fix

confluence_qa.py

@@ -12,8 +12,8 @@ class ConfluenceQA:
         self.embeddings = HuggingFaceEmbeddings(model_name="multi-qa-MiniLM-L6-cos-v1")
     
     def define_model(self) -> None:
-        tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
-        model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large")
+        tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl")
+        model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl")
         pipe = pipeline("text2text-generation", model=model, tokenizer=tokenizer,max_new_tokens=1024)
         self.llm = HuggingFacePipeline(pipeline = pipe,model_kwargs={"temperature": 0.5})
 
@@ -28,7 +28,7 @@ class ConfluenceQA:
             url=confluence_url, username=username, api_key=api_key
         )
         documents = loader.load(include_attachments=include_attachment, limit=100, space_key=space_key)
-        text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=10)
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
         documents = text_splitter.split_documents(documents)
         self.db = Chroma.from_documents(documents, self.embeddings)
         # question = "How do I make a space public?"