Update rag.py

app/rag.py

@@ -3,20 +3,18 @@ import logging
 
 from llama_index.core import (
     SimpleDirectoryReader,
-    # VectorStoreIndex,
+    VectorStoreIndex,
     StorageContext,
     Settings,
     get_response_synthesizer)
-from llama_index.core.query_engine import RetrieverQueryEngine, TransformQueryEngine
+# from llama_index.core.query_engine import RetrieverQueryEngine, TransformQueryEngine
 from llama_index.core.node_parser import SentenceSplitter
 from llama_index.core.schema import TextNode, MetadataMode
-from llama_index.core.retrievers import VectorIndexRetriever
-# from llama_index.core.indices.query.query_transform import HyDEQueryTransform
+# from llama_index.core.retrievers import VectorIndexRetriever
 
-from llama_index.core.response_synthesizers import ResponseMode
+# from llama_index.core.response_synthesizers import ResponseMode
 # from transformers import AutoTokenizer
 from llama_index.core.vector_stores import VectorStoreQuery
-from llama_index.core.indices.vector_store.base import VectorStoreIndex
 from llama_index.vector_stores.qdrant import QdrantVectorStore
 from qdrant_client import QdrantClient
 
@@ -33,7 +31,8 @@ logger = logging.getLogger(__name__)
 class ChatPDF:
     query_engine = None
 
-    model_url = "https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat-GGUF/resolve/main/qwen1_5-1_8b-chat-q8_0.gguf"
+    model_url = "https://huggingface.co/Qwen/Qwen2-0.5B-Instruct-GGUF/resolve/main/qwen2-0_5b-instruct-fp16.gguf"
+    # model_url = "https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat-GGUF/resolve/main/qwen1_5-1_8b-chat-q8_0.gguf"
     # model_url = "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf/resolve/main/Phi-3-mini-4k-instruct-q4.gguf"
 
     # def messages_to_prompt(messages):
@@ -58,7 +57,7 @@ class ChatPDF:
 
 
     def __init__(self):
-        self.text_parser = SentenceSplitter(chunk_size=512, chunk_overlap=20)
+        self.text_parser = SentenceSplitter(chunk_size=128, chunk_overlap=8)
 
         logger.info("initializing the vector store related objects")
         # client = QdrantClient(host="localhost", port=6333)
@@ -154,10 +153,6 @@ class ChatPDF:
 
         self.query_engine = index.as_query_engine()
 
-        # logger.info("creating the HyDEQueryTransform instance")
-        # hyde = HyDEQueryTransform(include_original=True)
-        # self.hyde_query_engine = TransformQueryEngine(vector_query_engine, hyde)
-
     def ask(self, query: str):
         if not self.query_engine:
             return "Please, add a PDF document first."