Skip to content

Backend redis fixes #1489

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Artuomka merged 4 commits into from
Dec 23, 2025
Merged

Backend redis fixes #1489

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
27d4958
redis large data handling
Artuomka Dec 23, 2025
1d9b887
Add support for standalone collections in Redis data access object
Artuomka Dec 23, 2025
69dcf2d
Merge branch 'main' into backend_redis_fixes
Artuomka Dec 23, 2025
965bcd0
refactor: remove unused maxTokens parameter from ConverseCommand
Artuomka Dec 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 1 addition & 3 deletions backend/src/entities/ai/amazon-bedrock/amazon-bedrock.ai.provider.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,12 +1,11 @@
import { Injectable } from '@nestjs/common';
import { BedrockRuntimeClient, ConverseCommand } from '@aws-sdk/client-bedrock-runtime';
import { Injectable } from '@nestjs/common';
import { IAIProvider } from './ai-provider.interface.js';

@Injectable()
export class AmazonBedrockAiProvider implements IAIProvider {
private readonly bedrockRuntimeClient: BedrockRuntimeClient;
private readonly modelId: string = 'global.anthropic.claude-sonnet-4-5-20250929-v1:0';
private readonly maxTokens: number = 1024;

constructor() {
this.bedrockRuntimeClient = new BedrockRuntimeClient();
Expand All @@ -22,7 +21,6 @@ export class AmazonBedrockAiProvider implements IAIProvider {
const command = new ConverseCommand({
modelId: this.modelId,
messages: conversation,
Copy link

Copilot AI Dec 23, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Removing the maxTokens configuration from inferenceConfig means the model will use its default token limit. This could lead to unexpectedly long responses or increased costs. If this change is intentional, consider documenting why the limit was removed. If not, the maxTokens parameter should be restored to control response length and costs.

Suggested change
messages: conversation,
messages: conversation,
inferenceConfig: {
maxTokens: 1024, // Limit response length to control cost and latency
},

Copilot uses AI. Check for mistakes.
inferenceConfig: { maxTokens: this.maxTokens },
});
try {
const response = await this.bedrockRuntimeClient.send(command);
Expand Down
34 changes: 17 additions & 17 deletions backend/src/interceptors/timeout.interceptor.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,21 +5,21 @@ import { Messages } from '../exceptions/text/messages.js';

@Injectable()
export class TimeoutInterceptor implements NestInterceptor {
intercept(_context: ExecutionContext, next: CallHandler): Observable<any> {
const timeoutMs = process.env.NODE_ENV !== 'test' ? 15000 : 200000;
return next.handle().pipe(
timeout(timeoutMs),
catchError((err) => {
if (err instanceof TimeoutError) {
return throwError(
() =>
new RequestTimeoutException({
message: Messages.CONNECTION_TIMED_OUT,
}),
);
}
return throwError(() => err);
}),
);
}
intercept(_context: ExecutionContext, next: CallHandler): Observable<any> {
const timeoutMs = process.env.NODE_ENV !== 'test' ? 15000 : 200000;
return next.handle().pipe(
timeout(timeoutMs),
catchError((err) => {
if (err instanceof TimeoutError) {
return throwError(
() =>
new RequestTimeoutException({
message: Messages.CONNECTION_TIMED_OUT,
}),
);
}
return throwError(() => err);
}),
);
}
}
Loading
Loading