Cache expensive file processing results (PDF parsing, text extraction, image analysis) using SHA-256 content hashes as cache keys. Unlike path-based caching, this approach survives file moves/renames and auto-invalidates when content changes.
When to Activate
- Building file processing pipelines (PDF, images, text extraction)
- Processing cost is high and same files are processed repeatedly
- Need a
--cache/--no-cacheCLI option - Want to add caching to existing pure functions without modifying them
Core Pattern
1. Content-Hash Based Cache Key
Use file content (not path) as the cache key:
import hashlib
from pathlib import Path
_HASH_CHUNK_SIZE = 65536 # 64KB chunks for large files
def compute_file_hash(path: Path) -> str:
"""SHA-256 of file contents (chunked for large files)."""
if not path.is_file():
raise FileNotFoundError(f"File not found: {path}")
sha256 = hashlib.sha256()
with open(path, "rb") as f:
while True:
chunk = f.read(_HASH_CHUNK_SIZE)
if not chunk:
break
sha256.update(chunk)
return sha256.hexdigest()
Why content hash? File rename/move = cache hit. Content change = automatic invalidation. No index file needed.
2. Frozen Dataclass for Cache Entry
from dataclasses import dataclass
@dataclass(frozen=True, slots=True)
class CacheEntry:
file_hash: str
source_path: str
document: ExtractedDocument # The cached result
3. File-Based Cache Storage
Each cache entry is stored as {hash}.json — O(1) lookup by hash, no index file required.
import json
from typing import Any
Fingerprint Invalidation for LLM Caches (Batch 16, #46)
For LLM output caches the key is a fingerprint of prompt + rules + model
- context + result, not the user question alone. If ANY component changes, the fingerprint misses and the entry regenerates. Serving a stale hit is the worst failure: the model answers wrong with total confidence. Never cache the question text by itself.