Remove local file ingestion tools

README.md

@@ -5,7 +5,7 @@ An MCP server exposing the LightRAG Server API as tools, resources, and prompts
 ## Features
 
 - Retrieval tools: `query_data`, `query`, `query_stream`, `query_stream_chunks`
-- Ingestion tools: `ingest_text`, `ingest_texts`, `ingest_file`, `ingest_files`, `upload_document`
+- Ingestion tools: `ingest_text`, `ingest_texts`, `upload_document`
 - Freshness tools: `scan_documents`, `scan_and_wait`, `pipeline_status`, `wait_for_idle`, `track_status`
 - Memory tool: `ingest_memory` for lessons, preferences, decisions, structures, functions, relationships
 - Graph tools: entity/relation CRUD, entity existence check, label search, graph export
@@ -52,4 +52,3 @@ lightrag-mcp-smoke --query "What is this project?" --format pretty
 - `query_stream` collects the streaming response and returns it as a single string.
 - `query_stream_chunks` returns chunked output and reports progress to clients that support progress events.
 - `refresh_and_query` is a convenience macro for evidence-first workflows.
-- `ingest_file(s)` chunk local files and store them with `file_source` references.

src/lightrag_mcp/server.py

@@ -3,7 +3,6 @@ from __future__ import annotations
 import asyncio
 import json
 import time
-from pathlib import Path
 from typing import Any, Iterable
 
 from mcp.server.fastmcp import Context, FastMCP
@@ -89,32 +88,6 @@ async def _wait_for_idle(timeout_s: float, interval_s: float) -> dict[str, Any]:
         await asyncio.sleep(interval_s)
 
 
-def _chunk_text(text: str, max_chars: int, overlap: int) -> list[str]:
-    if max_chars <= 0:
-        raise ValueError("max_chars must be > 0")
-    if overlap < 0 or overlap >= max_chars:
-        raise ValueError("overlap must be >= 0 and < max_chars")
-
-    chunks: list[str] = []
-    start = 0
-    length = len(text)
-    while start < length:
-        end = min(start + max_chars, length)
-        cut = text.rfind("\n", start, end)
-        if cut == -1 or cut <= start:
-            cut = end
-        chunk = text[start:cut].strip()
-        if chunk:
-            chunks.append(chunk)
-        if cut >= length:
-            break
-        next_start = max(cut - overlap, 0)
-        if next_start <= start:
-            next_start = cut
-        start = next_start
-    return chunks
-
-
 def _format_list(items: Iterable[str]) -> str:
     return ", ".join(item.strip() for item in items if item.strip())
 
@@ -359,45 +332,6 @@ async def ingest_texts(
     return await client.request_json("POST", "/documents/texts", json=payload)
 
 
-@mcp.tool()
-async def ingest_file(
-    path: str,
-    max_chars: int = 4000,
-    overlap: int = 200,
-    encoding: str = "utf-8",
-) -> dict[str, Any]:
-    """Read a local file, chunk it, and ingest as texts with file_sources set per chunk."""
-    file_path = Path(path)
-    if not file_path.exists():
-        raise FileNotFoundError(f"File not found: {file_path}")
-    text = file_path.read_text(encoding=encoding, errors="replace")
-    chunks = _chunk_text(text, max_chars=max_chars, overlap=overlap)
-    if not chunks:
-        raise ValueError(f"No content to ingest from {file_path}")
-    file_sources = [f"{file_path}#chunk:{idx + 1}/{len(chunks)}" for idx in range(len(chunks))]
-    payload: dict[str, Any] = {"texts": chunks, "file_sources": file_sources}
-    return await client.request_json("POST", "/documents/texts", json=payload)
-
-
-@mcp.tool()
-async def ingest_files(
-    paths: list[str],
-    max_chars: int = 4000,
-    overlap: int = 200,
-    encoding: str = "utf-8",
-) -> dict[str, Any]:
-    """Ingest multiple local files by chunking each file into texts."""
-    results: dict[str, Any] = {}
-    for path in paths:
-        results[path] = await ingest_file(
-            path=path,
-            max_chars=max_chars,
-            overlap=overlap,
-            encoding=encoding,
-        )
-    return {"results": results}
-
-
 @mcp.tool()
 async def upload_document(path: str) -> dict[str, Any]:
     """Upload a local file to the LightRAG input directory."""