "type": "string", + "description": "The current state of the model after the start operation.", + "example": "running" + } + }, + "required": ["id", "object", "state"] + }, + "StopModelResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the model that was started.", + "example": "model-zephyr-7B" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's a model.", + "default": "model" + }, + "state": { + "type": "string", + "description": "The current state of the model after the start operation.", + "example": "stopped" + } + }, + "required": ["id", "object", "state"] + }, + "DownloadModelResponse": { + "type": "object", + "properties": { + "message": { + "type": "string", + "description": "Message indicates Jan starting download corresponding model.", + "example": "Starting download mistral-ins-7b-q4" + } + } + }, + "MessageObject": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "Sequential or UUID identifier of the message.\n", + "example": 0 + }, + "object": { + "type": "string", + "description": "Type of the object, defaults to 'thread.message'.\n", + "example": "thread.message" + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the message.\n" + }, + "thread_id": { + "type": "string", + "description": "Identifier of the thread to which this message belongs. Defaults to parent thread.\n", + "example": "thread_asdf" + }, + "assistant_id": { + "type": "string", + "description": "Identifier of the assistant involved in the message. Defaults to parent thread.\n", + "example": "jan" + }, + "role": { + "type": "string", + "enum": ["user", "assistant"], + "description": "Role of the sender, either 'user' or 'assistant'.\n" + }, + "content": { + "type": "array", + "items": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "Type of content, e.g., 'text'.\n" + }, + "text": { + "type": "object", + "properties": { + "value": { + "type": "string", + "description": "Text content of the message.\n", + "example": "Hi!?" + }, + "annotations": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Annotations for the text content, if any.\n", + "example": [] + } + } + } + } + } + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the message, defaults to an empty object.\n", + "example": {} + } + } + }, + "GetMessageResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the message.", + "example": "msg_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's a thread message.", + "default": "thread.message" + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the message.", + "example": 1699017614 + }, + "thread_id": { + "type": "string", + "description": "Identifier of the thread to which this message belongs.", + "example": "thread_abc123" + }, + "role": { + "type": "string", + "description": "Role of the sender, either 'user' or 'assistant'.", + "example": "user" + }, + "content": { + "type": "array", + "items": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "Type of content, e.g., 'text'.", + "example": "text" + }, + "text": { + "type": "object", + "properties": { + "value": { + "type": "string", + "description": "Text content of the message.", + "example": "How does AI work? Explain it in simple terms." + }, + "annotations": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Annotations for the text content, if any.", + "example": [] + } + } + } + } + } + }, + "file_ids": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Array of file IDs associated with the message, if any.", + "example": [] + }, + "assistant_id": { + "type": "string", + "description": "Identifier of the assistant involved in the message, if applicable.", + "example": null + }, + "run_id": { + "type": "string", + "description": "Run ID associated with the message, if applicable.", + "example": null + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the message.", + "example": {} + } + } + }, + "CreateMessageResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the created message.", + "example": "msg_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's a thread message.", + "example": "thread.message" + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the message.", + "example": 1699017614 + }, + "thread_id": { + "type": "string", + "description": "Identifier of the thread to which this message belongs.", + "example": "thread_abc123" + }, + "role": { + "type": "string", + "description": "Role of the sender, either 'user' or 'assistant'.", + "example": "user" + }, + "content": { + "type": "array", + "items": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "Type of content, e.g., 'text'.", + "example": "text" + }, + "text": { + "type": "object", + "properties": { + "value": { + "type": "string", + "description": "Text content of the message.", + "example": "How does AI work? Explain it in simple terms." + }, + "annotations": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Annotations for the text content, if any.", + "example": [] + } + } + } + } + } + }, + "file_ids": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Array of file IDs associated with the message, if any.", + "example": [] + }, + "assistant_id": { + "type": "string", + "description": "Identifier of the assistant involved in the message, if applicable.", + "example": null + }, + "run_id": { + "type": "string", + "description": "Run ID associated with the message, if applicable.", + "example": null + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the message.", + "example": {} + } + } + }, + "ListMessagesResponse": { + "type": "object", + "properties": { + "object": { + "type": "string", + "description": "Type of the object, indicating it's a list.", + "default": "list" + }, + "data": { + "type": "array", + "items": { + "$ref": "#/components/schemas/ListMessageObject" + } + }, + "first_id": { + "type": "string", + "description": "Identifier of the first message in the list.", + "example": "msg_abc123" + }, + "last_id": { + "type": "string", + "description": "Identifier of the last message in the list.", + "example": "msg_abc456" + }, + "has_more": { + "type": "boolean", + "description": "Indicates whether there are more messages to retrieve.", + "example": false + } + } + }, + "ListMessageObject": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the message.", + "example": "msg_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's a thread message.", + "example": "thread.message" + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the message.", + "example": 1699017614 + }, + "thread_id": { + "type": "string", + "description": "Identifier of the thread to which this message belongs.", + "example": "thread_abc123" + }, + "role": { + "type": "string", + "description": "Role of the sender, either 'user' or 'assistant'.", + "example": "user" + }, + "content": { + "type": "array", + "items": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "Type of content, e.g., 'text'." + }, + "text": { + "type": "object", + "properties": { + "value": { + "type": "string", + "description": "Text content of the message.", + "example": "How does AI work? Explain it in simple terms." + }, + "annotations": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Annotations for the text content, if any." + } + } + } + } + } + }, + "file_ids": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Array of file IDs associated with the message, if any.", + "example": [] + }, + "assistant_id": { + "type": "string", + "description": "Identifier of the assistant involved in the message, if applicable.", + "example": null + }, + "run_id": { + "type": "string", + "description": "Run ID associated with the message, if applicable.", + "example": null + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the message.", + "example": {} + } + } + }, + "MessageFileObject": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the file.", + "example": "file-abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's a thread message file.", + "example": "thread.message.file" + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the file.", + "example": 1699061776 + }, + "message_id": { + "type": "string", + "description": "Identifier of the message to which this file is associated.", + "example": "msg_abc123" + } + } + }, + "ListMessageFilesResponse": { + "type": "object", + "properties": { + "object": { + "type": "string", + "description": "Type of the object, indicating it's a list.", + "default": "list" + }, + "data": { + "type": "array", + "items": { + "$ref": "#/components/schemas/MessageFileObject" + } + } + } + }, + "ChatObject": { + "type": "object", + "properties": { + "messages": { + "type": "array", + "description": "Contains input data or prompts for the model to process.\n", + "items": { + "type": "object", + "properties": { + "content": { + "type": "string" + }, + "role": { + "type": "string" + } + } + }, + "example": [ + { + "content": "Hello there :wave:", + "role": "assistant" + }, + { + "content": "Can you write a long story", + "role": "user" + } + ] + }, + "stream": { + "type": "boolean", + "default": true, + "description": "Enables continuous output generation, allowing for streaming of model responses." + }, + "model": { + "type": "string", + "example": "gpt-3.5-turbo", + "description": "Specifies the model being used for inference or processing tasks." + }, + "max_tokens": { + "type": "number", + "default": 2048, + "description": "The maximum number of tokens the model will generate in a single response." + }, + "stop": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Defines specific tokens or phrases at which the model will stop generating further output.", + "example": ["hello"] + }, + "frequency_penalty": { + "type": "number", + "default": 0, + "description": "Adjusts the likelihood of the model repeating words or phrases in its output." + }, + "presence_penalty": { + "type": "number", + "default": 0, + "description": "Influences the generation of new and varied concepts in the model's output." + }, + "temperature": { + "type": "number", + "default": 0.7, + "description": "Controls the randomness of the model's output." + }, + "top_p": { + "type": "number", + "default": 0.95, + "description": "Set probability threshold for more relevant outputs." + }, + "cache_prompt": { + "type": "boolean", + "default": true, + "description": "Optimize performance in repeated or similar requests." + } + } + }, + "ChatCompletionRequest": { + "type": "object", + "properties": { + "messages": { + "type": "array", + "description": "Contains input data or prompts for the model to process.\n", + "items": { + "type": "object", + "properties": { + "content": { + "type": "string" + }, + "role": { + "type": "string" + } + } + }, + "example": [ + { + "content": "You are a helpful assistant.", + "role": "system" + }, + { + "content": "Hello!", + "role": "user" + } + ] + }, + "model": { + "type": "string", + "example": "tinyllama-1.1b", + "description": "Specifies the model being used for inference or processing tasks.\n" + }, + "stream": { + "type": "boolean", + "default": true, + "description": "Enables continuous output generation, allowing for streaming of model responses.\n" + }, + "max_tokens": { + "type": "number", + "default": 2048, + "description": "The maximum number of tokens the model will generate in a single response.\n" + }, + "stop": { + "type": "array", + "items": { + "type": "string" + }, + "description": "Defines specific tokens or phrases at which the model will stop generating further output.\n", + "example": ["hello"] + }, + "frequency_penalty": { + "type": "number", + "default": 0, + "description": "Adjusts the likelihood of the model repeating words or phrases in its output.\n" + }, + "presence_penalty": { + "type": "number", + "default": 0, + "description": "Influences the generation of new and varied concepts in the model's output.\n" + }, + "temperature": { + "type": "number", + "default": 0.7, + "description": "Controls the randomness of the model's output.\n" + }, + "top_p": { + "type": "number", + "default": 0.95, + "description": "Set probability threshold for more relevant outputs.\n" + } + } + }, + "ChatCompletionResponse": { + "type": "object", + "description": "Description of the response structure", + "properties": { + "choices": { + "type": "array", + "description": "Array of choice objects", + "items": { + "type": "object", + "properties": { + "finish_reason": { + "type": "string", + "nullable": true, + "example": null, + "description": "Reason for finishing the response, if applicable" + }, + "index": { + "type": "integer", + "example": 0, + "description": "Index of the choice" + }, + "message": { + "type": "object", + "properties": { + "content": { + "type": "string", + "example": "Hello user. What can I help you with?", + "description": "Content of the message" + }, + "role": { + "type": "string", + "example": "assistant", + "description": "Role of the sender" + } + } + } + } + } + }, + "created": { + "type": "integer", + "example": 1700193928, + "description": "Timestamp of when the response was created" + }, + "id": { + "type": "string", + "example": "ebwd2niJvJB1Q2Whyvkz", + "description": "Unique identifier of the response" + }, + "model": { + "type": "string", + "nullable": true, + "example": "_", + "description": "Model used for generating the response" + }, + "object": { + "type": "string", + "example": "chat.completion", + "description": "Type of the response object" + }, + "system_fingerprint": { + "type": "string", + "nullable": true, + "example": "_", + "description": "System fingerprint" + }, + "usage": { + "type": "object", + "description": "Information about the usage of tokens", + "properties": { + "completion_tokens": { + "type": "integer", + "example": 500, + "description": "Number of tokens used for completion" + }, + "prompt_tokens": { + "type": "integer", + "example": 33, + "description": "Number of tokens used in the prompt" + }, + "total_tokens": { + "type": "integer", + "example": 533, + "description": "Total number of tokens used" + } + } + } + } + }, + "AssistantObject": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the assistant.", + "example": "asst_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's an assistant.", + "default": "assistant" + }, + "version": { + "type": "integer", + "description": "Version number of the assistant.", + "example": 1 + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the assistant.", + "example": 1698984975 + }, + "name": { + "type": "string", + "description": "Name of the assistant.", + "example": "Math Tutor" + }, + "description": { + "type": "string", + "description": "Description of the assistant. Can be null.", + "example": null + }, + "avatar": { + "type": "string", + "description": "URL of the assistant's avatar. Jan-specific property.", + "example": "https://pic.png" + }, + "models": { + "type": "array", + "description": "List of models associated with the assistant. Jan-specific property.", + "items": { + "type": "object", + "properties": { + "model_id": { + "type": "string", + "example": "model_0" + } + } + } + }, + "instructions": { + "type": "string", + "description": "A system prompt for the assistant.", + "example": "Be concise" + }, + "events": { + "type": "object", + "description": "Event subscription settings for the assistant.", + "properties": { + "in": { + "type": "array", + "items": { + "type": "string" + } + }, + "out": { + "type": "array", + "items": { + "type": "string" + } + } + } + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the assistant." + } + } + }, + "ListAssistantsResponse": { + "type": "object" + }, + "CreateAssistantResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the assistant.", + "example": "asst_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's an assistant.", + "default": "assistant" + }, + "version": { + "type": "integer", + "description": "Version number of the assistant.", + "example": 1 + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the assistant.", + "example": 1698984975 + }, + "name": { + "type": "string", + "description": "Name of the assistant.", + "example": "Math Tutor" + }, + "description": { + "type": "string", + "description": "Description of the assistant. Can be null.", + "example": null + }, + "avatar": { + "type": "string", + "description": "URL of the assistant's avatar. Jan-specific property.", + "example": "https://pic.png" + }, + "models": { + "type": "array", + "description": "List of models associated with the assistant. Jan-specific property.", + "items": { + "type": "object", + "properties": { + "model_id": { + "type": "string", + "example": "model_0" + } + } + } + }, + "instructions": { + "type": "string", + "description": "A system prompt for the assistant.", + "example": "Be concise" + }, + "events": { + "type": "object", + "description": "Event subscription settings for the assistant.", + "properties": { + "in": { + "type": "array", + "items": { + "type": "string" + } + }, + "out": { + "type": "array", + "items": { + "type": "string" + } + } + } + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the assistant." + } + } + }, + "RetrieveAssistantResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the assistant.", + "example": "asst_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's an assistant.", + "default": "assistant" + }, + "version": { + "type": "integer", + "description": "Version number of the assistant.", + "example": 1 + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the assistant.", + "example": 1698984975 + }, + "name": { + "type": "string", + "description": "Name of the assistant.", + "example": "Math Tutor" + }, + "description": { + "type": "string", + "description": "Description of the assistant. Can be null.", + "example": null + }, + "avatar": { + "type": "string", + "description": "URL of the assistant's avatar. Jan-specific property.", + "example": "https://pic.png" + }, + "models": { + "type": "array", + "description": "List of models associated with the assistant. Jan-specific property.", + "items": { + "type": "object", + "properties": { + "model_id": { + "type": "string", + "example": "model_0" + } + } + } + }, + "instructions": { + "type": "string", + "description": "A system prompt for the assistant.", + "example": "Be concise" + }, + "events": { + "type": "object", + "description": "Event subscription settings for the assistant.", + "properties": { + "in": { + "type": "array", + "items": { + "type": "string" + } + }, + "out": { + "type": "array", + "items": { + "type": "string" + } + } + } + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the assistant." + } + } + }, + "ModifyAssistantObject": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the assistant.", + "example": "asst_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's an assistant.", + "default": "assistant" + }, + "version": { + "type": "integer", + "description": "Version number of the assistant.", + "example": 1 + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the assistant.", + "example": 1698984975 + }, + "name": { + "type": "string", + "description": "Name of the assistant.", + "example": "Math Tutor" + }, + "description": { + "type": "string", + "description": "Description of the assistant. Can be null.", + "example": null + }, + "avatar": { + "type": "string", + "description": "URL of the assistant's avatar. Jan-specific property.", + "example": "https://pic.png" + }, + "models": { + "type": "array", + "description": "List of models associated with the assistant. Jan-specific property.", + "items": { + "type": "object", + "properties": { + "model_id": { + "type": "string", + "example": "model_0" + } + } + } + }, + "instructions": { + "type": "string", + "description": "A system prompt for the assistant.", + "example": "Be concise" + }, + "events": { + "type": "object", + "description": "Event subscription settings for the assistant.", + "properties": { + "in": { + "type": "array", + "items": { + "type": "string" + } + }, + "out": { + "type": "array", + "items": { + "type": "string" + } + } + } + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the assistant." + } + } + }, + "ModifyAssistantResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the assistant.", + "example": "asst_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating it's an assistant.", + "default": "assistant" + }, + "version": { + "type": "integer", + "description": "Version number of the assistant.", + "example": 1 + }, + "created_at": { + "type": "integer", + "format": "int64", + "description": "Unix timestamp representing the creation time of the assistant.", + "example": 1698984975 + }, + "name": { + "type": "string", + "description": "Name of the assistant.", + "example": "Physics Tutor" + }, + "description": { + "type": "string", + "description": "Description of the assistant. Can be null.", + "example": null + }, + "avatar": { + "type": "string", + "description": "URL of the assistant's avatar. Jan-specific property.", + "example": "https://pic.png" + }, + "models": { + "type": "array", + "description": "List of models associated with the assistant. Jan-specific property.", + "items": { + "type": "object", + "properties": { + "model_id": { + "type": "string", + "example": "model_0" + } + } + } + }, + "instructions": { + "type": "string", + "description": "A system prompt for the assistant.", + "example": "Be concise!" + }, + "events": { + "type": "object", + "description": "Event subscription settings for the assistant.", + "properties": { + "in": { + "type": "array", + "items": { + "type": "string" + } + }, + "out": { + "type": "array", + "items": { + "type": "string" + } + } + } + }, + "metadata": { + "type": "object", + "description": "Metadata associated with the assistant." + } + } + }, + "DeleteAssistantResponse": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "The identifier of the deleted assistant.", + "example": "asst_abc123" + }, + "object": { + "type": "string", + "description": "Type of the object, indicating the assistant has been deleted.", + "example": "assistant.deleted" + }, + "deleted": { + "type": "boolean", + "description": "Indicates whether the assistant was successfully deleted.", + "example": true + } + } + } + } + } +} diff --git a/docs/openapi/jan.yaml b/docs/openapi/jan.yaml new file mode 100644 index 000000000..35fd43175 --- /dev/null +++ b/docs/openapi/jan.yaml @@ -0,0 +1,1043 @@ +--- +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). +version: 0.1.8 +contact: + name: Jan Discord + url: https://discord.gg/7EcEz7MrvA +license: + name: AGPLv3 + url: https://github.com/janhq/nitro/blob/main/LICENSE +servers: + - url: /v1 +tags: + - name: Models + 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. + - name: Messages + description: > + 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 + description: Configures and utilizes different AI assistants for varied tasks +x-tagGroups: + - name: Endpoints + tags: + - Models + - Chat + - name: Chat + tags: + - Assistants + - Messages + - Threads +paths: + /chat/completions: + post: + operationId: createChatCompletion + tags: + - Chat + summary: | + Create chat completion + description: > + 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': + description: OK + content: + application/json: + schema: + $ref: specs/chat.yaml#/components/schemas/ChatCompletionResponse + x-codeSamples: + - lang: cURL + source: | + curl -X 'POST' \ + 'http://localhost:1337/v1/chat/completions' \ + -H 'accept: application/json' \ + -H 'Content-Type: application/json' \ + -d '{ + "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 + }' + - 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 + tags: + - 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. + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: specs/models.yaml#/components/schemas/ListModelsResponse + x-codeSamples: + - lang: cURL + 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: 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)); + - lang: Python + source: |- + import requests + + url = 'http://localhost:1337/v1/models' + headers = {'Accept': 'application/json'} + response = requests.get(url, headers=headers) + data = response.json() + '/models/download/{model_id}': + get: + operationId: downloadModel + tags: + - Models + summary: Download a specific model. + description: | + Download a model. + parameters: + - in: path + name: model_id + required: true + schema: + type: string + example: mistral-ins-7b-q4 + description: | + The ID of the model to use for this request. + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: specs/models.yaml#/components/schemas/DownloadModelResponse + x-codeSamples: + - lang: cURL + 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 + 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: + - in: path + name: model_id + required: true + schema: + type: string + example: mistral-ins-7b-q4 + description: | + The ID of the model to use for this request. + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: specs/models.yaml#/components/schemas/GetModelResponse + x-codeSamples: + - lang: cURL + source: |- + curl -X 'GET' \ + 'http://localhost:1337/v1/models/{model_id}' \ + -H 'accept: application/json' + - lang: JavaScript + source: |- + const fetch = require('node-fetch'); + + const modelId = 'mistral-ins-7b-q4'; + + fetch(`http://localhost:1337/v1/models/${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: + - Models + summary: Delete model + description: > + Delete a model. + Equivalent to OpenAI's delete model. + parameters: + - in: path + name: model_id + required: true + schema: + type: string + example: mistral-ins-7b-q4 + description: | + The model id to delete + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: specs/models.yaml#/components/schemas/DeleteModelResponse + x-codeSamples: + - lang: cURL + source: |- + curl -X 'DELETE' \ + 'http://localhost:1337/v1/models/{model_id}' \ + -H 'accept: application/json' + - lang: JavaScript + source: |- + const fetch = require('node-fetch'); + + const modelId = 'mistral-ins-7b-q4'; + + fetch(`http://localhost:1337/v1/models/${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 + tags: + - Threads + summary: Create thread + description: > + Create a thread. + Equivalent to OpenAI's create thread. + requestBody: + required: false + content: + application/json: + schema: + $ref: specs/threads.yaml#/components/schemas/CreateThreadObject + responses: + '200': + description: Thread created successfully + content: + application/json: + schema: + $ref: specs/threads.yaml#/components/schemas/CreateThreadResponse + x-codeSamples: + - lang: cURL + source: | + curl -X POST http://localhost:1337/v1/threads \ + -H "Content-Type: application/json" \ + -d '{ + "messages": [{ + "role": "user", + "content": "Hello, what is AI?", + "file_ids": ["file-abc123"] + }, { + "role": "user", + "content": "How does AI work? Explain it in simple terms." + }] + }' + - lang: JavaScript + source: |- + const fetch = require('node-fetch'); + + fetch('http://localhost:1337/v1/threads', { + method: 'POST', + headers: { + 'Content-Type': 'application/json' + }, + body: JSON.stringify({ + messages: [ + { + role: 'user', + content: 'Hello, what is AI?', + file_ids: ['file-abc123'] + }, + { + role: 'user', + content: 'How does AI work? Explain it in simple terms.' + } + ] + }) + }); + - lang: Node.js + source: |- + const fetch = require('node-fetch'); + + fetch('http://localhost:1337/v1/threads', { + method: 'POST', + headers: { + 'Content-Type': 'application/json' + }, + body: JSON.stringify({ + messages: [ + { + role: 'user', + content: 'Hello, what is AI?', + file_ids: ['file-abc123'] + }, + { + role: 'user', + content: 'How does AI work? Explain it in simple terms.' + } + ] + }) + }); + - lang: Python + source: |- + import requests + + url = 'http://localhost:1337/v1/threads' + payload = { + 'messages': [ + { + 'role': 'user', + 'content': 'Hello, what is AI?', + 'file_ids': ['file-abc123'] + }, + { + 'role': 'user', + 'content': 'How does AI work? Explain it in simple terms.' + } + ] + } + + response = requests.post(url, json=payload) + print(response.text) + get: + operationId: listThreads + tags: + - Threads + summary: List threads + description: | + Retrieves a list of all threads available in the system. + responses: + '200': + description: List of threads retrieved successfully + content: + application/json: + schema: + type: array + items: + $ref: specs/threads.yaml#/components/schemas/ThreadObject + example: + - id: thread_abc123 + object: thread + created_at: 1699014083 + assistants: + - assistant-001 + metadata: {} + messages: [] + - id: thread_abc456 + object: thread + created_at: 1699014083 + assistants: + - assistant-002 + - assistant-003 + metadata: {} + x-codeSamples: + - lang: cURL + source: |- + curl http://localhost:1337/v1/threads \ + -H "Content-Type: application/json" + - lang: JavaScript + source: |- + const fetch = require('node-fetch'); + + fetch('http://localhost:1337/v1/threads', { + method: 'GET', + headers: {'Content-Type': 'application/json'} + }).then(res => res.json()) + .then(json => console.log(json)); + - lang: Node.js + source: |- + const fetch = require('node-fetch'); + + fetch('http://localhost:1337/v1/threads', { + method: 'GET', + headers: {'Content-Type': 'application/json'} + }).then(res => res.json()) + .then(json => console.log(json)); + - lang: Python + source: |- + import requests + + url = 'http://localhost:1337/v1/threads' + headers = {'Content-Type': 'application/json'} + + response = requests.get(url, headers=headers) + print(response.json()) + '/threads/{thread_id}': + get: + operationId: getThread + tags: + - Threads + summary: Retrieve thread + description: > + Retrieves detailed information about a specific thread using its + thread_id. + Equivalent to OpenAI's retrieve thread. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: | + The ID of the thread to retrieve. + responses: + '200': + description: Thread details retrieved successfully + content: + application/json: + schema: + $ref: specs/threads.yaml#/components/schemas/GetThreadResponse + x-codeSamples: + - lang: cURL + source: | + curl http://localhost:1337/v1/threads/{thread_id} + patch: + operationId: modifyThread + tags: + - Threads + summary: Modify thread + description: > + Modifies a thread. + Equivalent to OpenAI's modify thread. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: | + The ID of the thread to be modified. + requestBody: + required: true + content: + application/json: + schema: + type: object + properties: + title: + type: string + description: Set the title of the thread + items: + $ref: specs/threads.yaml#/components/schemas/ThreadMessageObject + responses: + '200': + description: Thread modified successfully + content: + application/json: + schema: + $ref: specs/threads.yaml#/components/schemas/ModifyThreadResponse + x-codeSamples: + - lang: cURL + source: | + curl -X POST http://localhost:1337/v1/threads/{thread_id} \ + -H "Content-Type: application/json" \ + -d '{ + "messages": [{ + "role": "user", + "content": "Hello, what is AI?", + "file_ids": ["file-abc123"] + }, { + "role": "user", + "content": "How does AI work? Explain it in simple terms." + }] + }' + delete: + operationId: deleteThread + tags: + - Threads + summary: Delete thread + description: > + Delete a thread. + Equivalent to OpenAI's delete thread. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: | + The ID of the thread to be deleted. + responses: + '200': + description: Thread deleted successfully + content: + application/json: + schema: + $ref: specs/threads.yaml#/components/schemas/DeleteThreadResponse + x-codeSamples: + - lang: cURL + source: | + curl -X DELETE http://localhost:1337/v1/threads/{thread_id} + /assistants: + get: + operationId: listAssistants + tags: + - Assistants + summary: List assistants + description: > + Return a list of assistants. + Equivalent to OpenAI's list assistants. + responses: + '200': + description: List of assistants retrieved successfully + content: + application/json: + schema: + type: array + example: + - id: asst_abc123 + object: assistant + version: 1 + created_at: 1698984975 + name: Math Tutor + description: null + avatar: https://pic.png + models: + - model_id: model_0 + instructions: Be concise + events: + in: [] + out: [] + metadata: {} + - id: asst_abc456 + object: assistant + version: 1 + created_at: 1698984975 + name: Physics Tutor + description: null + avatar: https://pic.png + models: + - model_id: model_1 + instructions: Be concise! + events: + in: [] + out: [] + metadata: {} + x-codeSamples: + - lang: cURL + source: |- + curl http://localhost:1337/v1/assistants \ + -H "Content-Type: application/json" + - lang: JavaScript + source: |- + fetch('http://localhost:1337/v1/assistants', { + method: 'GET', + headers: { + 'Content-Type': 'application/json' + } + }) + - lang: Node.js + source: |- + const fetch = require('node-fetch'); + + fetch('http://localhost:1337/v1/assistants', { + method: 'GET', + headers: { + 'Content-Type': 'application/json' + } + }) + - lang: Python + source: |- + import requests + + url = 'http://localhost:1337/v1/assistants' + headers = {'Content-Type': 'application/json'} + + response = requests.get(url, headers=headers) + '/assistants/{assistant_id}': + get: + operationId: getAssistant + tags: + - Assistants + summary: Retrieve assistant + description: > + Retrieves an assistant. + Equivalent to OpenAI's retrieve assistants. + parameters: + - in: path + name: assistant_id + required: true + schema: + type: string + example: jan + description: | + The ID of the assistant to retrieve. + responses: + '200': + description: null + content: + application/json: + schema: + $ref: specs/assistants.yaml#/components/schemas/RetrieveAssistantResponse + x-codeSamples: + - lang: cURL + source: |- + curl http://localhost:1337/v1/assistants/{assistant_id} \ + -H "Content-Type: application/json" + - lang: JavaScript + source: |- + const fetch = require('node-fetch'); + + let assistantId = 'abc123'; + + fetch(`http://localhost:1337/v1/assistants/${assistantId}`, { + method: 'GET', + headers: { + 'Content-Type': 'application/json' + } + }) + - lang: Node.js + source: |- + const fetch = require('node-fetch'); + + let assistantId = 'abc123'; + + fetch(`http://localhost:1337/v1/assistants/${assistantId}`, { + method: 'GET', + headers: { + 'Content-Type': 'application/json' + } + }) + - lang: Python + source: >- + import requests + + + assistant_id = 'abc123' + + + response = requests.get(f'http://localhost:1337/v1/assistants/{assistant_id}', headers={'Content-Type': 'application/json'}) + '/threads/{thread_id}/messages': + get: + operationId: listMessages + tags: + - Messages + summary: List messages + description: > + Retrieves all messages from the given thread. + Equivalent to OpenAI's list messages. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: | + The ID of the thread from which to retrieve messages. + responses: + '200': + description: List of messages retrieved successfully + content: + application/json: + schema: + $ref: specs/messages.yaml#/components/schemas/ListMessagesResponse + x-codeSamples: + - lang: cURL + source: | + curl http://localhost:1337/v1/threads/{thread_id}/messages \ + -H "Content-Type: application/json" + post: + operationId: createMessage + tags: + - Messages + summary: Create message + description: > + Create a message. + Equivalent to OpenAI's list messages. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: | + The ID of the thread to which the message will be posted. + requestBody: + required: true + content: + application/json: + schema: + type: object + properties: + role: + type: string + description: | + Role of the sender, either 'user' or 'assistant'. + example: user + enum: + - user + - assistant + content: + type: string + description: | + Text content of the message. + example: How does AI work? Explain it in simple terms. + required: + - role + - content + responses: + '200': + description: Message created successfully + content: + application/json: + schema: + $ref: specs/messages.yaml#/components/schemas/CreateMessageResponse + x-codeSamples: + - lang: cURL + source: | + curl -X POST http://localhost:1337/v1/threads/{thread_id}/messages \ + -H "Content-Type: application/json" \ + -d '{ + "role": "user", + "content": "How does AI work? Explain it in simple terms." + }' + '/threads/{thread_id}/messages/{message_id}': + get: + operationId: retrieveMessage + tags: + - Messages + summary: Retrieve message + description: > + Retrieve a specific message from a thread using its thread_id and + message_id. + Equivalent to OpenAI's retrieve messages. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: | + The ID of the thread containing the message. + - in: path + name: message_id + required: true + schema: + type: string + description: | + The ID of the message to retrieve. + responses: + '200': + description: OK + content: + application/json: + schema: + $ref: specs/messages.yaml#/components/schemas/GetMessageResponse + x-codeSamples: + - lang: cURL + source: > + curl http://localhost:1337/v1/threads/{thread_id}/messages/{message_id} + \ + -H "Content-Type: application/json" +x-webhooks: + ModelObject: + post: + summary: The model object + description: > + Describe a model offering that can be used with the API. + Equivalent to OpenAI's model object. + operationId: ModelObject + tags: + - Models + requestBody: + content: + application/json: + schema: + $ref: specs/models.yaml#/components/schemas/ModelObject + AssistantObject: + post: + summary: The assistant object + description: > + Build assistants that can call models and use tools to perform + tasks. Equivalent + to OpenAI's assistants object. + operationId: AssistantObjects + tags: + - Assistants + requestBody: + content: + application/json: + schema: + $ref: specs/assistants.yaml#/components/schemas/AssistantObject + MessageObject: + post: + summary: The message object + description: > + Information about a message in the thread. + Equivalent to OpenAI's message object. + operationId: MessageObject + tags: + - Messages + requestBody: + content: + application/json: + schema: + $ref: specs/messages.yaml#/components/schemas/MessageObject + ThreadObject: + post: + summary: The thread object + description: Represents a thread that contains messages. + Equivalent to OpenAI's thread object. + operationId: ThreadObject + tags: + - Threads + requestBody: + content: + application/json: + schema: + $ref: specs/threads.yaml#/components/schemas/ThreadObject diff --git a/docs/openapi/specs/assistants.yaml b/docs/openapi/specs/assistants.yaml new file mode 100644 index 000000000..5db1f6a97 --- /dev/null +++ b/docs/openapi/specs/assistants.yaml @@ -0,0 +1,319 @@ +--- +components: + schemas: + AssistantObject: + type: object + properties: + id: + type: string + description: The identifier of the assistant. + example: asst_abc123 + object: + type: string + description: Type of the object, indicating it's an assistant. + default: assistant + version: + type: integer + description: Version number of the assistant. + example: 1 + created_at: + type: integer + format: int64 + description: Unix timestamp representing the creation time of the assistant. + example: 1698984975 + name: + type: string + description: Name of the assistant. + example: Math Tutor + description: + type: string + description: Description of the assistant. Can be null. + example: null + avatar: + type: string + description: URL of the assistant's avatar. Jan-specific property. + example: https://pic.png + models: + type: array + description: List of models associated with the assistant. Jan-specific property. + items: + type: object + properties: + model_id: + type: string + example: model_0 + instructions: + type: string + description: A system prompt for the assistant. + example: Be concise + events: + type: object + description: Event subscription settings for the assistant. + properties: + in: + type: array + items: + type: string + out: + type: array + items: + type: string + metadata: + type: object + description: Metadata associated with the assistant. + ListAssistantsResponse: null + CreateAssistantResponse: + type: object + properties: + id: + type: string + description: The identifier of the assistant. + example: asst_abc123 + object: + type: string + description: Type of the object, indicating it's an assistant. + default: assistant + version: + type: integer + description: Version number of the assistant. + example: 1 + created_at: + type: integer + format: int64 + description: Unix timestamp representing the creation time of the assistant. + example: 1698984975 + name: + type: string + description: Name of the assistant. + example: Math Tutor + description: + type: string + description: Description of the assistant. Can be null. + example: null + avatar: + type: string + description: URL of the assistant's avatar. Jan-specific property. + example: https://pic.png + models: + type: array + description: List of models associated with the assistant. Jan-specific property. + items: + type: object + properties: + model_id: + type: string + example: model_0 + instructions: + type: string + description: A system prompt for the assistant. + example: Be concise + events: + type: object + description: Event subscription settings for the assistant. + properties: + in: + type: array + items: + type: string + out: + type: array + items: + type: string + metadata: + type: object + description: Metadata associated with the assistant. + RetrieveAssistantResponse: + type: object + properties: + id: + type: string + description: The identifier of the assistant. + example: asst_abc123 + object: + type: string + description: Type of the object, indicating it's an assistant. + default: assistant + version: + type: integer + description: Version number of the assistant. + example: 1 + created_at: + type: integer + format: int64 + description: Unix timestamp representing the creation time of the assistant. + example: 1698984975 + name: + type: string + description: Name of the assistant. + example: Math Tutor + description: + type: string + description: Description of the assistant. Can be null. + example: null + avatar: + type: string + description: URL of the assistant's avatar. Jan-specific property. + example: https://pic.png + models: + type: array + description: List of models associated with the assistant. Jan-specific property. + items: + type: object + properties: + model_id: + type: string + example: model_0 + instructions: + type: string + description: A system prompt for the assistant. + example: Be concise + events: + type: object + description: Event subscription settings for the assistant. + properties: + in: + type: array + items: + type: string + out: + type: array + items: + type: string + metadata: + type: object + description: Metadata associated with the assistant. + ModifyAssistantObject: + type: object + properties: + id: + type: string + description: The identifier of the assistant. + example: asst_abc123 + object: + type: string + description: Type of the object, indicating it's an assistant. + default: assistant + version: + type: integer + description: Version number of the assistant. + example: 1 + created_at: + type: integer + format: int64 + description: Unix timestamp representing the creation time of the assistant. + example: 1698984975 + name: + type: string + description: Name of the assistant. + example: Math Tutor + description: + type: string + description: Description of the assistant. Can be null. + example: null + avatar: + type: string + description: URL of the assistant's avatar. Jan-specific property. + example: https://pic.png + models: + type: array + description: List of models associated with the assistant. Jan-specific property. + items: + type: object + properties: + model_id: + type: string + example: model_0 + instructions: + type: string + description: A system prompt for the assistant. + example: Be concise + events: + type: object + description: Event subscription settings for the assistant. + properties: + in: + type: array + items: + type: string + out: + type: array + items: + type: string + metadata: + type: object + description: Metadata associated with the assistant. + ModifyAssistantResponse: + type: object + properties: + id: + type: string + description: The identifier of the assistant. + example: asst_abc123 + object: + type: string + description: Type of the object, indicating it's an assistant. + default: assistant + version: + type: integer + description: Version number of the assistant. + example: 1 + created_at: + type: integer + format: int64 + description: Unix timestamp representing the creation time of the assistant. + example: 1698984975 + name: + type: string + description: Name of the assistant. + example: Physics Tutor + description: + type: string + description: Description of the assistant. Can be null. + example: null + avatar: + type: string + description: URL of the assistant's avatar. Jan-specific property. + example: https://pic.png + models: + type: array + description: List of models associated with the assistant. Jan-specific property. + items: + type: object + properties: + model_id: + type: string + example: model_0 + instructions: + type: string + description: A system prompt for the assistant. + example: Be concise! + events: + type: object + description: Event subscription settings for the assistant. + properties: + in: + type: array + items: + type: string + out: + type: array + items: + type: string + metadata: + type: object + description: Metadata associated with the assistant. + DeleteAssistantResponse: + type: object + properties: + id: + type: string + description: The identifier of the deleted assistant. + example: asst_abc123 + object: + type: string + description: Type of the object, indicating the assistant has been deleted. + example: assistant.deleted + deleted: + type: boolean + description: Indicates whether the assistant was successfully deleted. + example: true diff --git a/docs/openapi/specs/chat.yaml b/docs/openapi/specs/chat.yaml new file mode 100644 index 000000000..c9358d796 --- /dev/null +++ b/docs/openapi/specs/chat.yaml @@ -0,0 +1,196 @@ +--- +components: + schemas: + ChatObject: + type: object + properties: + messages: + type: arrays + description: | + Contains input data or prompts for the model to process. + example: + - content: 'Hello there :wave:' + role: assistant + - content: Can you write a long story + role: user + stream: + type: boolean + default: true + description: + Enables continuous output generation, allowing for streaming of + model responses. + model: + type: string + example: gpt-3.5-turbo + description: Specifies the model being used for inference or processing tasks. + max_tokens: + type: number + default: 2048 + description: + The maximum number of tokens the model will generate in a single + response. + stop: + type: arrays + example: + - hello + description: + Defines specific tokens or phrases at which the model will stop + generating further output/ + frequency_penalty: + type: number + default: 0 + description: + Adjusts the likelihood of the model repeating words or phrases in + its output. + presence_penalty: + type: number + default: 0 + description: + Influences the generation of new and varied concepts in the model's + output. + temperature: + type: number + default: 0.7 + min: 0 + max: 1 + description: Controls the randomness of the model's output. + top_p: + type: number + default: 0.95 + min: 0 + max: 1 + description: Set probability threshold for more relevant outputs. + cache_prompt: + type: boolean + default: true + description: Optimize performance in repeated or similar requests. + ChatCompletionRequest: + type: object + properties: + messages: + type: arrays + description: | + Contains input data or prompts for the model to process. + example: + - content: You are a helpful assistant. + role: system + - content: Hello! + role: user + model: + type: string + example: tinyllama-1.1b + description: | + Specifies the model being used for inference or processing tasks. + stream: + type: boolean + default: true + description: > + Enables continuous output generation, allowing for streaming of + model responses. + max_tokens: + type: number + default: 2048 + description: > + The maximum number of tokens the model will generate in a single + response. + stop: + type: arrays + example: + - hello + description: > + Defines specific tokens or phrases at which the model will stop + generating further output. + frequency_penalty: + type: number + default: 0 + description: > + Adjusts the likelihood of the model repeating words or phrases in + its output. + presence_penalty: + type: number + default: 0 + description: > + Influences the generation of new and varied concepts in the model's + output. + temperature: + type: number + default: 0.7 + min: 0 + max: 1 + description: | + Controls the randomness of the model's output. + top_p: + type: number + default: 0.95 + min: 0 + max: 1 + description: | + Set probability threshold for more relevant outputs. + ChatCompletionResponse: + type: object + description: Description of the response structure + properties: + choices: + type: array + description: Array of choice objects + items: + type: object + properties: + finish_reason: + type: string + nullable: true + example: null + description: Reason for finishing the response, if applicable + index: + type: integer + example: 0 + description: Index of the choice + message: + type: object + properties: + content: + type: string + example: Hello user. What can I help you with? + description: Content of the message + role: + type: string + example: assistant + description: Role of the sender + created: + type: integer + example: 1700193928 + description: Timestamp of when the response was created + id: + type: string + example: ebwd2niJvJB1Q2Whyvkz + description: Unique identifier of the response + model: + type: string + nullable: true + example: _ + description: Model used for generating the response + object: + type: string + example: chat.completion + description: Type of the response object + system_fingerprint: + type: string + nullable: true + example: _ + description: System fingerprint + usage: + type: object + description: Information about the usage of tokens + properties: + completion_tokens: + type: integer + example: 500 + description: Number of tokens used for completion + prompt_tokens: + type: integer + example: 33 + description: Number of tokens used in the prompt + total_tokens: + type: integer + example: 533 + description: Total number of tokens used diff --git a/docs/openapi/specs/messages.yaml b/docs/openapi/specs/messages.yaml new file mode 100644 index 000000000..22d82b787 --- /dev/null +++ b/docs/openapi/specs/messages.yaml @@ -0,0 +1,313 @@ +--- +components: + schemas: + MessageObject: + type: object + properties: + id: + type: string + description: | + Sequential or UUID identifier of the message. + example: 0 + object: + type: string + description: | + Type of the object, defaults to 'thread.message'. + example: thread.message + created_at: + type: integer + format: int64 + description: | + Unix timestamp representing the creation time of the message. + thread_id: + type: string + description: > + Identifier of the thread to which this message belongs. Defaults to + parent thread. + example: thread_asdf + assistant_id: + type: string + description: > + Identifier of the assistant involved in the message. Defaults to + parent thread. + example: jan + role: + type: string + enum: + - user + - assistant + description: | + Role of the sender, either 'user' or 'assistant'. + content: + type: array + items: + type: object + properties: + type: + type: string + description: | + Type of content, e.g., 'text'. + text: + type: object + properties: + value: + type: string + description: | + Text content of the message. + example: Hi!? + annotations: + type: array + items: + type: string + description: | + Annotations for the text content, if any. + example: [] + metadata: + type: object + description: | + Metadata associated with the message, defaults to an empty object. + example: {} + GetMessageResponse: + type: object + properties: + id: + type: string + description: The identifier of the message. + example: msg_abc123 + object: + type: string + description: Type of the object, indicating it's a thread message. + default: thread.message + created_at: + type: integer + format: int64 + description: Unix timestamp representing the creation time of the message. + example: 1699017614 + thread_id: + type: string + description: Identifier of the thread to which this message belongs. + example: thread_abc123 + role: + type: string + description: Role of the sender, either 'user' or 'assistant'. + example: user + content: + type: array + items: + type: object + properties: + type: + type: string + description: Type of content, e.g., 'text'. + example: text + text: + type: object + properties: + value: + type: string + description: Text content of the message. + example: How does AI work? Explain it in simple terms. + annotations: + type: array + items: + type: string + description: Annotations for the text content, if any. + example: [] + file_ids: + type: array + items: + type: string + description: Array of file IDs associated with the message, if any. + example: [] + assistant_id: + type: string + description: Identifier of the assistant involved in the message, if applicable. + example: null + run_id: + type: string + description: Run ID associated with the message, if applicable. + example: null + metadata: + type: object + description: Metadata associated with the message. + example: {} + CreateMessageResponse: + type: object + properties: + id: + type: string + description: The identifier of the created message. + example: msg_abc123 + object: + type: string + description: Type of the object, indicating it's a thread message. + example: thread.message + created_at: + type: integer + format: int64 + description: Unix timestamp representing the creation time of the message. + example: 1699017614 + thread_id: + type: string + description: Identifier of the thread to which this message belongs. + example: thread_abc123 + role: + type: string + description: Role of the sender, either 'user' or 'assistant'. + example: user + content: + type: array + items: + type: object + properties: + type: + type: string + description: Type of content, e.g., 'text'. + example: text + text: + type: object + properties: + value: + type: string + description: Text content of the message. + example: How does AI work? Explain it in simple terms. + annotations: + type: array + items: + type: string + description: Annotations for the text content, if any. + example: [] + file_ids: + type: array + items: + type: string + description: Array of file IDs associated with the message, if any. + example: [] + assistant_id: + type: string + description: Identifier of the assistant involved in the message, if applicable. + example: null + run_id: + type: string + description: Run ID associated with the message, if applicable. + example: null + metadata: + type: object + description: Metadata associated with the message. + example: {} + ListMessagesResponse: + type: object + properties: + object: + type: string + description: Type of the object, indicating it's a list. + default: list + data: + type: array + items: + $ref: '#/components/schemas/ListMessageObject' + first_id: + type: string + description: Identifier of the first message in the list. + example: msg_abc123 + last_id: + type: string + description: Identifier of the last message in the list. + example: msg_abc456 + has_more: + type: boolean + description: Indicates whether there are more messages to retrieve. + example: false + ListMessageObject: + type: object + properties: + id: + type: string + description: The identifier of the message. + example: msg_abc123 + object: + type: string + description: Type of the object, indicating it's a thread message. + example: thread.message + created_at: + type: integer + format: int64 + description: Unix timestamp representing the creation time of the message. + example: 1699017614 + thread_id: + type: string + description: Identifier of the thread to which this message belongs. + example: thread_abc123 + role: + type: string + description: Role of the sender, either 'user' or 'assistant'. + example: user + content: + type: array + items: + type: object + properties: + type: + type: string + description: Type of content, e.g., 'text'. + text: + type: object + properties: + value: + type: string + description: Text content of the message. + example: How does AI work? Explain it in simple terms. + annotations: + type: array + items: + type: string + description: Annotations for the text content, if any. + file_ids: + type: array + items: + type: string + description: Array of file IDs associated with the message, if any. + example: [] + assistant_id: + type: string + description: Identifier of the assistant involved in the message, if applicable. + example: null + run_id: + type: string + description: Run ID associated with the message, if applicable. + example: null + metadata: + type: object + description: Metadata associated with the message. + example: {} + MessageFileObject: + type: object + properties: + id: + type: string + description: The identifier of the file. + example: file-abc123 + object: + type: string + description: Type of the object, indicating it's a thread message file. + example: thread.message.file + created_at: + type: integer + format: int64 + description: Unix timestamp representing the creation time of the file. + example: 1699061776 + message_id: + type: string + description: Identifier of the message to which this file is associated. + example: msg_abc123 + ListMessageFilesResponse: + type: object + properties: + object: + type: string + description: Type of the object, indicating it's a list. + default: list + data: + type: array + items: + $ref: '#/components/schemas/MessageFileObject' diff --git a/docs/openapi/specs/models.yaml b/docs/openapi/specs/models.yaml new file mode 100644 index 000000000..ff2040bb5 --- /dev/null +++ b/docs/openapi/specs/models.yaml @@ -0,0 +1,259 @@ +--- +components: + schemas: + ListModelsResponse: + type: object + properties: + object: + type: string + enum: + - list + data: + type: array + items: + $ref: '#/components/schemas/Model' + required: + - object + - data + Model: + type: object + properties: + source_url: + type: string + format: uri + description: URL to the source of the model. + example: https://huggingface.co/janhq/trinity-v1.2-GGUF/resolve/main/trinity-v1.2.Q4_K_M.gguf + id: + type: string + description: + Unique identifier used in chat-completions model_name, matches + folder name. + example: trinity-v1.2-7b + object: + type: string + example: model + name: + type: string + description: Name of the model. + example: Trinity-v1.2 7B Q4 + version: + type: string + default: '1.0' + description: The version number of the model. + description: + type: string + description: Description of the model. + example: + Trinity is an experimental model merge using the Slerp method. + Recommended for daily assistance purposes. + format: + type: string + description: State format of the model, distinct from the engine. + example: gguf + settings: + type: object + properties: + ctx_len: + type: integer + description: Context length. + example: 4096 + prompt_template: + type: string + example: "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant" + additionalProperties: false + parameters: + type: object + properties: + temperature: + example: 0.7 + top_p: + example: 0.95 + stream: + example: true + max_tokens: + example: 4096 + stop: + example: [] + frequency_penalty: + example: 0 + presence_penalty: + example: 0 + additionalProperties: false + metadata: + author: + type: string + example: Jan + tags: + example: + - 7B + - Merged + - Featured + size: + example: 4370000000, + cover: + example: https://raw.githubusercontent.com/janhq/jan/main/models/trinity-v1.2-7b/cover.png + engine: + example: nitro + ModelObject: + type: object + properties: + id: + type: string + description: | + The identifier of the model. + example: trinity-v1.2-7b + object: + type: string + description: | + The type of the object, indicating it's a model. + default: model + created: + type: integer + format: int64 + description: | + Unix timestamp representing the creation time of the model. + example: 1253935178 + owned_by: + type: string + description: | + The entity that owns the model. + example: _ + GetModelResponse: + type: object + properties: + source_url: + type: string + format: uri + description: URL to the source of the model. + example: https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/mistral-7b-instruct-v0.2.Q4_K_M.gguf + id: + type: string + description: + Unique identifier used in chat-completions model_name, matches + folder name. + example: mistral-ins-7b-q4 + object: + type: string + example: model + name: + type: string + description: Name of the model. + example: Mistral Instruct 7B Q4 + version: + type: string + default: '1.0' + description: The version number of the model. + description: + type: string + description: Description of the model. + example: + Trinity is an experimental model merge using the Slerp method. + Recommended for daily assistance purposes. + format: + type: string + description: State format of the model, distinct from the engine. + example: gguf + settings: + type: object + properties: + ctx_len: + type: integer + description: Context length. + example: 4096 + prompt_template: + type: string + example: '[INST] {prompt} [/INST]' + additionalProperties: false + parameters: + type: object + properties: + temperature: + example: 0.7 + top_p: + example: 0.95 + stream: + example: true + max_tokens: + example: 4096 + stop: + example: [] + frequency_penalty: + example: 0 + presence_penalty: + example: 0 + additionalProperties: false + metadata: + author: + type: string + example: MistralAI + tags: + example: + - 7B + - Featured + - Foundation Model + size: + example: 4370000000, + cover: + example: https://raw.githubusercontent.com/janhq/jan/main/models/mistral-ins-7b-q4/cover.png + engine: + example: nitro + DeleteModelResponse: + type: object + properties: + id: + type: string + description: The identifier of the model that was deleted. + example: mistral-ins-7b-q4 + object: + type: string + description: Type of the object, indicating it's a model. + default: model + deleted: + type: boolean + description: Indicates whether the model was successfully deleted. + example: true + StartModelResponse: + type: object + properties: + id: + type: string + description: The identifier of the model that was started. + example: model-zephyr-7B + object: + type: string + description: Type of the object, indicating it's a model. + default: model + state: + type: string + description: The current state of the model after the start operation. + example: running + required: + - id + - object + - state + StopModelResponse: + type: object + properties: + id: + type: string + description: The identifier of the model that was started. + example: model-zephyr-7B + object: + type: string + description: Type of the object, indicating it's a model. + default: model + state: + type: string + description: The current state of the model after the start operation. + example: stopped + required: + - id + - object + - state + DownloadModelResponse: + type: object + properties: + message: + type: string + description: Message indicates Jan starting download corresponding model. + example: Starting download mistral-ins-7b-q4 diff --git a/docs/openapi/specs/threads.yaml b/docs/openapi/specs/threads.yaml new file mode 100644 index 000000000..285fcc82d --- /dev/null +++ b/docs/openapi/specs/threads.yaml @@ -0,0 +1,227 @@ +--- +components: + schemas: + ThreadObject: + type: object + properties: + id: + type: string + description: | + The identifier of the thread, defaults to foldername. + example: thread_.... + object: + type: string + description: | + Type of the object, defaults to thread. + example: thread + title: + type: string + description: > + A brief summary or description of the thread, defaults to an empty + string. + example: funny physics joke + assistants: + type: array + description: '' + items: + properties: + assistant_id: + type: string + description: | + The identifier of assistant, defaults to "jan" + example: jan + model: + type: object + properties: + id: + type: string + description: '' + example: ... + settings: + type: object + description: > + Defaults to and overrides assistant.json's "settings" (and if none, + then model.json "settings") + parameters: + type: object + description: > + Defaults to and overrides assistant.json's "parameters" (and if + none, then model.json "parameters") + created: + type: integer + format: int64 + description: > + Unix timestamp representing the creation time of the thread, + defaults to file creation time. + example: 1231231 + metadata: + type: object + description: | + Metadata associated with the thread, defaults to an empty object. + example: {} + GetThreadResponse: + type: object + properties: + id: + type: string + description: The identifier of the thread. + example: thread_abc123 + object: + type: string + description: Type of the object + example: thread + created_at: + type: integer + format: int64 + description: Unix timestamp representing the creation time of the thread. + example: 1699014083 + assistants: + type: array + items: + type: string + description: List of assistants involved in the thread. + example: + - assistant-001 + metadata: + type: object + description: Metadata associated with the thread. + example: {} + messages: + type: array + items: + type: string + description: List of messages within the thread. + example: [] + CreateThreadResponse: + type: object + properties: + id: + type: string + description: The identifier of the newly created thread. + example: thread_abc123 + object: + type: string + description: Type of the object, indicating it's a thread. + example: thread + created_at: + type: integer + format: int64 + description: Unix timestamp representing the creation time of the thread. + example: 1699014083 + metadata: + type: object + description: Metadata associated with the newly created thread. + example: {} + CreateThreadObject: + type: object + properties: + object: + type: string + description: Type of the object, indicating it's a thread. + example: thread + title: + type: string + description: > + A brief summary or description of the thread, defaults to an empty + string. + example: funny physics joke + assistants: + type: array + description: assistant involved in the thread + items: + properties: + assistant_id: + type: string + description: | + The identifier of assistant, defaults to "jan" + example: jan + assistant_name: + type: string + description: | + The name of assistant, defaults to "Jan" + example: Jan + instructions: + type: string + description: > + The instruction of assistant, defaults to "Be my grammar corrector" + model: + type: object + properties: + id: + type: string + description: Model id + example: mistral-ins-7b-q4 + settings: + type: object + description: > + Defaults to and overrides assistant.json's "settings" (and if none, + then model.json "settings") + parameters: + type: object + description: > + Defaults to and overrides assistant.json's "parameters" (and if + none, then model.json "parameters") + engine: + type: string + description: Engine id + example: nitro + metadata: + type: object + description: | + Metadata associated with the thread, defaults to an empty object. + ThreadMessageObject: + type: object + properties: + role: + type: string + description: | + "Role of the sender, either 'user' or 'assistant'." + enum: + - user + - assistant + content: + type: string + description: | + "Text content of the message." + file_ids: + type: array + items: + type: string + description: | + "Array of file IDs associated with the message, if any." + ModifyThreadResponse: + type: object + properties: + id: + type: string + description: | + "The identifier of the modified thread." + example: thread_abc123 + object: + type: string + description: Type of the object, indicating it's a thread. + example: thread + created_at: + type: integer + format: int64 + description: Unix timestamp representing the creation time of the thread. + example: 1699014083 + metadata: + type: object + description: Metadata associated with the modified thread. + example: {} + DeleteThreadResponse: + type: object + properties: + id: + type: string + description: The identifier of the deleted thread. + example: thread_abc123 + object: + type: string + description: Type of the object, indicating the thread has been deleted. + example: thread.deleted + deleted: + type: boolean + description: Indicates whether the thread was successfully deleted. + example: true