[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
Python aifaissgpt-osslangchainllama-indexllmlocalstorageoffline-firstollamaprivacypythonragretrieval-augmented-generationvector-databasevector-searchvectors
add reuse code
yichuan5200309103206fc57eb48e6b
diff --git a/examples/data_/BartoSutton.pdf b/examples/data_/BartoSutton.pdfdeleted file mode 100644index 9deb811..0000000Binary files a/examples/data_/BartoSutton.pdf and /dev/null differdiff --git a/examples/main_cli_example.py b/examples/main_cli_example.pyindex e89e1ee..a03035c 100644--- a/examples/main_cli_example.py+++ b/examples/main_cli_example.py@@ -72,6 +72,7 @@ async def main():chat = LeannChat(index_path=INDEX_PATH)query = "Based on the paper, what are the main techniques LEANN explores to reduce the storage overhead and DLPM explore to achieve Fairness and Efiiciency trade-off?"+ query = "What is the main idea of RL and give me 5 exapmle of classic RL algorithms?"print(f"You: {query}")chat_response = chat.ask(query, top_k=20, recompute_beighbor_embeddings=True)print(f"Leann: {chat_response}")diff --git a/examples/resue_index.py b/examples/resue_index.pynew file mode 100644index 0000000..6e7dbfc--- /dev/null+++ b/examples/resue_index.py@@ -0,0 +1,18 @@+import asyncio+from leann.api import LeannChat+from pathlib import Path++INDEX_DIR = Path("./test_pdf_index")+INDEX_PATH = str(INDEX_DIR / "pdf_documents.leann")++async def main():+ print(f"\n[PHASE 2] Starting Leann chat session...")+ chat = LeannChat(index_path=INDEX_PATH)+ query = "What is the main idea of RL and give me 5 exapmle of classic RL algorithms?"+ query = "Based on the paper, what are the main techniques LEANN explores to reduce the storage overhead and DLPM explore to achieve Fairness and Efiiciency trade-off?"++ response = chat.ask(query,top_k=20,recompute_beighbor_embeddings=True,complexity=64,beam_width=1)+ print(f"\n[PHASE 2] Response: {response}")++if __name__ == "__main__":+ asyncio.run(main())\ No newline at end of filediff --git a/packages/leann-core/src/leann/api.py b/packages/leann-core/src/leann/api.pyindex 48478bf..014264a 100644--- a/packages/leann-core/src/leann/api.py+++ b/packages/leann-core/src/leann/api.py@@ -217,7 +217,12 @@ class LeannChat:results = self.searcher.search(question, top_k=top_k, **kwargs)context = "\n\n".join([r.text for r in results])- prompt = f"Context:\n{context}\n\nQuestion: {question}\n\nAnswer:"+ prompt = (+ "Here is some retrieved context that might help answer your question:\n\n"+ f"{context}\n\n"+ f"Question: {question}\n\n"+ "Please provide the best answer you can based on this context and your knowledge."+ )print(f"DEBUG: Calling LLM with prompt: {prompt}...")try: