From 65fb2b1837fca8abc3ca6f504bb50b8e5430461b Mon Sep 17 00:00:00 2001
From: "Charles E. Gormley" <ceg98@drexel.edu>
Date: Sat, 12 Oct 2024 13:43:29 -0400
Subject: [PATCH] fixing issue with embedding model initialization.

---
 src/infra/cloudformation/eventbridge.yaml                      | 2 +-
 .../src/analytics/embeddings/vector_db.py                      | 3 +--
 .../lambdas/RSSFeedProcessorLambda/src/lambda_function.py      | 1 -
 src/infra/lambdas/lambda_utils/update_lambda_env_vars.py       | 3 ++-
 todo.md                                                        | 2 +-
 5 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/src/infra/cloudformation/eventbridge.yaml b/src/infra/cloudformation/eventbridge.yaml
index 6726a04..04371cf 100644
--- a/src/infra/cloudformation/eventbridge.yaml
+++ b/src/infra/cloudformation/eventbridge.yaml
@@ -28,7 +28,7 @@ Resources:
     Properties:
       Name: rss-feed-processor-schedule
       Description: Runs the RSS Feed Processor Lambda function every hour
-      ScheduleExpression: rate(5 minutes)
+      ScheduleExpression: rate(30 minutes)
       FlexibleTimeWindow: 
         Mode: FLEXIBLE
         MaximumWindowInMinutes: 1
diff --git a/src/infra/lambdas/RSSFeedProcessorLambda/src/analytics/embeddings/vector_db.py b/src/infra/lambdas/RSSFeedProcessorLambda/src/analytics/embeddings/vector_db.py
index 8c99396..5483513 100644
--- a/src/infra/lambdas/RSSFeedProcessorLambda/src/analytics/embeddings/vector_db.py
+++ b/src/infra/lambdas/RSSFeedProcessorLambda/src/analytics/embeddings/vector_db.py
@@ -11,8 +11,7 @@ embedding_dim = os.getenv("VECTOR_EMBEDDING_DIM")
 vector_search_metric = os.getenv("VECTOR_SEARCH_METRIC")
 index_name = os.getenv("PINECONE_DB_NAME")
 
-client = OpenAI()
-
+client = OpenAI() # For Embedding Models, Not LLMs
 pc = Pinecone(api_key=api_key)
 
 def get_index():
diff --git a/src/infra/lambdas/RSSFeedProcessorLambda/src/lambda_function.py b/src/infra/lambdas/RSSFeedProcessorLambda/src/lambda_function.py
index 8717448..22029ed 100644
--- a/src/infra/lambdas/RSSFeedProcessorLambda/src/lambda_function.py
+++ b/src/infra/lambdas/RSSFeedProcessorLambda/src/lambda_function.py
@@ -36,7 +36,6 @@ def lambda_handler(event, context):
 
         # Process the feed
         result = extract_feed(feed)
-        print(type(result))
         logger.info("Process Feed Result Dictionary: ", result)
         last_pub_dt = result['max_date']
 
diff --git a/src/infra/lambdas/lambda_utils/update_lambda_env_vars.py b/src/infra/lambdas/lambda_utils/update_lambda_env_vars.py
index c1d5e8f..f106eb7 100644
--- a/src/infra/lambdas/lambda_utils/update_lambda_env_vars.py
+++ b/src/infra/lambdas/lambda_utils/update_lambda_env_vars.py
@@ -20,7 +20,8 @@ def update_env_vars(function_name):
         'VECTOR_EMBEDDING_MODEL': os.environ.get('VECTOR_EMBEDDING_MODEL'),
         'VECTOR_EMBEDDING_DIM': os.environ.get('VECTOR_EMBEDDING_DIM'),
         'VECTOR_SEARCH_METRIC': os.environ.get('VECTOR_SEARCH_METRIC'),
-        'PINECONE_DB_NAME': os.environ.get('PINECONE_DB_NAME')
+        'PINECONE_DB_NAME': os.environ.get('PINECONE_DB_NAME'),
+        'OPENAI_API_KEY': os.environ.get('OPENAI_API_KEY')
     }
     
     return lambda_client.update_function_configuration(
diff --git a/todo.md b/todo.md
index 484a4d7..474261d 100644
--- a/todo.md
+++ b/todo.md
@@ -1,5 +1,5 @@
 # Testing🧪
-* Testing from 3rd party aws account. [ Today ]
+* Testing from 3rd party aws account. 
 * Test Large Amounts of Feeds ( Decrease the cadence of ingesting. ) [ Today ]
 * Test out Vector Databases at Small Scale
 * Test out Vector Databases at Scale.