NotifAI Performance Improvements #91
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,94 @@ | ||
| x-aws-environment: &aws-environment | ||
| AWS_DEFAULT_REGION: eu-west-2 | ||
| AWS_REGION: eu-west-2 | ||
| AWS_SECRET_ACCESS_KEY: ${AWS_SECRET_ACCESS_KEY} | ||
| AWS_ACCESS_KEY_ID: ${AWS_ACCESS_KEY_ID} | ||
| AWS_SESSION_TOKEN: ${AWS_SESSION_TOKEN} | ||
|
|
||
| services: | ||
| frontend: | ||
| build: | ||
| context: src/frontend/notifai-uploader | ||
| ports: | ||
| - "3000:80" | ||
| depends_on: | ||
| - backend | ||
| - bedrock-prompt-messager | ||
| environment: | ||
| <<: *aws-environment | ||
| REACT_APP_BACKEND_API_BASE_URL: ${REACT_APP_BACKEND_API_BASE_URL} | ||
| REACT_APP_COGNITO_ID: ${COGNITO_APP_CLIENT_ID} | ||
| REACT_APP_COGNITO_USER_POOL_ID: ${COGNITO_USER_POOL_ID} | ||
| REACT_APP_API_GATEWAY: ${REACT_APP_API_GATEWAY} | ||
| healthcheck: | ||
| test: ["CMD", "curl", "http://localhost:80/health"] | ||
| interval: 30s | ||
| timeout: 10s | ||
| retries: 3 | ||
| start_period: 30s | ||
|
|
||
| backend: | ||
| build: | ||
| context: src/backend/app | ||
| ports: | ||
| - "8080:8080" | ||
| entrypoint: | ||
| [ | ||
| "fastapi", | ||
| "dev", | ||
| "/app/main.py", | ||
| "--port", | ||
| "8080", | ||
| "--host", | ||
| "0.0.0.0", | ||
| "--reload", | ||
| ] | ||
| volumes: | ||
| - "${PWD}/src/backend/app:/app" | ||
| environment: | ||
| <<: *aws-environment | ||
| COGNITO_REGION: ${AWS_REGION} | ||
| COGNITO_USER_POOL_ID: ${COGNITO_USER_POOL_ID} | ||
| COGNITO_APP_CLIENT_ID: COGNITO_APP_CLIENT_ID | ||
| S3_LLM_LOGS_BUCKET: ${S3_LLM_LOGS_BUCKET} | ||
| S3_LLM_LOGS_DIRECTORY: ${S3_LLM_LOGS_DIRECTORY} | ||
| S3_LLM_LOGS_BUCKET_ACCOUNT_ID: ${S3_LLM_LOGS_BUCKET_ACCOUNT_ID} | ||
| healthcheck: | ||
| test: | ||
| [ | ||
| "CMD", | ||
| "python3", | ||
| "-c", | ||
| "import urllib.request; urllib.request.urlopen('http://localhost:8080/health')", | ||
| ] | ||
| interval: 30s | ||
| timeout: 10s | ||
| retries: 3 | ||
| start_period: 30s | ||
|
|
||
| bedrock-prompt-messager: | ||
| build: | ||
| context: src/backend/bedrock-prompt-messager | ||
| dockerfile: Dockerfile | ||
| ports: | ||
| - "8081:8080" | ||
| volumes: | ||
| - "${PWD}/src/backend/bedrock-prompt-messager:/var/task" | ||
| environment: | ||
| <<: *aws-environment | ||
| env_model_id: "amazon.nova-lite-v1:0" | ||
| env_temperature: "0.1" | ||
| env_max_tokens: "10000" | ||
| env_top_p: "0.5" | ||
| env_logging_s3_bucket: ${S3_LLM_LOGS_BUCKET} | ||
| env_logging_s3_key_prefix: ${S3_LLM_LOGS_DIRECTORY} | ||
| env_guardrail_arn: ${GUARDRAIL_ARN} | ||
| env_guardrail_version: ${GUARDRAIL_VERSION} | ||
| env_logging_s3_account_id: ${S3_LLM_LOGS_BUCKET_ACCOUNT_ID} | ||
| # FEAT_EXTENDED_ADVICE: true | ||
| healthcheck: | ||
| test: ["CMD", "curl", "http://localhost:8080/health"] | ||
| interval: 30s | ||
| timeout: 10s | ||
| retries: 3 | ||
| start_period: 30s | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -12,6 +12,8 @@ module "eventbridge" { | |
| arn = aws_lambda_function.bedrock_evaluations.arn | ||
| input = jsonencode({ "job" : "cron-by-rate" }) | ||
| role_arn = aws_iam_role.eventbridge_scheduler_role.arn | ||
|
|
||
| end_date = "2025-12-16T00:00:00Z" | ||
| } | ||
|
Comment on lines
14
to
17
There was a problem hiding this comment. Hard-coding
Author
There was a problem hiding this comment. This was deliberate - as the smallest change that could disable the evaluation runner. That code needs to be updated/replaced/removed as per the adopting team. At the moment it doesn't add value because it always tests the same model against the same documents (and will not function against the updated prompt). A proper MLOps type evaluation pipeline would be desirable, but was out of the scope of these changes. (This rationale applies to all of the comments impacting the evaulation service code) |
||
| } | ||
| } | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
|
|
@@ -67,7 +67,7 @@ data "aws_iam_policy_document" "bedrock_access" { | |||||
| "${aws_s3_bucket.lambda_prompt_logging_s3_bucket.arn}/${local.s3_lambda_logging_key}*", | ||||||
| "arn:aws:bedrock:${var.region}:${var.aws_account_id}:guardrail/*", | ||||||
| "arn:aws:bedrock:${var.region}:${var.aws_account_id}:inference-profile/eu.amazon.nova-pro-v1:*", | ||||||
|
There was a problem hiding this comment. IAM policy still grants access to the Nova Pro inference profile (
Suggested change
|
||||||
| "arn:aws:bedrock:${var.region}::foundation-model/amazon.nova-lite-v1:0", | ||||||
| "arn:aws:logs:${var.region}:${var.aws_account_id}:log-group:/aws/lambda/${local.lambda_name}:*" | ||||||
| ] | ||||||
| } | ||||||
|
|
||||||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The backend is started with
fastapi dev /app/main.py, butmain.pyimports modules asfrom app.... In this container layout, that typically requiresPYTHONPATHto include the parent directory of theapppackage (mirroringpytest.ini: pythonpath = src/backend). Without settingPYTHONPATH(or switching to module-style startup likefastapi dev app.main:app), the backend may fail to start withModuleNotFoundError: No module named 'app'.