Update app.py

app.py

@@ -72,7 +72,13 @@ class EmbeddingModel:
         # Embed the list of chunks
         return self.model.embed_documents(chunks)
 
-def process_files(model_name, split_strategy, chunk_size=500, overlap_size=50, max_tokens=None):
+def process_files(model_name, split_strategy, chunk_size, overlap_size, max_tokens):
+    print('-----mmm--------') 
+    print(model_name)
+    print(split_strategy)
+    print(overlap_size)
+    print(chunk_size)
+    print(max_tokens) 
     # File processing
     text = ""
     for file in os.listdir(FILES_DIR):
@@ -90,7 +96,7 @@ def process_files(model_name, split_strategy, chunk_size=500, overlap_size=50, m
     # Embed chunks, not the full text
     model = EmbeddingModel(MODELS[model_name], max_tokens=max_tokens)
     embeddings = model.embed(chunks)
-    
+    print(chunks)
     return embeddings, chunks
 
 def search_embeddings(query, model_name, top_k):
@@ -133,7 +139,15 @@ def upload_file(file, model_name, split_strategy, overlap_size,chunk_size,  max_
             overlap_size = int(overlap_size)  # Convert to int if valid
     except ValueError:
         return {"error": "Chunk size and overlap size must be valid integers."}
-        
+    print('-------------')
+    print(file.name)
+    print(model_name)
+    print(split_strategy)
+    print(overlap_size)
+    print(chunk_size)
+    print(max_tokens)
+    print(query)
+    print(top_k)
       
     # Handle file upload using Gradio file object
     file_path = file.name  # Get the file path from Gradio file object