PineconeChatDataSource Class
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
The PineconeChatDataSource.
public class PineconeChatDataSource : Azure.AI.OpenAI.Chat.AzureChatDataSource, System.ClientModel.Primitives.IJsonModel<Azure.AI.OpenAI.Chat.PineconeChatDataSource>, System.ClientModel.Primitives.IPersistableModel<Azure.AI.OpenAI.Chat.PineconeChatDataSource>
type PineconeChatDataSource = class
inherit AzureChatDataSource
interface IJsonModel<PineconeChatDataSource>
interface IPersistableModel<PineconeChatDataSource>
Public Class PineconeChatDataSource
Inherits AzureChatDataSource
Implements IJsonModel(Of PineconeChatDataSource), IPersistableModel(Of PineconeChatDataSource)
- Inheritance
- Implements
Constructors
PineconeChatDataSource() |
Properties
AllowPartialResult |
If set to true, the system will allow partial search results to be used and the request will fail if all partial queries fail. If not specified or specified as false, the request will fail if any search query fails. |
Authentication |
The authentication options to use with the Pinecone data source. |
Environment |
The environment name to use with Pinecone. |
FieldMappings |
The index field mappings. This is required for Pinecone data sources. |
IndexName |
The name of the Pinecone database index to use. |
InScope |
Whether queries should be restricted to use of the indexed data. |
MaxSearchQueries |
The maximum number of rewritten queries that should be sent to the search provider for a single user message. By default, the system will make an automatic determination. |
OutputContextFlags |
The |
RoleInformation |
Additional instructions for the model to inform how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. This is limited to 100 tokens and counts against the overall token limit. |
Strictness |
The configured strictness of the search relevance filtering. Higher strictness will increase precision but lower recall of the answer. |
TopNDocuments |
The configured number of documents to feature in the query. |
VectorizationSource |
The vectorization dependency used for embeddings. |