* Revert "Merge branch 'microsoft:dev' into dev"

This reverts commit 096a7c3199, reversing
changes made to cb0948670f.

* Revert "Merge branch 'microsoft:dev' into dev"

This reverts commit cb0948670f, reversing
changes made to dc26e8a026.

* Revert "Revert "Merge branch 'microsoft:dev' into dev""

This reverts commit 01764d0a6d.

* Revert "Revert "Merge branch 'microsoft:dev' into dev""

This reverts commit a3f086ef0f.

* Add files via upload

* Revert "Add files via upload"

This reverts commit eeff7b7a02.

* Add files via upload

* Delete independent-publisher-connectors/FileIO directory

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Revert "Add files via upload"

This reverts commit 1d85506958.

* Update readme.md

* Revert "Update readme.md"

This reverts commit b94447a142.

* Add files via upload
This commit is contained in:
Troy Taylor 2023-11-29 12:37:48 -05:00 коммит произвёл GitHub
Родитель a47aa55fb7
Коммит 66655566ae
Не найден ключ, соответствующий данной подписи
Идентификатор ключа GPG: 4AEE18F83AFDEB23
3 изменённых файлов: 378 добавлений и 0 удалений

Просмотреть файл

@ -0,0 +1,336 @@
{
"swagger": "2.0",
"info": {
"title": "Neum",
"description": "With Neum AI, your context in prompts is always accurate and up to date. It enables you to create a pipeline that keeps your data synced between a source (ex. Document DB) and a sink (ex. Pinecone).",
"version": "1.0",
"contact": {
"name": "Troy Taylor",
"url": "https://www.hitachisolutions.com",
"email": "ttaylor@hitachisolutions.com"
}
},
"host": "api.neum.ai",
"basePath": "/v1/",
"schemes": [
"https"
],
"consumes": [
"application/json"
],
"produces": [
"application/json"
],
"paths": {
"/pipelines": {
"post": {
"responses": {
"200": {
"description": "default",
"schema": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "The identifier.",
"title": "ID"
},
"source": {
"type": "object",
"properties": {
"source_name": {
"type": "string",
"description": "The source name.",
"title": "Name"
}
},
"title": "Source"
},
"sink": {
"type": "object",
"properties": {
"sink_name": {
"type": "string",
"description": "The sink name.",
"title": "Name"
}
},
"title": "Sink"
},
"embed": {
"type": "object",
"properties": {
"embed_name": {
"type": "string",
"description": "The embed name.",
"title": "Name"
}
},
"title": "Embed"
},
"created": {
"type": "number",
"format": "float",
"description": "When created.",
"title": "Created"
},
"trigger_schedule": {
"type": "object",
"properties": {
"start_date": {
"type": "string",
"description": "The start date.",
"title": "Start Date"
},
"cadence": {
"type": "string",
"description": "The cadence.",
"title": "Cadence"
}
},
"title": "Trigger Schedule"
}
}
}
}
},
"summary": "Create a pipeline",
"description": "Creates a pipeline with an optional scheduled trigger.",
"operationId": "PipelinePost",
"parameters": [
{
"name": "body",
"in": "body",
"required": false,
"schema": {
"type": "object",
"properties": {
"source": {
"type": "object",
"properties": {
"source_name": {
"type": "string",
"description": "The source name.",
"title": "Source"
},
"metadata": {
"type": "object",
"properties": {
"connection_string": {
"type": "string",
"description": "The connection string.",
"title": "Connection String"
},
"container_name": {
"type": "string",
"description": "The container name.",
"title": "Container"
}
},
"title": "Metadata",
"required": [
"connection_string",
"container_name"
]
}
},
"title": "Source",
"required": [
"source_name"
]
},
"embed": {
"type": "object",
"properties": {
"embed_name": {
"type": "string",
"description": "The embed name.",
"title": "Name"
},
"metadata": {
"type": "object",
"properties": {
"api_key": {
"type": "string",
"description": "The API key.",
"title": "API Key"
},
"organization": {
"type": "string",
"description": "The organization.",
"title": "Organization"
}
},
"title": "Metadata",
"required": [
"api_key",
"organization"
]
}
},
"title": "Embed",
"required": [
"embed_name"
]
},
"sink": {
"type": "object",
"properties": {
"sink_name": {
"type": "string",
"description": "The sink name.",
"title": "Sink Name"
},
"metadata": {
"type": "object",
"properties": {
"api_key": {
"type": "string",
"description": "The API key.",
"title": "API Key"
},
"environment": {
"type": "string",
"description": "The environment.",
"title": "Environment"
},
"index": {
"type": "string",
"description": "The index.",
"title": "Index"
},
"namespace": {
"type": "string",
"description": "The namespace.",
"title": "Namespace"
}
},
"title": "Metadata",
"required": [
"api_key",
"environment",
"index",
"namespace"
]
}
},
"title": "Sink",
"required": [
"sink_name"
]
},
"trigger_schedule": {
"type": "object",
"properties": {
"start_date": {
"type": "string",
"description": "The start date.",
"title": "Start Date"
},
"cadence": {
"type": "string",
"description": "The cadence.",
"title": "Cadence"
}
},
"title": "Trigger Schedule"
}
}
}
}
]
}
},
"/pipelines/{pipeline_id}/search": {
"post": {
"responses": {
"200": {
"description": "default",
"schema": {
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "string"
},
"description": "The results.",
"title": "Results"
}
}
}
}
},
"summary": "Test pipeline",
"description": "To test your new pipeline, Neum AI provides capabilities to quickly query the vector store that data is being pushed into. You can observe general information like the number of vectors in it as well as do quick queries using a provided text.",
"operationId": "PipelineTestPost",
"parameters": [
{
"name": "pipeline_id",
"in": "path",
"x-ms-summary": "Pipeline ID",
"x-ms-url-encoding": "single",
"description": "The pipeline identifier.",
"required": true,
"type": "string"
},
{
"name": "body",
"in": "body",
"required": false,
"schema": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The query.",
"title": "Query"
},
"number_of_results": {
"type": "integer",
"format": "int32",
"description": "The number of results.",
"title": "Number Of Results"
}
},
"required": [
"number_of_results",
"query"
]
}
}
]
}
}
},
"definitions": {},
"parameters": {},
"responses": {},
"securityDefinitions": {
"API Key": {
"type": "apiKey",
"in": "header",
"name": "neum-api-key"
}
},
"security": [
{
"API Key": []
}
],
"tags": [],
"x-ms-connector-metadata": [
{
"propertyName": "Website",
"propertyValue": "https://www.neum.ai/"
},
{
"propertyName": "Privacy policy",
"propertyValue": "https://www.neum.ai/"
},
{
"propertyName": "Categories",
"propertyValue": "AI"
}
]
}

Просмотреть файл

@ -0,0 +1,23 @@
{
"properties": {
"connectionParameters": {
"api_key": {
"type": "securestring",
"uiDefinition": {
"displayName": "API Key",
"description": "The API Key for this api",
"tooltip": "Provide your API Key",
"constraints": {
"tabIndex": 2,
"clearText": false,
"required": "true"
}
}
}
},
"iconBrandColor": "#da3b01",
"capabilities": [],
"publisher": "Troy Taylor",
"stackOwner": "Neum"
}
}

Просмотреть файл

@ -0,0 +1,19 @@
# Neum
With Neum AI, your context in prompts is always accurate and up to date. It enables you to create a pipeline that keeps your data synced between a source (ex. Document DB) and a sink (ex. Pinecone).
## Publisher: Troy Taylor, Hitachi Solutions
## Prerequisites
You will need to sign up for an account with [Neum](https://dashboard.neum.ai/).
## Obtaining Credentials
Once logged in to your dashboard you will find your API key under Settings.
## Supported Operations
### Create a pipeline
Creates a pipeline with an optional scheduled trigger.
### Test pipeline
To test your new pipeline, Neum AI provides capabilities to quickly query the vector store that data is being pushed into. You can observe general information like the number of vectors in it as well as do quick queries using a provided text.
## Known Issues and Limitations
There are no known issues at this time.