logging

Author: hemanth-1321

server/agentic/utils/qdrant_db.py

@@ -1,6 +1,7 @@
 import os
 import uuid
 import json
+import logging
 from qdrant_client import QdrantClient, models
 from qdrant_client.models import PointStruct, VectorParams, HnswConfig, Distance
 from dotenv import load_dotenv
@@ -9,6 +10,8 @@
 
 load_dotenv()
 
+logger = logging.getLogger(__name__)
+
 collection_name = "pr_context"
 
 URL = os.getenv("QDRANT_DB")
@@ -22,36 +25,36 @@
 
 # Initialize Qdrant
 qdrant_client = QdrantClient(url=URL, api_key=API_KEY)
-print("Qdrant client initialized successfully")
+logger.info("Qdrant client initialized successfully")
 
 # Initialize embeddings
 if not os.getenv("GOOGLE_API_KEY"):
     raise ValueError("GOOGLE_API_KEY not found")
 
 embeddings = GoogleGenerativeAIEmbeddings(model="models/gemini-embedding-001")
 VECTOR_DIM = len(embeddings.embed_query("dimension test"))
-print(f"✓ Embedding dimension detected: {VECTOR_DIM}")
+logger.info(f"✓ Embedding dimension detected: {VECTOR_DIM}")
 
 # Check or create collection with optimized HNSW indexing
 collections = [c.name for c in qdrant_client.get_collections().collections]
 if collection_name not in collections:
-    print(f"Creating Qdrant collection '{collection_name}' with HNSW index...")
+    logger.info(f"Creating Qdrant collection '{collection_name}' with HNSW index...")
     qdrant_client.create_collection(
         collection_name=collection_name,
         vectors_config=VectorParams(
             size=VECTOR_DIM,
             distance=Distance.COSINE,
             hnsw_config=HnswConfig(
-                m=16,            # neighbors per node (memory vs accuracy tradeoff)
-                ef_construct=200 # index build accuracy
+                m=16,
+                ef_construct=200,
             )
         ),
         shard_number=6,
         replication_factor=2,
     )
-    print(f"Collection '{collection_name}' created successfully!")
+    logger.info(f"Collection '{collection_name}' created successfully!")
 else:
-    print(f"Collection '{collection_name}' already exists")
+    logger.info(f"Collection '{collection_name}' already exists")
 
 def prepare_and_store_context(pr_contexts: List[Dict]):
     """
@@ -85,6 +88,5 @@ def prepare_and_store_context(pr_contexts: List[Dict]):
             },
         ))
 
-    # Upsert all points in one call (faster for large batches)
     qdrant_client.upsert(collection_name=collection_name, points=points)
-    print(f"[Agent] Stored batch of {len(points)} PR contexts in Qdrant")
+    logger.info(f"[Agent] Stored batch of {len(points)} PR contexts in Qdrant")

server/agentic/utils/vector_tool.py

@@ -12,7 +12,6 @@ def search_vector_tool(query: str, limit: int = 10) -> list[dict]:
         query_vector=query_vector,
         limit=limit
     )
-    print("")
     out = []
     for r in results:
         payload = r.payload or {}

server/routes/webhook.py

@@ -2,6 +2,7 @@
 import hmac
 import hashlib
 import json
+import logging
 from server.worker.main import process_pr
 from dotenv import load_dotenv
 from fastapi import APIRouter, Request, HTTPException
@@ -11,19 +12,20 @@
 
 load_dotenv()
 
+logger = logging.getLogger(__name__)
 router = APIRouter()
 
 REDIS_URL = os.getenv("REDIS_URL")
-print("redis url", REDIS_URL)
+logger.info(f"redis url {REDIS_URL}")
 if not REDIS_URL:
     raise RuntimeError("REDIS_URL is not set")
 
 try:
     connection = Redis.from_url(REDIS_URL, decode_responses=False)
     connection.ping()
-    print("Connected to Redis successfully")
+    logger.info("Connected to Redis successfully")
 except Exception as e:
-    print("Redis connection failed:", e)
+    logger.error(f"Redis connection failed: {e}")
     raise
 
 queue = Queue("github_prs", connection=connection)
@@ -72,10 +74,10 @@ def post_progress_comment(pr_number: int, owner: str, repo: str, installation_id
     try:
         response = post_pr_comment(pr_number, owner, repo, progress_body, installation_id)
         comment_id = response.get("id")
-        print(f"[Progress] Posted progress comment ID: {comment_id}")
+        logger.info(f"[Progress] Posted progress comment ID: {comment_id}")
         return comment_id
     except Exception as e:
-        print(f"[Progress] Failed to post progress comment: {e}")
+        logger.error(f"[Progress] Failed to post progress comment: {e}")
         return None
 
 
@@ -101,7 +103,6 @@ async def webhook(request: Request):
             installation = payload.get("installation", {})
             installation_id = installation.get("id")
 
-            
             pr_number = payload.get("number")
             repo_name = repo.get("full_name")
             owner, repo_name_only = repo_name.split("/")
@@ -116,16 +117,15 @@ async def webhook(request: Request):
                 "repo_name": repo_name,
                 "action": action,
                 "commit_sha": pr.get("head", {}).get("sha"),
-                "progress_comment_id": comment_id, 
+                "progress_comment_id": comment_id,
                 "installation_id": installation_id,
                 "owner": owner,
                 "repo": repo_name_only
             }
 
-            print("Enqueuing PR:", pr_data)
-            queue.enqueue(process_pr, pr_data, retry=Retry(max=3, interval=[10, 30, 60])) 
+            logger.info(f"Enqueuing PR: {pr_data}")
+            queue.enqueue(process_pr, pr_data, retry=Retry(max=3, interval=[10, 30, 60]))
 
             return {"status": "queued", "pr": pr_data, "progress_comment_id": comment_id}
 
-
-    return {"status": "ignored"}
+    return {"status": "ignored"}

server/worker/main.py

@@ -4,6 +4,7 @@
 import networkx as nx
 import json
 import boto3
+import logging
 from redis import Redis
 from rq import Queue
 from dotenv import load_dotenv
@@ -16,19 +17,19 @@
 
 load_dotenv()
 
+logger = logging.getLogger(__name__)
 
 REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379/0")
 try:
     connection = Redis.from_url(REDIS_URL, decode_responses=False)
     connection.ping()
-    print("[Worker] Connected to Redis successfully")
+    logger.info("[Worker] Connected to Redis successfully")
 except Exception as e:
-    print("[Worker] Redis connection failed:", e)
+    logger.error(f"[Worker] Redis connection failed: {e}")
     raise
 
 queue = Queue("pr_context_queue", connection=connection)
 
-
 s3_client = boto3.client(
     "s3",
     aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID"),
@@ -47,24 +48,25 @@ def upload_to_s3(file_path, key_prefix):
     return f"s3://{bucket_name}/{s3_key}"
 
 def process_pr(pr_data):
-    print("pr_data",pr_data)
+    logger.info(f"pr_data {pr_data}")
+    
     repo_url = pr_data["clone_url"]
     pr_number = pr_data["pr_number"]
     base_branch = pr_data["base_branch"]
     head_branch = pr_data["head_branch"]
     repo_name = pr_data.get("repo_name", os.path.basename(repo_url).replace(".git", ""))
     commit_sha = pr_data.get("commit_sha")
-    
+
     progress_comment_id = pr_data.get("progress_comment_id")
     installation_id = pr_data.get("installation_id")
-    print("installationid",installation_id)
+    logger.info(f"installationid {installation_id}")
     owner = pr_data.get("owner")
     repo = pr_data.get("repo")
-    
+
     safe_repo_name = repo_name.replace("/", "_")
     s3_prefix = f"pr_contexts/{safe_repo_name}_{pr_number}"
 
-    print(f"[Worker] Reviewing PR #{pr_number} from {repo_name}")
+    logger.info(f"[Worker] Reviewing PR #{pr_number} from {repo_name}")
 
     temp_dir = tempfile.mkdtemp()
 
@@ -133,7 +135,7 @@ def parse_file_if_needed(file_path, file_name):
 
         s3_json_uri = upload_to_s3(context_json_path, s3_prefix)
         s3_txt_uri = upload_to_s3(context_txt_path, s3_prefix)
-        print(f"[Worker] Uploaded context files to S3: {s3_json_uri}, {s3_txt_uri}")
+        logger.info(f"[Worker] Uploaded context files to S3: {s3_json_uri}, {s3_txt_uri}")
 
         queue_data = {
             "pr_number": pr_number,
@@ -148,7 +150,8 @@ def parse_file_if_needed(file_path, file_name):
             "owner": owner,
             "repo": repo
         }
-        print("queue",queue_data)
+        logger.info(f"queue {queue_data}")
+
         queue.enqueue(process_ai_job, queue_data)
 
         return {
@@ -162,8 +165,8 @@ def parse_file_if_needed(file_path, file_name):
         }
 
     except Exception as e:
-        print(f"[Worker] Error: {e}")
+        logger.error(f"[Worker] Error: {e}")
         return {"error": str(e)}
 
     finally:
-        shutil.rmtree(temp_dir)
+        shutil.rmtree(temp_dir)