Skip to content

armgit / LEANN

Public Imported from GitHub
0

[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.

Display context chunks in ask and search results (#149)

CelineNi2abf312d9983b
diff --git a/packages/leann-core/src/leann/api.py b/packages/leann-core/src/leann/api.py
index 112a541..c2f1d93 100644
--- a/packages/leann-core/src/leann/api.py
+++ b/packages/leann-core/src/leann/api.py
@@ -1236,6 +1236,17 @@ class LeannChat:
"Please provide the best answer you can based on this context and your knowledge."
)
+ print("The context provided to the LLM is:")
+ print(f"{'Relevance':<10} | {'Chunk id':<10} | {'Content':<60} | {'Source':<80}")
+ print("-" * 150)
+ for r in results:
+ chunk_relevance = f"{r.score:.3f}"
+ chunk_id = r.id
+ chunk_content = r.text[:60]
+ chunk_source = r.metadata.get("source", "")[:80]
+ print(
+ f"{chunk_relevance:<10} | {chunk_id:<10} | {chunk_content:<60} | {chunk_source:<80}"
+ )
ask_time = time.time()
ans = self.llm.ask(prompt, **llm_kwargs)
ask_time = time.time() - ask_time
diff --git a/packages/leann-core/src/leann/cli.py b/packages/leann-core/src/leann/cli.py
index 47ea88c..b7d6e48 100644
--- a/packages/leann-core/src/leann/cli.py
+++ b/packages/leann-core/src/leann/cli.py
@@ -1,5 +1,6 @@
import argparse
import asyncio
+import time
from pathlib import Path
from typing import Any, Optional, Union
@@ -1186,6 +1187,7 @@ Examples:
for doc in other_docs:
file_path = doc.metadata.get("file_path", "")
if file_filter(file_path):
+ doc.metadata["source"] = file_path
filtered_docs.append(doc)
documents.extend(filtered_docs)
@@ -1290,7 +1292,10 @@ Examples:
nodes = parser.get_nodes_from_documents([doc])
for node in nodes:
- all_texts.append(node.get_content())
+ text_with_source = (
+ "Chunk source:" + source_path + "\n" + node.get_content().replace("\n", " ")
+ )
+ all_texts.append(text_with_source)
print(f"Loaded {len(documents)} documents, {len(all_texts)} chunks")
return all_texts
@@ -1388,8 +1393,10 @@ Examples:
num_threads=args.num_threads,
)
- for chunk_text in all_texts:
- builder.add_text(chunk_text)
+ for chunk_text_with_source in all_texts:
+ chunk_source = chunk_text_with_source.split("\n")[0].split(":")[1]
+ chunk_text = chunk_text_with_source.split("\n")[1]
+ builder.add_text(chunk_text, {"source": chunk_source})
builder.build_index(index_path)
print(f"Index built at {index_path}")
@@ -1511,6 +1518,7 @@ Examples:
for i, result in enumerate(results, 1):
print(f"{i}. Score: {result.score:.3f}")
print(f" {result.text[:200]}...")
+ print(f" Source: {result.metadata.get('source', '')}")
print()
async def ask_questions(self, args):
@@ -1542,6 +1550,7 @@ Examples:
llm_kwargs["thinking_budget"] = args.thinking_budget
def _ask_once(prompt: str) -> None:
+ query_start_time = time.time()
response = chat.ask(
prompt,
top_k=args.top_k,
@@ -1552,7 +1561,9 @@ Examples:
pruning_strategy=args.pruning_strategy,
llm_kwargs=llm_kwargs,
)
+ query_completion_time = time.time() - query_start_time
print(f"LEANN: {response}")
+ print(f"The query took {query_completion_time:.3f} seconds to finish")
initial_query = (args.query or "").strip()