public sealed class RagFileParsingConfig.Types.LlmParser : IMessage<RagFileParsingConfig.Types.LlmParser>, IEquatable<RagFileParsingConfig.Types.LlmParser>, IDeepCloneable<RagFileParsingConfig.Types.LlmParser>, IBufferMessage, IMessage
Reference documentation and code samples for the Cloud AI Platform v1beta1 API class RagFileParsingConfig.Types.LlmParser.
Specifies the advanced parsing for RagFiles.
Implements
IMessageRagFileParsingConfigTypesLlmParser, IEquatableRagFileParsingConfigTypesLlmParser, IDeepCloneableRagFileParsingConfigTypesLlmParser, IBufferMessage, IMessageNamespace
Google.Cloud.AIPlatform.V1Beta1Assembly
Google.Cloud.AIPlatform.V1Beta1.dll
Constructors
LlmParser()
public LlmParser()
LlmParser(LlmParser)
public LlmParser(RagFileParsingConfig.Types.LlmParser other)
Parameter | |
---|---|
Name | Description |
other |
RagFileParsingConfigTypesLlmParser |
Properties
CustomParsingPrompt
public string CustomParsingPrompt { get; set; }
The prompt to use for parsing. If not specified, a default prompt will be used.
Property Value | |
---|---|
Type | Description |
string |
MaxParsingRequestsPerMin
public int MaxParsingRequestsPerMin { get; set; }
The maximum number of requests the job is allowed to make to the LLM model per minute. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If unspecified, a default value of 5000 QPM would be used.
Property Value | |
---|---|
Type | Description |
int |
ModelName
public string ModelName { get; set; }
The name of a LLM model used for parsing.
Format: gemini-1.5-pro-002
Property Value | |
---|---|
Type | Description |
string |