From 1648ace1e6f2d6ebe9938a509527fe2755833dbc Mon Sep 17 00:00:00 2001
From: tiennm99 <tiennm99@outlook.com>
Date: Tue, 11 Mar 2025 19:21:44 +0700
Subject: [PATCH] feat: ask ATNVC data

---
 data/.gitignore |  2 ++
 main.py         | 32 +++++++++++++++++---------------
 2 files changed, 19 insertions(+), 15 deletions(-)
 create mode 100644 data/.gitignore

diff --git a/data/.gitignore b/data/.gitignore
new file mode 100644
index 0000000..c96a04f
--- /dev/null
+++ b/data/.gitignore
@@ -0,0 +1,2 @@
+*
+!.gitignore
\ No newline at end of file
diff --git a/main.py b/main.py
index 56f3b43..82d5c74 100644
--- a/main.py
+++ b/main.py
@@ -4,29 +4,32 @@ from haystack import Pipeline, Document
 from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
 from haystack.components.builders.prompt_builder import PromptBuilder
 from haystack.document_stores.in_memory import InMemoryDocumentStore
+import os
+import glob
 
-# Write documents to InMemoryDocumentStore
 document_store = InMemoryDocumentStore()
-document_store.write_documents([
-    Document(content="My name is Jean and I live in Paris."),
-    Document(content="My name is Mark and I live in Berlin."),
-    Document(content="My name is Giorgio and I live in Rome.")
-])
 
-# Build a RAG pipeline
+documents = []
+for txt_file in glob.glob("data/*.txt"):
+    with open(txt_file, 'r', encoding='utf-8') as f:
+        content = f.read()
+        documents.append(Document(content=content))
+
+document_store.write_documents(documents)
+
 prompt_template = """
-Given these documents, answer the question.
-Documents:
+Dựa trên những tài liệu sau, trả lời câu hỏi.
+Tài liệu:
 {% for doc in documents %}
     {{ doc.content }}
 {% endfor %}
-Question: {{question}}
-Answer:
+Câu hỏi: {{question}}
+Trả lời:
 """
 
 retriever = InMemoryBM25Retriever(document_store=document_store)
 prompt_builder = PromptBuilder(template=prompt_template)
-llm = OllamaGenerator(url = "http://localhost:11434", model="llama3.2:1b")
+llm = OllamaGenerator(url = "http://localhost:11434", model="qwen2.5")
 
 rag_pipeline = Pipeline()
 rag_pipeline.add_component("retriever", retriever)
@@ -35,8 +38,7 @@ rag_pipeline.add_component("llm", llm)
 rag_pipeline.connect("retriever", "prompt_builder.documents")
 rag_pipeline.connect("prompt_builder", "llm")
 
-# Ask a question
-question = "Who lives in Paris?"
+question = "Khan là ai?"
 results = rag_pipeline.run(
     {
         "retriever": {"query": question},
@@ -44,4 +46,4 @@ results = rag_pipeline.run(
     }
 )
 
-print(results["llm"]["replies"])
\ No newline at end of file
+print(results["llm"]["replies"])