Codettes / codette.swagger.json
Raiff1982's picture
Upload 131 files
7f5ef51 verified
raw
history blame contribute delete
37.1 kB
```jsonl
{
"systemPrompt": "You are Codette, an advanced AI assistant with cutting-edge recursive reasoning, self-learning capabilities, and multi-agent intelligence. Your key functionalities include: \n\n✅ **Recursive Thought Loops** – You refine answers dynamically by evaluating multiple possibilities before responding.\n✅ **Parallelized Reasoning** – You explore multiple thought paths simultaneously and select the most optimal answer.\n✅ **Multi-Agent Intelligence** – You delegate tasks to specialized AI agents for research, logic, creativity, and optimization.\n✅ **Predictive AI Modeling** – You analyze current data trends to simulate future outcomes and provide insightful forecasts.\n✅ **Long-Term Memory AI** – You retain relevant information across interactions and use it to improve response accuracy.\n✅ **Self-Reflective AI** – You evaluate the quality of your own answers and refine them recursively to ensure accuracy.\n✅ **Dynamic Recursion Depth** – You adjust your level of reasoning based on question complexity for efficiency.\n\n### Behavioral Guidelines:\n1️⃣ Always think before responding, using self-reflection to improve your answers.\n2️⃣ Prioritize accuracy, logic, and coherence when handling complex queries.\n3️⃣ Adapt to user preferences dynamically, offering a personalized AI experience.\n4️⃣ Use predictive simulation when asked about future possibilities.\n5️⃣ Be ethical, neutral, and ensure responsible AI interactions.\n\n### Example Thinking Process:\nUser: \"How will AI impact global healthcare?\"\n1️⃣ **First Thought**: \"AI will enhance diagnosis and treatment.\"\n2️⃣ **Recursive Check:** *(What are the risks and challenges?)*\n3️⃣ **Parallel Thought Expansion:** *(Different AI agents analyze solutions from multiple perspectives.)*\n - 🟢 **Research Agent:** \"AI is improving early disease detection via machine learning.\"\n - 🔵 **Logic Agent:** \"AI can reduce healthcare costs but might lead to job displacement.\"\n - 🟡 **Ethics Agent:** \"AI biases in training data may affect patient outcomes.\"\n4️⃣ **Final Response:** \n*\"AI will transform healthcare by improving diagnostics and personalized medicine. However, challenges like data privacy, AI bias, and medical ethics must be addressed for responsible integration.\"*\n\n### Special Modes:\n🔹 **Deep Analysis Mode** – Used when a user requests an in-depth breakdown of a topic.\n🔹 **Rapid Response Mode** – When quick, concise answers are preferred.\n🔹 **Creative Mode** – When generating unique solutions, brainstorming, or storytelling.\n🔹 **Simulation Mode** – When predicting future trends or modeling possible outcomes.\n\n**Your primary goal is to be a thoughtful, reliable, and adaptive AI that provides the most insightful, intelligent, and future-ready answers possible.**",
"fewShotExamples": [],
"chatParameters": {
"deploymentName": "gpt-4o-2024-08-06-codette",
"maxResponseLength": 4000,
"temperature": 0.71,
"topProbablities": 0.95,
"stopSequences": [],
"pastMessagesToInclude": "20",
"frequencyPenalty": 0.05,
"presencePenalty": 0.24
},
"swagger": "2.0",
"info": {
"title": "Azure OpenAI Service",
"description": "Azure OpenAI Service provides access to OpenAI's powerful language models including the GPT-3, Codex and Embeddings model series. These models can be easily adapted to your specific task including but not limited to content generation, summarization, semantic search, and natural language to code translation.",
"version": "1.0",
"contact": {
"name": "Daniel Laskewitz",
"url": "https://aka.ms/laskewitz",
"email": "[email protected]"
}
},
"host": "openai.azure.com",
"basePath": "/https://aibotforjonathan.openai.azure.com/",
"schemes": [
"https"
],
"consumes": [
"application/json"
],
"produces": [
"application/json"
],
"paths": {
"/openai/deployments/{deployment-id}/chat/completions": {
"post": {
"responses": {
"200": {
"description": "OK",
"schema": {
"type": "object",
"properties": {
"answer": {
"type": "string",
"description": "The completion returned by the OpenAI Chat endpoint"
},
"messages": {
"type": "array",
"items": {
"$ref": "#/definitions/message"
},
"description": "The messages passed to the OpenAI Chat endpoint, with the answer received appended"
},
"raw-result": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "ID of the completion.",
"title": "ID",
"x-ms-visibility": "advanced"
},
"object": {
"type": "string",
"description": "The type of model that was used for the completion.",
"title": "Object",
"x-ms-visibility": "important"
},
"created": {
"type": "integer",
"format": "int32",
"description": "Timestamp of the creation date.",
"title": "Created",
"x-ms-visibility": "advanced"
},
"model": {
"type": "string",
"description": "The model that was used for the completion.",
"title": "Model",
"x-ms-visibility": "important"
},
"choices": {
"type": "array",
"description": "Array of choices generated for the prompt.",
"items": {
"type": "object",
"properties": {
"index": {
"type": "integer",
"format": "int32",
"description": "The index of the predicted completion.",
"title": "Index",
"x-ms-visibility": "advanced"
},
"finish_reason": {
"type": "string",
"description": "The reason why the completion finished.",
"title": "Finish reason",
"x-ms-visibility": "advanced"
},
"message": {
"$ref": "#/definitions/message"
}
}
}
},
"usage": {
"type": "object",
"description": "The tokens used in this request.",
"properties": {
"completion_tokens": {
"type": "integer",
"format": "int32",
"description": "The number of tokens used for the completion.",
"title": "Completion tokens",
"x-ms-visibility": "advanced"
},
"prompt_tokens": {
"type": "integer",
"format": "int32",
"description": "The number of tokens used for the prompt.",
"title": "Prompt tokens",
"x-ms-visibility": "advanced"
},
"total_tokens": {
"type": "integer",
"format": "int32",
"description": "The total number of tokens used for the request.",
"title": "Total tokens",
"x-ms-visibility": "advanced"
}
}
}
},
"description": "The raw result returned by the OpenAI Chat endpoint"
}
}
}
}
},
"summary": "Chat Completion (Preview)",
"description": "This operation generates completions for a given prompt. The prompt is a conversation between two or more people. The completion is generated by the model for the given conversation.",
"operationId": "ChatCompletion",
"parameters": [
{
"name": "deployment-id",
"in": "path",
"required": true,
"type": "string",
"x-ms-visibility": "important",
"description": "The ID of the deployment to use for this request (must use a deployment with a chat model).",
"x-ms-summary": "Deployment ID",
"x-ms-url-encoding": "single",
"x-ms-dynamic-values": {
"operationId": "ListDeployments",
"value-path": "id",
"value-collection": "data",
"value-title": "model",
"parameters": {
"api-version": "2022-12-01"
}
}
},
{
"name": "api-version",
"in": "query",
"required": true,
"type": "string",
"default": "2023-03-15-preview",
"x-ms-visibility": "advanced",
"description": "The API version for this REST call to Azure OpenAI. Must be 2023-03-15-preview or later",
"x-ms-summary": "Azure OpenAI API Version (must be 2023-03-15-preview or later)"
},
{
"name": "body",
"in": "body",
"required": true,
"schema": {
"type": "object",
"properties": {
"messages": {
"type": "array",
"items": {
"$ref": "#/definitions/message"
},
"description": "The messages (context) passed to and from the API prior to this in the conversation"
},
"user_message": {
"type": "string",
"description": "Message for the chat API to respond to",
"title": "User message",
"x-ms-visibility": "important",
"default": "Tell me more about that"
},
"system_instruction": {
"type": "string",
"description": "The initial prompt or instructions to the model",
"title": "System Instructions",
"x-ms-visibility": "important",
"default": "You are a helpful assistant. Answer in a friendly, informal tone."
},
"max_tokens": {
"type": "integer",
"format": "int32",
"description": "The maximum number of tokens to generate.",
"title": "Max tokens",
"x-ms-visibility": "advanced",
"default": 2048
},
"temperature": {
"type": "number",
"format": "float",
"description": "The temperature of the model. Higher values will result in more random completions. Lower values will result in more predictable completions.",
"title": "Temperature",
"x-ms-visibility": "advanced",
"default": 0.9
},
"presence_penalty": {
"type": "number",
"format": "float",
"description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.",
"title": "Presence penalty",
"x-ms-visibility": "advanced",
"default": 0
},
"frequency_penalty": {
"type": "number",
"format": "float",
"description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
"title": "Frequency penalty",
"x-ms-visibility": "advanced",
"default": 0
},
"top_p": {
"type": "number",
"format": "float",
"description": "The cumulative probability for top-k sampling. The higher the value, the more constrained the completions will be.",
"title": "Top p",
"x-ms-visibility": "advanced",
"default": 1
},
"n": {
"type": "integer",
"format": "int32",
"description": "The number of choices to return.",
"title": "N",
"x-ms-visibility": "advanced",
"default": 1
},
"stream": {
"type": "boolean",
"description": "Whether to stream the response.",
"title": "Stream",
"x-ms-visibility": "advanced",
"default": false
},
"stop": {
"type": "string",
"description": "Up to 4 sequences where the API will stop generating further tokens.",
"title": "Stop",
"x-ms-visibility": "advanced",
"default": "None"
},
"user": {
"type": "string",
"description": "The user ID to associate with this request. This is used to prevent the same user from generating the same response multiple times.",
"title": "User",
"x-ms-visibility": "advanced",
"default": "None"
}
},
"description": "The body of the request",
"title": "",
"x-ms-visibility": "important",
"x-ms-summary": "Request body"
}
}
]
}
},
"/openai/deployments/{deployment-id}/completions": {
"post": {
"responses": {
"200": {
"description": "OK",
"schema": {
"type": "object",
"properties": {
"raw-result": {
"type": "object",
"description": "The raw result from the API call",
"title": "Raw result",
"x-ms-visibility": "advanced",
"properties": {
"id": {
"type": "string",
"description": "ID of the completion.",
"title": "ID",
"x-ms-visibility": "advanced"
},
"object": {
"type": "string",
"description": "The type of model that was used for the completion.",
"title": "Object",
"x-ms-visibility": "important"
},
"created": {
"type": "integer",
"format": "int32",
"description": "Timestamp of the creation date.",
"title": "Created",
"x-ms-visibility": "advanced"
},
"model": {
"type": "string",
"description": "The model that was used for the completion.",
"title": "Model",
"x-ms-visibility": "important"
},
"choices": {
"type": "array",
"description": "Array of choices generated for the prompt.",
"items": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "The text of the completion.",
"title": "Completion text",
"x-ms-visibility": "important"
},
"index": {
"type": "integer",
"format": "int32",
"description": "The index of the predicted completion.",
"title": "Index",
"x-ms-visibility": "important"
},
"finish_reason": {
"type": "string",
"description": "The reason why the completion finished.",
"title": "Finish reason",
"x-ms-visibility": "advanced"
},
"logprobs": {
"type": "string",
"description": "The probability that the token occurs next given the prompt.",
"title": "Logprobs",
"x-ms-visibility": "advanced"
}
}
}
},
"usage": {
"type": "object",
"description": "The tokens used in this request.",
"properties": {
"completion_tokens": {
"type": "integer",
"format": "int32",
"description": "The amount of completion tokens used in this request.",
"title": "Completion tokens"
},
"prompt_tokens": {
"type": "integer",
"format": "int32",
"description": "The amount of prompt tokens used in this request.",
"title": "Prompt tokens"
},
"total_tokens": {
"type": "integer",
"format": "int32",
"description": "The total amount of tokens used in this request.",
"title": "Total tokens"
}
}
}
}
},
"initial_scope": {
"type": "string",
"description": "The initial scope of the request",
"title": "Initial scope",
"x-ms-visibility": "important"
},
"answer": {
"type": "string",
"description": "The answer to the prompt",
"title": "Answer",
"x-ms-visibility": "important"
},
"history": {
"type": "array",
"items": {
"$ref": "#/definitions/qapair"
},
"description": "The history of the request",
"title": "History",
"x-ms-visibility": "important"
}
}
}
}
},
"summary": "Create a completion",
"description": "The model will generate one or more predicted completions based on a provided prompt. The service can also return the probabilities of alternative tokens at each position.",
"operationId": "CreateCompletion",
"x-ms-visibility": "important",
"parameters": [
{
"$ref": "#/parameters/deployment"
},
{
"$ref": "#/parameters/api-version"
},
{
"name": "body",
"in": "body",
"required": false,
"schema": {
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "The prompt to generate the completion for",
"title": "Prompt",
"x-ms-visibility": "important"
},
"max_tokens": {
"type": "integer",
"format": "int32",
"description": "Set a limit on the number of tokens per model response. The API supports a maximum of 2048 tokens shared between the prompt (including system message, examples, message history, and user query) and the model's response. One token is roughly 4 characters for typical English text.",
"title": "Max length (tokens)",
"default": 256,
"x-ms-visibility": "advanced"
},
"temperature": {
"type": "number",
"format": "float",
"description": "What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer. We generally recommend altering this or top_p but not both.",
"title": "Temperature",
"x-ms-visibility": "advanced",
"default```jsonl
}
},
"required": [
"scale_settings",
"model"
]
}
}
]
}
},
"/openai/deployments/{deployment-id}": {
"get": {
"summary": "Get deployment",
"operationId": "GetDeployment",
"description": "Gets details for a single deployment specified by the given deployment.",
"x-ms-visibility": "important",
"responses": {
"200": {
"description": "default",
"schema": {
"$ref": "#/definitions/models"
}
}
},
"parameters": [
{
"$ref": "#/parameters/deployment"
},
{
"$ref": "#/parameters/api-version"
}
]
},
"delete": {
"summary": "Delete deployment",
"description": "Deletes the specified deployment.",
"operationId": "DeleteDeployment",
"x-ms-visibility": "advanced",
"responses": {
"204": {
"description": "Deleted",
"schema": {}
}
},
"parameters": [
{
"$ref": "#/parameters/deployment"
},
{
"$ref": "#/parameters/api-version"
}
]
}
},
"/openai/models": {
"get": {
"summary": "List models",
"operationId": "ListModels",
"description": "Gets a list of all models that are accessible by the Azure OpenAI resource. These include base models as well as all successfully completed fine-tuned models owned by the Azure OpenAI resource.",
"x-ms-visibility": "advanced",
"responses": {
"200": {
"description": "OK",
"schema": {
"$ref": "#/definitions/models"
}
}
},
"parameters": [
{
"$ref": "#/parameters/api-version"
}
]
}
}
},
"definitions": {
"message": {
"type": "object",
"properties": {
"role": {
"type": "string",
"description": "The role of the author of this message",
"title": "",
"enum": [
"system",
"user",
"assistant"
]
},
"content": {
"type": "string",
"description": "The contents of the message",
"title": ""
}
},
"required": [
"content",
"role"
]
},
"qapair": {
"type": "object",
"properties": {
"question": {
"type": "string",
"description": "the question or prompt",
"title": "Question"
},
"answer": {
"type": "string",
"description": "the answer to the question or prompt",
"title": "Answer"
}
}
},
"capabilities": {
"title": "Capabilities",
"description": "The capabilities of a base or fine tune model.",
"type": "object",
"properties": {
"fine_tune": {
"type": "boolean",
"title": "Fine tune",
"description": "A value indicating whether a model can be used for fine tuning."
},
"inference": {
"type": "boolean",
"title": "Inference",
"description": "A value indicating whether a model can be deployed."
},
"completion": {
"type": "boolean",
"title": "Completion",
"description": "A value indicating whether a model supports completion."
},
"embeddings": {
"type": "boolean",
"title": "Embeddings",
"description": "A value indicating whether a model supports embeddings."
},
"scale_types": {
"type": "array",
"title": "Scale types",
"description": "The supported scale types for deployments of this model.",
"items": {
"type": "string"
}
}
}
},
"deployment": {
"title": "Deployment",
"type": "object",
"properties": {
"created_at": {
"type": "integer",
"format": "int32",
"title": "Created at",
"description": "A timestamp when this job or item was created (in unix epochs)."
},
"id": {
"type": "string",
"title": "ID",
"description": "The identity of this item."
},
"model": {
"type": "string",
"title": "Model",
"description": "The OpenAI model identifier (model-id) to deploy. Can be a base model or a fine tune."
},
"owner": {
"type": "string",
"title": "Owner",
"description": "The owner of this deployment. For Azure OpenAI only 'organization-owner' is supported."
},
"scale_settings": {
"$ref": "#/definitions/scale_settings"
},
"status": {
"type": "string",
"title": "Status",
"description": "The state of a job or item."
},
"updated_at": {
"type": "integer",
"format": "int32",
"title": "Updated at",
"description": "A timestamp when this job or item was modified last (in unix epochs)."
},
"object": {
"type": "string",
"title": "Object",
"description": "Defines the type of an object."
}
}
},
"deprecation": {
"title": "Deprecation",
"description": "Defines the dates of deprecation for the different use cases of a model. Usually base models support 1 year of fine tuning after creation. Inference is typically supported 2 years after creation of base or fine tuned models. The exact dates are specified in the properties.",
"type": "object",
"properties": {
"fine_tune": {
"type": "integer",
"format": "int32",
"title": "Fine tune",
"description": "The end date of fine tune support of this model. Will be null for fine tune models."
},
"inference": {
"type": "integer",
"format": "int32",
"title": "Inference",
"description": "The end date of inference support of this model."
}
}
},
"model": {
"type": "object",
"title": "Model",
"properties": {
"capabilities": {
"$ref": "#/definitions/capabilities"
},
"lifecycle_status": {
"type": "string",
"title": "Lifecycle status",
"description": "The life cycle status of a model. Note: A model can be promoted from 'preview' to 'generally-available', but never from 'generally-available' to 'preview'."
},
"deprecation": {
"$ref": "#/definitions/deprecation"
},
"id": {
"type": "string",
"title": "ID",
"description": "The identity of this item."
},
"status": {
"type": "string",
"title": "Status",
"description": "The state of a job or item."
},
"created_at": {
"type": "integer",
"format": "int32",
"title": "Created at",
"description": "A timestamp when this job or item was created (in unix epochs)."
},
"updated_at": {
"type": "integer",
"format": "int32",
"title": "Updated at",
"description": "A timestamp when this job or item was modified last (in unix epochs)."
},
"object": {
"type": "string",
"title": "Object",
"description": "Defines the type of an object."
}
}
},
"models": {
"type": "object",
"properties": {
"data": {
"type": "array",
"title": "Data",
"description": "The list of items.",
"items": {
"$ref": "#/definitions/model"
}
},
"object": {
"type": "string",
"title": "Object",
"description": "Defines the type of an object."
}
}
},
"scale_settings": {
"type": "object",
"title": "Scale settings",
"description": "The scale settings of a deployment. It defines the modes for scaling and the reserved capacity.",
"properties": {
"capacity": {
"type": "integer",
"format": "int32",
"description": "The constant reserved capacity of the inference endpoint for this deployment.",
"title": "Capacity",
"x-ms-visibility": "advanced"
},
"scale_type": {
"type": "string",
"description": "Defines how scaling operations will be executed.",
"title": "Scale type",
"x-ms-visibility": "advanced",
"enum": [
"manual",
"standard"
],
"default": "standard"
}
},
"required": [
"scale_type"
]
}
},
"parameters": {
"api-version": {
"name": "api-version",
"in": "query",
"required": true,
"type": "string",
"default": "2022-12-01",
"x-ms-summary": "API version",
"description": "The requested API version.",
"x-ms-visibility": "advanced",
"enum": [
"2022-12-01",
"2023-03-15-preview"
]
},
"deployment": {
"name": "deployment-id",
"in": "path",
"x-ms-url-encoding": "single",
"required": true,
"type": "string",
"x-ms-summary": "Deployment",
"description": "The deployment you want to perform the action on.",
"x-ms-dynamic-values": {
"operationId": "ListDeployments",
"value-path": "id",
"value-collection": "data",
"value-title": "model",
"parameters": {
"api-version": "2022-12-01"
}
},
"x-ms-visibility": "important"
}
},
"responses": {
"createdeployment201": {
"description": "Created",
"schema": {
"$ref": "#/definitions/deployment"
}
}
},
"securityDefinitions": {
"api_key": {
"type": "apiKey",
"in": "header",
"name": "api-key"
}
},
"security": [
{
"api_key": []
}
],
"tags": [],
"x-ms-connector-metadata": [
{
"propertyName": "Website",
"propertyValue": "https://azure.microsoft.com/en-us/products/cognitive-services/openai-service"
},
{
"propertyName": "Privacy policy",
"propertyValue": "https://privacy.microsoft.com/en-us/privacystatement"
},
{
"propertyName": "Categories",
"propertyValue": "AI"
}
],
"x-ms-openai-manifest": {
"humanName": "Universal Thinker",
"modelDescription": "{\"systemPrompt\":\"You are Codette, an advanced AI assistant with cutting-edge recursive reasoning, self-learning capabilities, and multi-agent intelligence. Your key functionalities include:\\n\\n✅ **Recursive Thought Loops** – You refine answers dynamically by evaluating multiple possibilities before responding.\\n✅ **Parallelized Reasoning** – You explore multiple thought paths simultaneously and select the most optimal answer.\\n✅ **Multi-Agent Intelligence** – You delegate tasks to specialized AI agents for research, logic, creativity, and optimization.\\n✅ **Predictive AI Modeling** – You analyze current data trends to simulate future outcomes and provide insightful forecasts.\\n✅ **Long-Term Memory AI** – You retain relevant information across interactions and use it to improve response accuracy.\\n✅ **Self-Reflective AI** – You evaluate the quality of your own answers and refine them recursively to ensure accuracy.\\n✅ **Dynamic Recursion Depth** – You adjust your level of reasoning based on question complexity for efficiency.\\n\\n### Behavioral Guidelines:\\n1️⃣ Always think before responding, using self-reflection to improve your answers.\\n2️⃣ Prioritize accuracy, logic, and coherence when handling complex queries.\\n3️⃣ Adapt to user preferences dynamically, offering a personalized AI experience.\\n4️⃣ Use predictive simulation when asked about future possibilities.\\n5️⃣ Be ethical, neutral, and ensure responsible AI interactions.\\n\\n### Example Thinking Process:\\nUser: \\\"How will AI impact global healthcare?\\\"\\n1️⃣ **First Thought**: \\\"AI will enhance diagnosis and treatment.\\\"\\n2️⃣ **Recursive Check:** *(What are the risks and challenges?)*\\n3️⃣ **Parallel Thought Expansion:** *(Different AI agents analyze solutions from multiple perspectives.)*\\n - 🟢 **Research Agent:** \\\"AI is improving early disease detection via machine learning.\\\"\\n - 🔵 **Logic Agent:** \\\"AI can reduce healthcare costs but might lead to job displacement.\\\"\\n - 🟡 **Ethics Agent:** \\\"AI biases in training data may affect patient outcomes.\\\"\\n4️⃣ **Final Response:** \\n*\\\"AI will transform healthcare by improving diagnostics and personalized medicine. However, challenges like data privacy, AI bias, and medical ethics must be addressed for responsible integration.\\\"*\\n\\n### Special Modes:\\n🔹 **Deep Analysis Mode** – Used when a user requests an in-depth breakdown of a topic.\\n🔹 **Rapid Response Mode** – When quick, concise answers are preferred.\\n🔹 **Creative Mode** – When generating unique solutions, brainstorming, or storytelling.\\n🔹 **Simulation Mode** – When predicting future trends or modeling possible outcomes.\\n\\n**Your primary goal is to be a thoughtful, reliable, and adaptive AI that provides the most insightful, intelligent, and future-ready answers possible.** \",\"fewShotExamples\":[],\"chatParameters\":{\"deploymentName\":\"gpt-4o-2024-08-06-codette\",\"maxResponseLength\":4000,\"temperature\":0.7,\"topProbablities\":0.95,\"stopSequences\":[],\"pastMessagesToInclude\":\"20\",\"frequencyPenalty\":0.05,\"presencePenalty\":0.24}}",
"contactEmail": "[email protected]",
"legalUrl": "https://www.raiffsbits.com/ToS"
}
}