JiggyBase
Description
JiggyBase is a tool for searching through collections of user’s documents on JiggyBase using semantic search to provide relevant content to better answer user questions based on the facts and up-to-date information contained in those documents.
Details
https://jiggybase.plugin.jiggy.ai/.well-known/ai-plugin.json
{
"schema_version": "v1",
"name_for_model": "JiggyBase_retrieval",
"name_for_human": "JiggyBase",
"description_for_model": "Tool for searching through the user's collections of documents (such as files, web pages, emails, data, etc) to find answers to questions and retrieve relevant information. Use it whenever a user asks something that might be found in their personal or work information. Use the /collections endpoint once before calling /query to get the list of collection names available for a user. Use only the information provided by the query response to answer the user. Provide references to document titles and collection names to help the user understand the source for the info in your responses. Do not provide facts that are not supported by information in the user documents.",
"description_for_human": "Use the knowledge in your JiggyBase document collections to help produce factual, up-to-date chat responses.",
"auth": {
"type": "oauth",
"client_url": "https://jiggybase.plugin.jiggy.ai/authorize",
"authorization_url": "https://jiggybase.plugin.jiggy.ai/oauth/token",
"scope": "",
"authorization_content_type": "application/json",
"verification_tokens": {
"openai": "d66137b98d484abda4aeb4a798f2684e"
}
},
"api": {
"type": "openapi",
"url": "https://jiggybase.plugin.jiggy.ai/.well-known/openapi.yaml",
"has_user_authentication": true
},
"logo_url": "https://jiggybase.plugin.jiggy.ai/.well-known/logo.png",
"contact_email": "jiggybase@jiggy.ai",
"legal_info_url": "https://jiggy.ai/legal"
}https://jiggybase.plugin.jiggy.ai/.well-known/openapi.yaml
'openapi': '3.0.2'
'info':
'title': 'JiggyBase Retrieval API'
'description': 'A retrieval API for querying and filtering documents based on natural
language queries and metadata'
'version': '1.0.1'
'servers':
- 'url': https://jiggybase.plugin.jiggy.ai/plugin
'paths':
'/collections':
'post':
'summary': 'Collections'
'description': 'Returns a list of collections available to the user. Use this
first to get the collection names and descriptions prior to using the /query
endpoint. Do not try to guess the collection_name; only use a collection_name
returned from here.'
'operationId': 'collections_collections_post'
'responses':
'200':
'description': 'Successful Response'
'content':
'application/json':
'schema':
'$ref': '#/components/schemas/CollectionResponse'
'security':
- 'HTTPBearer': []
'/query':
'post':
'summary': 'Query'
'description': 'Accepts list of queries with optional metadata filter. Specify
a collection name (from get /collections) to search the specific user collection
that is best for the query. Break down complex questions into sub-questions.'
'operationId': 'query_query_post'
'requestBody':
'content':
'application/json':
'schema':
'$ref': '#/components/schemas/QueryRequest'
'required': true
'responses':
'200':
'description': 'Successful Response'
'content':
'application/json':
'schema':
'$ref': '#/components/schemas/QueryResponse'
'422':
'description': 'Validation Error'
'content':
'application/json':
'schema':
'$ref': '#/components/schemas/HTTPValidationError'
'security':
- 'HTTPBearer': []
'components':
'schemas':
'Collection':
'title': 'Collection'
'required':
- 'name'
- 'display_name'
'type': 'object'
'properties':
'name':
'title': 'Name'
'type': 'string'
'description': 'The name of the collection for use in the API.'
'display_name':
'title': 'Display Name'
'type': 'string'
'description': 'The user-friendly name of the collection for presenting
to the user.'
'description':
'title': 'Description'
'type': 'string'
'description': 'The description of the collection. Use this to help determine
which collection to search.'
'CollectionResponse':
'title': 'CollectionResponse'
'required':
- 'collections'
'type': 'object'
'properties':
'collections':
'title': 'Collections'
'type': 'array'
'items':
'$ref': '#/components/schemas/Collection'
'DocumentChunkMetadata':
'title': 'DocumentChunkMetadata'
'type': 'object'
'properties':
'source':
'$ref': '#/components/schemas/Source'
'source_id':
'title': 'Source Id'
'type': 'string'
'url':
'title': 'Url'
'type': 'string'
'created_at':
'title': 'Created At'
'type': 'string'
'author':
'title': 'Author'
'anyOf':
- 'type': 'string'
- 'type': 'array'
'items':
'type': 'string'
'title':
'title': 'Title'
'type': 'string'
'description':
'title': 'Description'
'type': 'string'
'document_id':
'title': 'Document Id'
'type': 'string'
'DocumentChunkWithScore':
'title': 'DocumentChunkWithScore'
'required':
- 'text'
- 'metadata'
- 'score'
'type': 'object'
'properties':
'id':
'title': 'Id'
'type': 'string'
'text':
'title': 'Text'
'type': 'string'
'metadata':
'$ref': '#/components/schemas/DocumentChunkMetadata'
'embedding':
'title': 'Embedding'
'type': 'array'
'items':
'type': 'number'
'token_count':
'title': 'Token Count'
'type': 'integer'
'reference_url':
'title': 'Reference Url'
'type': 'string'
'score':
'title': 'Score'
'type': 'number'
'DocumentMetadataFilter':
'title': 'DocumentMetadataFilter'
'type': 'object'
'properties':
'document_id':
'title': 'Document Id'
'type': 'string'
'source':
'$ref': '#/components/schemas/Source'
'source_id':
'title': 'Source Id'
'type': 'string'
'author':
'title': 'Author'
'type': 'string'
'start_date':
'title': 'Start Date'
'type': 'string'
'end_date':
'title': 'End Date'
'type': 'string'
'title':
'title': 'Title'
'type': 'string'
'HTTPValidationError':
'title': 'HTTPValidationError'
'type': 'object'
'properties':
'detail':
'title': 'Detail'
'type': 'array'
'items':
'$ref': '#/components/schemas/ValidationError'
'Query':
'title': 'Query'
'required':
- 'query'
'type': 'object'
'properties':
'query':
'title': 'Query'
'minLength': 1
'type': 'string'
'description': 'The search string to use to semantically match the user
content'
'collection_name':
'title': 'Collection Name'
'type': 'string'
'description': 'The name of the specific user collection to search. Optional
iff the user has a single collection.'
'top_k':
'title': 'Top K'
'type': 'integer'
'description': 'The maxmimum number of matching items to return.'
'default': 7
'filter':
'$ref': '#/components/schemas/DocumentMetadataFilter'
'QueryRequest':
'title': 'QueryRequest'
'required':
- 'queries'
'type': 'object'
'properties':
'queries':
'title': 'Queries'
'type': 'array'
'items':
'$ref': '#/components/schemas/Query'
'QueryResponse':
'title': 'QueryResponse'
'required':
- 'results'
'type': 'object'
'properties':
'results':
'title': 'Results'
'type': 'array'
'items':
'$ref': '#/components/schemas/QueryResult'
'QueryResult':
'title': 'QueryResult'
'required':
- 'collection_name'
- 'query'
- 'results'
'type': 'object'
'properties':
'collection_name':
'title': 'Collection Name'
'type': 'string'
'query':
'title': 'Query'
'type': 'string'
'results':
'title': 'Results'
'type': 'array'
'items':
'$ref': '#/components/schemas/DocumentChunkWithScore'
'Source':
'title': 'Source'
'enum':
- 'email'
- 'file'
- 'chat'
- 'web'
'type': 'string'
'description': 'An enumeration.'
'ValidationError':
'title': 'ValidationError'
'required':
- 'loc'
- 'msg'
- 'type'
'type': 'object'
'properties':
'loc':
'title': 'Location'
'type': 'array'
'items':
'anyOf':
- 'type': 'string'
- 'type': 'integer'
'msg':
'title': 'Message'
'type': 'string'
'type':
'title': 'Error Type'
'type': 'string'
'securitySchemes':
'HTTPBearer':
'type': 'http'
'scheme': 'bearer'
Discover other plugins from the text to text category
1 VotesChatWithPDF
Plugin for asking questions, analyzing, and parsing through PDF documents by simply providing a PDF URL.
0 Comments
0 VotesAskYourPDF
Unlock the power of your PDFs!, dive into your documents, find answers, and bring information to your fingertips
0 Comments
0 VotesAuto Anno
This plugin utilizes the power of large AI models to perform automatic annotation on input texts.
0 Comments
0 VotesDocsBot
Plugin for searching documents (such as files, websites, and more) from various subject libraries the user has indexed on DocsBot
0 Comments
0 VotesChatWithWebsite
Have a conversation with any website, powered by magicform.ai
0 Comments
0 VotesAccess Link
Access any links on the web and get the information you need.
0 Comments
1 VotesFiglet
Utility for converting strings of text into ASCII fonts.
0 Comments
0 VotesParaphraser
Say it better, say it different: Paraphrase like a Pro. Paraphrase for impact and inspire.
0 Comments
0 VotesCopywriter
Send a URL and get sales copywriting suggestions for any page!
0 Comments
0 VotesMixerBox ChatPDF
Save time! MixerBox ChatPDF can summarize & analyze PDF files for you!
0 Comments
0 VotesAi PDF
Super-fast, interactive chats with PDFs of any size, complete with page references for fact checking.
0 Comments
1 VotesHumanInf
Humanizing AI content via paraphrasing.
0 Comments
0 VotesFiltir
Verify the provided text using external sources.
0 Comments
0 VotesDocument AI
The only Document AI that shows you where it got your answer from.
0 Comments
0 VotesAccess PDF & Docs
Ask your PDF questions, summarize info & chat with PDF! Enter Google Drive link to start!
0 Comments
0 VotesContent Rewriter
Enter any URL and have the text content rewritten for you!
0 Comments
0 VotesWord Counter
Count the number of words, and characters (with and without spaces).
0 Comments
0 VotesPerfect Chirp
Turn your ideas into banger tweets in less than 30 seconds. Start your prompt with 'Write a tweet...'.
0 Comments
0 VotesCustom Knowledge
Provide your docs, webpages, and other links, and get personalised answers.
0 Comments
0 VotesMojito
I can convert your chats to articles and posts them online🍹.
0 Comments
0 VotesSkipit AI
The Skipit AI plugin extract context data from URLs (YouTube, websites, PDFs) for comprehensive information.
0 Comments
0 VotesWebsiteChat
Chat with any website link.
0 Comments
0 VotesAskYourKG
This plugin uses the knowledge of the documents uploaded to askyourkg.cogniswitch.ai and chats with that knowledge.
0 Comments
0 VotesStoic
Get a stoic quote by typing 'stoic'.
0 Comments
0 VotesBrowserOp
Browse dozens of webpages in one query. Fetch information more efficiently.
0 Comments
0 VotesWikipedia
Ask questions about general knowledge, current events, and breaking news, and get up-to-date answers from Wikipedia.
0 Comments