minor adjustments

.github/workflows/build_deploy.yaml

@@ -3,7 +3,7 @@ name: Build and Deploy to GKE
 on:
   push:
     branches:
-      - main
+      - production
 
 env:
   PROJECT_ID: ${{ secrets.GKE_PROJECT }} 
@@ -49,7 +49,7 @@ jobs:
           --build-arg GITHUB_REF="$GITHUB_REF" \
           .
 
-    # Push the Docker image to Google Container Registry
+    # Push the Docker image to Google Artifact Registry
     - name: Publish
       run: |-
         docker push "gcr.io/$PROJECT_ID/$IMAGE:$GITHUB_SHA"

README.md

@@ -12,7 +12,7 @@ Main Steps
 
 - **Data Ingestion**: Load data from GitHub repositories.
 - **Indexing**: Use SentenceSplitter for indexing in nodes.
-- **Embedding**: Implement FastEmbedEmbedding.
+- **Embedding and Model**: OpenAI.
 - **Vector Store**: Use Qdrant for inserting metadata.
 - **Query Retrieval**: Implement RetrieverQueryEngine.
 - **FastAPI and GKE**: Handle requests via the FastAPI app deployed on GKE.
@@ -131,7 +131,7 @@ The Python version used for this project is Python 3.10. You can follow along th
         --zone=europe-west6-a \
         --num-nodes=5 \
         --enable-autoscaling \
-        --min-nodes=1 \
+        --min-nodes=2 \
         --max-nodes=10 \
         --machine-type=n1-standard-4 \
         --enable-vertical-pod-autoscaling
@@ -162,19 +162,20 @@ The Python version used for this project is Python 3.10. You can follow along th
     <img width="767" alt="lambda-gke" src="https://github.com/benitomartin/mlops-car-prices/assets/116911431/b4a7e10c-52f9-4ca2-ade3-f2136ff6bbdf">
     </p>
 
-    http://34.65.191.211:8000
+    http://34.65.157.134:8000
 
 12. Check some pods and logs
 
     ```bash
-    kubectl logs llama-gke-deploy-8476f496bc-gxhms
-    kubectl describe pod llama-gke-deploy-8476f496bc-gxhms 
+    kubectl logs llama-gke-deploy-668b58b455-fjwvq 
+    kubectl describe pod llama-gke-deploy-668b58b455-fjwvq
+    kubectl top pod llama-gke-deploy-668b58b455-8xfhf 
     ```
 
 13. Clean up to avoid costs deleting the cluster and the docker image
 
     ```bash
-    gcloud container clusters delete app-llama-gke-cluster --zone=europe-west6-a
+    gcloud container clusters delete llama-gke-cluster --zone=europe-west6-a
     kubectl delete deployment llama-gke-deploy
     ```
 
@@ -186,6 +187,6 @@ Run the streamlit app adding the endpoint url that you get after deployment:
    streamlit run streamlit_app.py
    ```
 
-    <p align="center">
-    <img width="767" alt="lambda-gke" src="https://github.com/benitomartin/mlops-car-prices/assets/116911431/b4a7e10c-52f9-4ca2-ade3-f2136ff6bbdf">
-    </p>
+   <p align="center">
+   <img width="767" alt="lambda-gke" src="https://github.com/benitomartin/mlops-car-prices/assets/116911431/b4a7e10c-52f9-4ca2-ade3-f2136ff6bbdf">
+   </p>

create_qdrant_collection.py

@@ -26,7 +26,7 @@ OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
 openai.api_key = OPENAI_API_KEY
 
 
-def get_repository_list(github_token, github_username):
+def get_code_file_list(github_token, github_username):
     """
     Fetch all repositories for a given GitHub user.
 
@@ -194,7 +194,7 @@ def chunked_nodes(data, client, collection_name):
 
 if __name__ == "__main__":
     # Fetch documents from GitHub repositories
-    all_documents = get_repository_list(ACCESS_TOKEN, GITHUB_USERNAME)
+    all_documents = get_code_file_list(ACCESS_TOKEN, GITHUB_USERNAME)
 
     if all_documents:
         # Split documents into nodes

deploy_gke.yaml

@@ -3,7 +3,7 @@ kind: Deployment
 metadata:
   name: llama-gke-deploy
 spec:
-  replicas: 2
+  replicas: 2                     # Pods
   selector:
     matchLabels:
       app: llama-gke-pod
@@ -43,8 +43,8 @@ spec:
             memory: "2Gi"
             cpu: "1"
           limits:                 # Maximum resources allowed
-            memory: "4Gi"
-            cpu: "2"
+            memory: "12Gi"        # Maximum memory of the instance (80-90%)
+            cpu: "4"              # Maximum vCPUs of the instance
         readinessProbe:           # Check if the pod is ready to serve traffic.
           httpGet:
             scheme: HTTP

kustomization.yaml

@@ -2,4 +2,4 @@ apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
   
 resources:
-  - deploy-gke.yaml
+  - deploy_gke.yaml

streamlit_app.py

@@ -0,0 +1,24 @@
+import streamlit as st
+import requests
+
+# Set the FastAPI endpoint
+FASTAPI_ENDPOINT = "http://34.65.157.134:8000/query/"
+
+# Streamlit app title
+st.title("Find Your Code")
+
+# Input field for the query
+query = st.text_input("Query:")
+
+# Button to submit the query
+if st.button("Get Response"):
+    if query:
+        response = requests.post(FASTAPI_ENDPOINT, json={"query": query})
+        if response.status_code == 200:
+            st.write(response.text)
+        else:
+            st.write("Error:", response.status_code)
+    else:
+        st.write("Please enter a query.")
+
+