Update app.py

app.py

@@ -68,14 +68,22 @@ def update_feedback_in_firestore(session_id, conversation_id, feedback):
     conv_doc.update({"feedback": feedback})
 
 class Config:
-    CHUNK_WORDS = 300
-    EMBEDDING_MODEL = "models/gemini-embedding-exp-03-07"
+    CHUNK_WORDS = 3000
+    # Use the unified Gemini text embedding model recommended in the docs:
+    # https://docs.cloud.google.com/vertex-ai/generative-ai/docs/embeddings/get-text-embeddings
+    # This model produces up to 3072-dimensional vectors.
+    EMBEDDING_MODEL = "models/gemini-embedding-001"
     TOP_N = 5
     SYSTEM_PROMPT = (
         "You are a helpful assistant. Answer the question using the provided context below. "
         "Answer based on your knowledge if the context given is not enough."
     )
-    GENERATION_MODEL = "models/gemini-2.5-flash-lite"
+    # Use a text-generation model that is available on the v1beta Generative Language API.
+    # If you want to confirm available models, run:
+    #   import google.generativeai as genai
+    #   for m in genai.list_models():
+    #       if "generateContent" in m.supported_generation_methods: print(m.name)
+    GENERATION_MODEL = "gemini-2.5-flash"
 
 API_KEY = os.getenv("GOOGLE_API_KEY")
 if not API_KEY:
@@ -98,19 +106,20 @@ def generate_embedding_cached(text: str) -> list:
         if "embedding" not in response or not response["embedding"]:
             logger.error("No embedding returned from API.")
             st.error("No embedding returned. Please verify your API settings and input text.")
-            return [0.0] * 768
+            # Fallback vector size should roughly match gemini-embedding-001 (3072 dims).
+            return [0.0] * 3072
         embedding = np.array(response["embedding"])
         if embedding.ndim == 2:
             embedding = embedding.flatten()
         elif embedding.ndim > 2:
             logger.error("Embedding has more than 2 dimensions.")
             st.error("Invalid embedding dimensions. Please check the API response.")
-            return [0.0] * 768
+            return [0.0] * 3072
         return embedding.tolist()
     except Exception as e:
         logger.error("Embedding generation failed: %s", e)
         st.error(f"Embedding generation failed: {e}")
-        return [0.0] * 768
+        return [0.0] * 3072
 
 def generate_embedding(text: str) -> np.ndarray:
     embedding_list = generate_embedding_cached(text)