langchain
Version:
Typescript bindings for langchain
207 lines (206 loc) • 8.74 kB
text/typescript
import { AgentMiddleware } from "../../types.cjs";
import * as _$_langchain_core_tools0 from "@langchain/core/tools";
import { InferInteropZodInput } from "@langchain/core/utils/types";
import { z } from "zod/v3";
//#region src/agents/middleware/provider/aws/promptCaching.d.ts
declare const contextSchema: z.ZodObject<{
/**
* Whether to enable prompt caching.
* @default true
*/
enableCaching: z.ZodOptional<z.ZodBoolean>;
/**
* The time-to-live for the cached prompt.
* @default "5m"
*/
ttl: z.ZodOptional<z.ZodEnum<["5m", "1h"]>>;
/**
* The minimum number of messages required before caching is applied.
* @default 1
*/
minMessagesToCache: z.ZodOptional<z.ZodNumber>;
/**
* The behavior to take when an unsupported model is used.
* - "ignore" will ignore the unsupported model and continue without caching.
* - "warn" will warn the user and continue without caching.
* - "raise" will raise an error and stop the agent.
* @default "warn"
*/
unsupportedModelBehavior: z.ZodOptional<z.ZodEnum<["ignore", "warn", "raise"]>>;
}, "strip", z.ZodTypeAny, {
enableCaching?: boolean | undefined;
ttl?: "1h" | "5m" | undefined;
minMessagesToCache?: number | undefined;
unsupportedModelBehavior?: "ignore" | "raise" | "warn" | undefined;
}, {
enableCaching?: boolean | undefined;
ttl?: "1h" | "5m" | undefined;
minMessagesToCache?: number | undefined;
unsupportedModelBehavior?: "ignore" | "raise" | "warn" | undefined;
}>;
type BedrockConversePromptCachingMiddlewareConfig = Partial<InferInteropZodInput<typeof contextSchema>>;
/**
* Creates a prompt caching middleware for AWS Bedrock Converse models to optimize API usage.
*
* This middleware automatically enables Bedrock's prompt caching when using AWS Bedrock Converse
* models. This can significantly reduce costs for applications with repetitive prompts, long
* system messages, or extensive conversation histories.
*
* ## How It Works
*
* The middleware intercepts model requests and sets a cache control signal that
* `ChatBedrockConverse` translates into Bedrock `cachePoint` breakpoints. Cache points are
* inserted after the system prompt, after the tool definitions, and after the final message, so
* the stable prefix of each request is cached. On subsequent requests with a matching prefix, the
* cached representations are reused, skipping redundant token processing. Exact placement varies
* by model (e.g. Amazon Nova models cache fewer breakpoints and ignore the `"1h"` TTL).
*
* ## Benefits
*
* - **Cost Reduction**: Avoid reprocessing the same tokens repeatedly
* - **Lower Latency**: Cached prompts are processed faster as embeddings are pre-computed
* - **Better Scalability**: Reduced computational load enables handling more requests
* - **Consistent Performance**: Stable response times for repetitive queries
*
* @param middlewareOptions - Configuration options for the caching behavior
* @param middlewareOptions.enableCaching - Whether to enable prompt caching (default: `true`)
* @param middlewareOptions.ttl - Cache time-to-live: `"5m"` for 5 minutes or `"1h"` for 1 hour (default: `"5m"`)
* @param middlewareOptions.minMessagesToCache - Minimum number of messages required before caching is applied (default: `1`)
* @param middlewareOptions.unsupportedModelBehavior - The behavior to take when an unsupported model is used (default: `"warn"`)
*
* @returns A middleware instance that can be passed to `createAgent`
*
* @throws {Error} When `unsupportedModelBehavior` is `"raise"` and the model is not a
* cache-capable Bedrock Converse model — either a non-Bedrock provider, or a Bedrock
* Converse model outside the Anthropic Claude / Amazon Nova families.
*
* @example
* Basic usage with default settings
* ```typescript
* import { createAgent } from "langchain";
* import { bedrockPromptCachingMiddleware } from "langchain";
*
* const agent = createAgent({
* model: "bedrock:anthropic.claude-haiku-4-5-20251001-v1:0",
* middleware: [
* bedrockPromptCachingMiddleware()
* ]
* });
* ```
*
* @example
* Custom configuration for longer conversations
* ```typescript
* const cachingMiddleware = bedrockPromptCachingMiddleware({
* ttl: "1h", // Cache for 1 hour instead of default 5 minutes
* minMessagesToCache: 5 // Only cache after 5 messages
* });
*
* const agent = createAgent({
* model: "bedrock:anthropic.claude-haiku-4-5-20251001-v1:0",
* systemPrompt: "You are a helpful assistant with deep knowledge of...", // Long system prompt
* middleware: [cachingMiddleware]
* });
* ```
*
* @example
* Conditional caching based on runtime context
* ```typescript
* const agent = createAgent({
* model: "bedrock:anthropic.claude-haiku-4-5-20251001-v1:0",
* middleware: [
* bedrockPromptCachingMiddleware({
* enableCaching: true,
* ttl: "5m"
* })
* ]
* });
*
* // Disable caching for specific requests
* await agent.invoke(
* { messages: [new HumanMessage("Process this without caching")] },
* {
* configurable: {
* middleware_context: { enableCaching: false }
* }
* }
* );
* ```
*
* @example
* Optimal setup for customer support chatbot
* ```typescript
* const supportAgent = createAgent({
* model: "bedrock:anthropic.claude-haiku-4-5-20251001-v1:0",
* systemPrompt: `You are a customer support agent for ACME Corp.
*
* Company policies:
* - Always be polite and professional
* - Refer to knowledge base for product information
* - Escalate billing issues to human agents
* ... (extensive policies and guidelines)
* `,
* tools: [searchKnowledgeBase, createTicket, checkOrderStatus],
* middleware: [
* bedrockPromptCachingMiddleware({
* ttl: "1h", // Long TTL for stable system prompt
* minMessagesToCache: 1 // Cache immediately due to large system prompt
* })
* ]
* });
* ```
*
* @remarks
* - **Bedrock Converse Only**: This middleware only applies caching to AWS Bedrock Converse models. Other providers are handled per `unsupportedModelBehavior`
* - **Supported Families**: Bedrock prompt caching is only available on the **Anthropic Claude** and **Amazon Nova** model families. Other Bedrock Converse models (e.g. Mistral, Cohere, Meta) reject cache points at request time, so they are treated as unsupported and routed through `unsupportedModelBehavior`
* - **Automatic Application**: Caching is applied automatically when the message count reaches `minMessagesToCache`
* - **TTL Options**: Only supports "5m" (5 minutes) and "1h" (1 hour) as TTL values; actual support varies by model
* - **Best Use Cases**: Long system prompts, multi-turn conversations, repetitive queries, RAG applications
*
* @see {@link createAgent} for agent creation
* @see {@link https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html} AWS Bedrock prompt caching documentation
* @public
*/
declare function bedrockPromptCachingMiddleware(middlewareOptions?: BedrockConversePromptCachingMiddlewareConfig): AgentMiddleware<undefined, z.ZodObject<{
/**
* Whether to enable prompt caching.
* @default true
*/
enableCaching: z.ZodOptional<z.ZodBoolean>;
/**
* The time-to-live for the cached prompt.
* @default "5m"
*/
ttl: z.ZodOptional<z.ZodEnum<["5m", "1h"]>>;
/**
* The minimum number of messages required before caching is applied.
* @default 1
*/
minMessagesToCache: z.ZodOptional<z.ZodNumber>;
/**
* The behavior to take when an unsupported model is used.
* - "ignore" will ignore the unsupported model and continue without caching.
* - "warn" will warn the user and continue without caching.
* - "raise" will raise an error and stop the agent.
* @default "warn"
*/
unsupportedModelBehavior: z.ZodOptional<z.ZodEnum<["ignore", "warn", "raise"]>>;
}, "strip", z.ZodTypeAny, {
enableCaching?: boolean | undefined;
ttl?: "1h" | "5m" | undefined;
minMessagesToCache?: number | undefined;
unsupportedModelBehavior?: "ignore" | "raise" | "warn" | undefined;
}, {
enableCaching?: boolean | undefined;
ttl?: "1h" | "5m" | undefined;
minMessagesToCache?: number | undefined;
unsupportedModelBehavior?: "ignore" | "raise" | "warn" | undefined;
}>, {
enableCaching?: boolean | undefined;
ttl?: "1h" | "5m" | undefined;
minMessagesToCache?: number | undefined;
unsupportedModelBehavior?: "ignore" | "raise" | "warn" | undefined;
}, readonly (_$_langchain_core_tools0.ServerTool | _$_langchain_core_tools0.ClientTool)[], readonly []>;
//#endregion
export { BedrockConversePromptCachingMiddlewareConfig, bedrockPromptCachingMiddleware };
//# sourceMappingURL=promptCaching.d.cts.map