Update app.py

app.py

@@ -1,6 +1,7 @@
 import nltk
 import os, json
-from dotenv import load_dotenv
+#from dotenv import load_dotenv
+
 nltk.download("punkt_tab")
 
 RETRIEVER = None
@@ -8,10 +9,29 @@ RETRIEVER = None
 import gradio as gr
 import nltk
 from typing import List
+from nltk.tokenize import sent_tokenize
+from dataclasses import dataclass
+import re
 
+from sentence_transformers import CrossEncoder
+from llama_index.retrievers.bm25 import BM25Retriever
+from llama_index.core.retrievers import QueryFusionRetriever
 
+from llama_index.core import Settings, VectorStoreIndex
+from llama_index.core.schema import TextNode
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from llama_index.llms.openai import OpenAI
 
-from dataclasses import dataclass
+
+
+
+Settings.embed_model = HuggingFaceEmbedding(model_name="sentence-transformers/all-MiniLM-L6-v2")
+
+
+Settings.llm = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"), base_url=os.environ.get("OPENAI_API_BASE"))
+
+# OPENAI_API_KEY = os.environ.get("API_KEY")
+# OPENAI_API_BASE = os.environ.get("API_BASE")
 
 @dataclass
 class Utterance:
@@ -52,7 +72,7 @@ def parse_webvtt(path: str) -> list[Utterance]:
 
 
 
-from nltk.tokenize import sent_tokenize
+
 
 def build_subchunks(
     utterances,
@@ -93,7 +113,7 @@ def build_subchunks(
     return subchunks
 
 
-import re
+
 
 TOPIC_RULES = {
     "gpu": ["gpu", "graphics card", "cuda", "vram", "nvidia"],
@@ -123,25 +143,9 @@ def tag_topics(text: str) -> list[str]:
     return list(tags)
 
 
-from llama_index.core import Settings, VectorStoreIndex
-from llama_index.core.schema import TextNode
-from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-from llama_index.llms.openai import OpenAI
 
-Settings.embed_model = HuggingFaceEmbedding(
-    model_name="sentence-transformers/all-MiniLM-L6-v2"
-)
 
 
-Settings.llm = OpenAI(
-    api_key= os.environ.get("OPENAI_API_KEY"),
-    base_url= os.environ.get("OPENAI_API_BASE")
-    
-)
-
-# OPENAI_API_KEY = os.environ.get("API_KEY")
-# OPENAI_API_BASE = os.environ.get("API_BASE")
-
 
 
 
@@ -162,8 +166,7 @@ def build_nodes(subchunks):
     return nodes
 
 
-from llama_index.retrievers.bm25 import BM25Retriever
-from llama_index.core.retrievers import QueryFusionRetriever
+
 
 def build_hybrid_retriever(nodes):
     index = VectorStoreIndex(nodes)
@@ -205,7 +208,7 @@ def infer_required_topics(q: str) -> set[str]:
     return req
 
 
-from sentence_transformers import CrossEncoder
+
 
 reranker = CrossEncoder("cross-encoder/ms-marco-MiniLM-L-6-v2")