first commti

.gitignore

@@ -0,0 +1,2 @@
+.idea/
+*.iml

app.py

@@ -0,0 +1,45 @@
+from datasets import load_dataset
+from ragatouille import RAGPretrainedModel
+import gradio as gr
+
+dataset=load_dataset("davidr70/menachot")
+documents = []
+document_ids = []
+metadatas = []
+for row in dataset['train']:
+    document_id = row['id']
+    if document_id not in document_ids:
+        document_ids.append(document_id)
+        documents.append(row['content'])
+        metadatas.append(row['metadata'])
+
+RAG = RAGPretrainedModel.from_pretrained("answerdotai/answerai-colbert-small-v1")
+
+index_path = RAG.index(
+    index_name="menachot_small_model",
+    collection=documents,
+    document_ids=document_ids,
+    document_metadatas=metadatas
+)
+
+
+def ask(question):
+    results = RAG.search(question)
+    full_result = ""
+    for result in results:
+        output = f"document_id: {result['document_id']}\nscore: {str(result['score'])}\nrank: {str(result['rank'])}\ntext: {result['content']}\n\n\n"
+        full_result += output
+    return full_result
+
+
+with gr.Blocks(title="Menachot Search") as demo:
+    gr.Markdown("# Menachot Search")
+    gr.Markdown("Search through the Menachot dataset using RAG")
+
+    question = gr.Textbox(label="Question", placeholder="Ask a question about Menachot...")
+    submit_btn = gr.Button("Search")
+    answer = gr.Textbox(label="Sources", lines=20)
+
+    submit_btn.click(fn=ask, inputs=question, outputs=answer)
+
+demo.launch()

requirements.txt

@@ -0,0 +1 @@
+ragatouille