Merge branch 'development'

.env.example

@@ -0,0 +1,2 @@
+OPENAI_API_KEY=
+TMDB_API_KEY=

components/gradio_ui.py

@@ -1,116 +1,50 @@
 import gradio as gr
+from components.imdb_poster import get_imdb_poster
+
+
+def get_multiple_imdb_posters(imdb_ids):
+    posters = []
+    for imdb_id in imdb_ids:
+        poster_url = get_imdb_poster(imdb_id)
+        print(f"IMDB ID: {imdb_id}, Poster URL: {poster_url}")
+        posters.append({"tconst": imdb_id, "poster_url": poster_url})
+    return posters
+
 
 def create_interface(engine):
-    def get_recommendations_text(query):
-        try:
-            result = engine.get_recommendations(query)
-            if isinstance(result, tuple) and len(result) >= 1:
-                return result[0]
-            else:
-                return str(result)
-        except Exception as e:
-            return f"❌ Error: {str(e)}"
+    def chat_function(message, history):
+        if not message:
+            return history, "", []
 
-    def get_thumbnails_html(query):
         try:
-            result = engine.get_recommendations(query)
-            if isinstance(result, tuple) and len(result) >= 1:
-                search_results = engine.get_recommendations(query)
-                
+            result = engine.get_recommendations(message)
+            imdb_ids = []
+            df = result[1]
+            if isinstance(result, tuple) and len(result) > 1:
+                if hasattr(result[1], "columns") and "ImdbId" in result[1].columns:
+                    imdb_ids = result[1]["ImdbId"].tolist()
 
-                thumbnails_html = []
-                thumbnails_html.append("""
-                <div style="display: grid; grid-template-columns: repeat(auto-fill, minmax(150px, 1fr)); gap: 15px; padding: 20px; max-height: 600px; overflow-y: auto;">
-                """)
+            posters = get_multiple_imdb_posters(imdb_ids)
 
-                thumbnails_html.append("""
-                <div style="grid-column: 1 / -1; text-align: center; padding: 20px; color: #666;">
-                    Thumbnails will appear here when poster URLs are available
-                </div>
-                """)
-                
-                thumbnails_html.append("</div>")
-                return "".join(thumbnails_html)
-                
-        except Exception as e:
-            return f"<div style='color: red; padding: 20px;'>❌ Error: {str(e)}</div>"
+            thumbnails = [p["poster_url"] for p in posters if p["poster_url"]]
 
-    def get_thumbnails_from_results(query):
-        """Get thumbnails from search results"""
-        try:
-            formatted_results, df_results = engine.get_recommendations(query)
-        
-            html_parts = []
-            html_parts.append("""
-            <div style="display: grid; grid-template-columns: repeat(auto-fill, minmax(150px, 1fr)); gap: 15px; padding: 20px; max-height: 600px; overflow-y: auto; background: #f8f9fa; border-radius: 8px;">
-            """)
-            
-            for i in range(10): 
-                html_parts.append(f"""
-                <div style="position: relative; border-radius: 8px; overflow: hidden; box-shadow: 0 2px 8px rgba(0,0,0,0.1); transition: transform 0.2s; cursor: pointer;" 
-                     onmouseover="this.style.transform='scale(1.05)'" 
-                     onmouseout="this.style.transform='scale(1)'">
-                    <div style="width: 100%; height: 200px; background: #ddd; display: flex; align-items: center; justify-content: center; color: #666; font-size: 12px;">
-                        Poster {i+1}
-                    </div>
-                    <div style="position: absolute; bottom: 0; left: 0; right: 0; background: linear-gradient(transparent, rgba(0,0,0,0.7)); color: white; padding: 8px; font-size: 12px; text-align: center;">
-                        Movie Title {i+1}
-                    </div>
-                </div>
-                """)
-            
-            html_parts.append("</div>")
-            return "".join(html_parts)
-            
-        except Exception as e:
-            return f"<div style='color: red; padding: 20px;'>❌ Error: {str(e)}</div>"
-        
-    with gr.Blocks(
-        theme=gr.themes.Soft(), 
-        title="TV-Series and Movie Recommend",
-        css="""
-        .gradio-container {
-            max-width: 1200px !important;
-        }
-        """
-    ) as demo:
-        gr.Markdown("# 🎬 TV-Series and Movie Recommend")
+            response_text = result[0] if isinstance(result, tuple) else str(result)
+            history.append([message, response_text])
 
-        with gr.Row():
-            with gr.Column(scale=1):
-                query_input = gr.Textbox(
-                    label="What you want to watch?",
-                    placeholder="Define your preferences as detailed as possible.",
-                    lines=3,
-                )
+            return history, "", thumbnails
 
-                search_btn = gr.Button("🔍 Search", variant="primary")
+        except Exception as e:
+            history.append([message, f"❌ Error: {str(e)}"])
+            return history, "", []
 
-            with gr.Column(scale=1):
-                results_text = gr.Textbox(
-                    label="Detailed Results",
-                    lines=20,
-                    max_lines=25,
-                    show_copy_button=True,
-                    interactive=False,
-                )
-                
-            with gr.Column(scale=1):
-                thumbnails_display = gr.HTML(
-                    label="Movie Posters",
-                    value="<div style='text-align: center; padding: 40px; color: #666;'>Movie thumbnails will appear here</div>"
-                )
+    with gr.Blocks() as demo:
+        with gr.Column():
+            chatbot = gr.Chatbot(height=600)
+            gallery = gr.Gallery(
+                label="Posters", show_label=False, columns=5, height=400
+            )
+            msg = gr.Textbox(placeholder="Enter your query", scale=1)
 
-        search_btn.click(
-            fn=get_recommendations_text,
-            inputs=[query_input],
-            outputs=[results_text],
-        )
-        
-        search_btn.click(
-            fn=get_thumbnails_from_results,
-            inputs=[query_input],
-            outputs=[thumbnails_display],
-        )
+        msg.submit(chat_function, [msg, chatbot], [chatbot, msg, gallery])
 
-    return demo
+    return demo

components/imdb_poster.py

@@ -0,0 +1,17 @@
+import requests
+from bs4 import BeautifulSoup
+
+
+def get_imdb_poster(imdb_id):
+    url = f"https://www.imdb.com/title/{imdb_id}/"
+    headers = {"User-Agent": "Mozilla/5.0"}
+    r = requests.get(url, headers=headers)
+    soup = BeautifulSoup(r.text, "html.parser")
+
+    poster_div = soup.find("div", class_="ipc-poster")
+    if poster_div:
+        img_tag = poster_div.find("img")
+        if img_tag and img_tag.get("src"):
+            return img_tag["src"]
+
+    return None

components/tmdb_api.py

@@ -1,54 +1,52 @@
 import requests
 from config import Config
 
+
 class TMDBApi:
     def __init__(self):
         self.config = Config()
         self.base_url = self.config.TMDB_BASE_URL
         self.api_key = self.config.TMDB_API_KEY
         self.image_base_url = self.config.TMDB_IMAGE_BASE_URL
-    
+
     def get_poster_by_imdb_id(self, imdb_id: str):
         try:
-            if not imdb_id.startswith('tt'):
+            if not imdb_id.startswith("tt"):
                 imdb_id = f"tt{imdb_id}"
-            
+
             endpoint = f"{self.base_url}/find/{imdb_id}"
-            params = {
-                "api_key": self.api_key,
-                "external_source": "tconst"
-            }
-            
+            params = {"api_key": self.api_key, "external_source": "tconst"}
+
             response = requests.get(endpoint, params=params)
             response.raise_for_status()
-            
+
             data = response.json()
-            
+
             poster_path = None
             if data.get("movie_results"):
                 poster_path = data["movie_results"][0].get("poster_path")
             elif data.get("tv_results"):
                 poster_path = data["tv_results"][0].get("poster_path")
-            
+
             if poster_path:
                 return f"{self.image_base_url}{poster_path}"
             return None
-            
+
         except Exception as e:
             print(f"❌ TMDB API Error for IMDB ID {imdb_id}: {str(e)}")
             return None
-    
+
     def get_multiple_posters_by_imdb(self, items: list):
         results = []
         for item in items:
-            imdb_id = item.get('tconst')
-            
+            imdb_id = item.get("tconst")
+
             if imdb_id:
                 poster_url = self.get_poster_by_imdb_id(imdb_id)
-                item['poster_url'] = poster_url
+                item["poster_url"] = poster_url
             else:
-                item['poster_url'] = None
-                
+                item["poster_url"] = None
+
             results.append(item)
-            
+
         return results

models/pydantic_schemas.py

@@ -16,7 +16,7 @@ class Features(BaseModel):
     themes: list[str] = Field(
         description="Actual thematic content (not quality descriptors)"
     )
-    date_range: list[int] = Field(description="Date range [min_year, max_year] (note: max_year is 2025)")
+    date_range: list[int] = Field(description="Date range [min_year, max_year] (note: min_year is 1900, max_year is 2025)")
     negative_keywords: list[str] = Field(description="List of negative keywords")
     production_region: list[str] = Field(description="Production region")
     min_rating: Optional[float] = Field(

models/recommendation_engine.py

@@ -8,6 +8,7 @@ from components.filters import MovieFilter
 from sentence_transformers import SentenceTransformer
 from components.tmdb_api import TMDBApi
 
+
 class RecommendationEngine:
     def __init__(self):
         self.config = Config()
@@ -36,16 +37,6 @@ class RecommendationEngine:
             search_results = self.similarity_calc.calculate_similarity(
                 features.themes, filtered_data, top_k
             )
-            if search_results["results"]:
-                    print(f"🔍 First result keys: {search_results['results'][0].keys()}")
-                    
-                    for i, result in enumerate(search_results["results"]):
-                        print(f"🔍 Result {i}: tconst = {result.get('tconst', 'NOT FOUND')}")
-                        
-                    search_results["results"] = self.tmdb_api.get_multiple_posters_by_imdb(
-                        search_results["results"]
-                    )
-
             formatted_results = self._format_results(search_results)
 
             return formatted_results, self._create_results_dataframe(search_results)
@@ -66,17 +57,13 @@ class RecommendationEngine:
                 ],
                 response_format=Features,
             )
-            
-            
+
             response_model = response.choices[0].message.parsed
 
             print(type(response_model))
             print(response_model.model_dump_json(indent=2))
-            print(f"✅ Parsed features: {response_model}")
             return response_model
-        
-        
-        
+
         except Exception as e:
             print(f"❌ Error parsing user query: {str(e)}")
             return Features(
@@ -125,6 +112,7 @@ class RecommendationEngine:
         for result in search_results["results"]:
             df_data.append(
                 {
+                    "ImdbId": result["tconst"],
                     "Title": result["title"],
                     "Type": result["type"],
                     "Year": result["year"],

tmdb_api.py

@@ -0,0 +1,54 @@
+import requests
+from config import Config
+
+class TMDBApi:
+    def __init__(self):
+        self.config = Config()
+        self.base_url = self.config.TMDB_BASE_URL
+        self.api_key = self.config.TMDB_API_KEY
+        self.image_base_url = self.config.TMDB_IMAGE_BASE_URL
+    
+    def get_poster_by_imdb_id(self, imdb_id: str):
+        try:
+            if not imdb_id.startswith('tt'):
+                imdb_id = f"tt{imdb_id}"
+            
+            endpoint = f"{self.base_url}/find/{imdb_id}"
+            params = {
+                "api_key": self.api_key,
+                "external_source": "tconst"
+            }
+            
+            response = requests.get(endpoint, params=params)
+            response.raise_for_status()
+            
+            data = response.json()
+            
+            poster_path = None
+            if data.get("movie_results"):
+                poster_path = data["movie_results"][0].get("poster_path")
+            elif data.get("tv_results"):
+                poster_path = data["tv_results"][0].get("poster_path")
+            
+            if poster_path:
+                return f"{self.image_base_url}{poster_path}"
+            return None
+            
+        except Exception as e:
+            print(f"❌ TMDB API Error for IMDB ID {imdb_id}: {str(e)}")
+            return None
+    
+    def get_multiple_posters_by_imdb(self, items: list):
+        results = []
+        for item in items:
+            imdb_id = item.get('tconst')
+            
+            if imdb_id:
+                poster_url = self.get_poster_by_imdb_id(imdb_id)
+                item['poster_url'] = poster_url
+            else:
+                item['poster_url'] = None
+                
+            results.append(item)
+            
+        return results