Revert "Delete chroma.sqlite3"

This reverts commit 0728bfa0c0de754b797326662801c3abf913d31c.

.gitignore

@@ -1,4 +1,2 @@
 .env
 .venv
-chroma_db/chroma.sqlite3
-__pycache__

agent.py

@@ -139,12 +139,12 @@ def build_graph():
 
     # --- Graph Definition ---
     builder = StateGraph(MessagesState)
-    # builder.add_node("retriever", retriever_node)
+    builder.add_node("retriever", retriever_node)
     builder.add_node("assistant", assistant)
     builder.add_node("tools", ToolNode(tools))
 
-    builder.add_edge(START, "assistant")
-    # builder.add_edge("retriever", "assistant")
+    builder.add_edge(START, "retriever")
+    builder.add_edge("retriever", "assistant")
     builder.add_conditional_edges("assistant", tools_condition)
     builder.add_edge("tools", "assistant")
 

tools.py

@@ -766,20 +766,13 @@ def reverse_sentence(text: str) -> str:
     return text[::-1]
 
 
-@tool
-def get_max_bird_species_count_from_video(
-    url: str,
-    model_path: str = "best_birds.pt",
-    sample_rate_seconds: int = 1
-) -> dict:
+def get_max_bird_species_count_from_video(url: str) -> Dict:
     """
     Downloads a YouTube video and returns the maximum number of unique bird species 
-    visible in any frame, along with the timestamp and species list.
+    visible in any frame, along with the timestamp.
 
-    Args:
-        url (str): YouTube video URL.
-        model_path (str): Path to the YOLOv5 bird species detection model.
-        sample_rate_seconds (int): How often (in seconds) to sample frames.
+    Parameters:
+        url (str): YouTube video URL
 
     Returns:
         dict: {
@@ -788,60 +781,50 @@ def get_max_bird_species_count_from_video(
             "species_list": List[str],
         }
     """
-    import traceback
-
+    # 1. Download YouTube video
+    yt = YouTube(url)
+    stream = yt.streams.filter(file_extension='mp4').get_highest_resolution()
     temp_video_path = os.path.join(tempfile.gettempdir(), "video.mp4")
-    try:
-        # Download YouTube video
-        yt = YouTube(url)
-        stream = yt.streams.filter(file_extension='mp4').get_highest_resolution()
-        stream.download(filename=temp_video_path)
-
-        # Load object detection model
-        model = torch.hub.load('ultralytics/yolov5', 'custom', path=model_path)
-
-        # Process video frames
-        cap = cv2.VideoCapture(temp_video_path)
-        fps = cap.get(cv2.CAP_PROP_FPS)
-        if not fps or fps <= 0:
-            return {"error": "Could not determine video FPS."}
-        frame_interval = int(fps * sample_rate_seconds)
-
-        max_species_count = 0
-        max_species_frame_time = 0
-        species_at_max = []
-
-        frame_idx = 0
-        while cap.isOpened():
-            ret, frame = cap.read()
-            if not ret:
-                break
-            if frame_idx % frame_interval == 0:
-                # Run detection
-                results = model(frame)
-                detected_species = set()
-                for *box, conf, cls in results.xyxy[0]:
-                    species_name = model.names[int(cls)]
-                    detected_species.add(species_name)
-
-                if len(detected_species) > max_species_count:
-                    max_species_count = len(detected_species)
-                    max_species_frame_time = int(cap.get(cv2.CAP_PROP_POS_MSEC)) // 1000
-                    species_at_max = list(detected_species)
-
-            frame_idx += 1
-
-        cap.release()
-        return {
-            "max_species_count": max_species_count,
-            "timestamp": f"{max_species_frame_time}s",
-            "species_list": species_at_max
-        }
-    except Exception as e:
-        return {"error": f"Exception occurred: {str(e)}\n{traceback.format_exc()}"}
-    finally:
-        if os.path.exists(temp_video_path):
-            try:
-                os.remove(temp_video_path)
-            except Exception:
-                pass
+    stream.download(filename=temp_video_path)
+
+    # 2. Load object detection model for bird species
+    # Load a fine-tuned YOLOv5 model or similar pretrained on bird species
+    model = torch.hub.load('ultralytics/yolov5', 'custom', path='best_birds.pt')  # path to your trained model
+
+    # 3. Process video frames
+    cap = cv2.VideoCapture(temp_video_path)
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    frame_interval = int(fps * 1)  # 1 frame per second
+
+    max_species_count = 0
+    max_species_frame_time = 0
+    species_at_max = []
+
+    frame_idx = 0
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+        if frame_idx % frame_interval == 0:
+            # Run detection
+            results = model(frame)
+            detected_species = set()
+            for *box, conf, cls in results.xyxy[0]:
+                species_name = model.names[int(cls)]
+                detected_species.add(species_name)
+
+            if len(detected_species) > max_species_count:
+                max_species_count = len(detected_species)
+                max_species_frame_time = int(cap.get(cv2.CAP_PROP_POS_MSEC)) // 1000
+                species_at_max = list(detected_species)
+
+        frame_idx += 1
+
+    cap.release()
+    os.remove(temp_video_path)
+
+    return {
+        "max_species_count": max_species_count,
+        "timestamp": f"{max_species_frame_time}s",
+        "species_list": species_at_max
+    }