langchain-performance-tuning

name	langchain-performance-tuning
description	Tune LangChain 1.0 / LangGraph 1.0 Python chains and agents for throughput, latency, and cost — streaming modes, explicit batch concurrency, semantic plus exact caches, persistent message history, and async-safe retriever patterns. Use when p95 latency exceeds target, batching "does not work", cost grows linearly with traffic, or a process restart wipes chat history. Trigger with "langchain performance", "langchain slow batch", "langchain throughput", "langchain p95 latency", "semantic cache hit rate".
allowed-tools	Read, Write, Edit, Bash(python:*), Bash(redis-cli:*)
version	2.5.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","langchain","langgraph","python","langchain-1.0","performance","caching","async"]
compatibility	Designed for Claude Code, also compatible with Codex

LangChain Performance Tuning

Overview

An engineer calls chain.batch(inputs_1000) expecting 1000 parallel LLM calls. Actual behavior: Runnable.batch and Runnable.abatch in LangChain 1.0 default to max_concurrency=1, so the 1000 inputs run sequentially with bookkeeping overhead — sometimes slower than a plain for loop. This is pain-catalog entry P08. The fix is one line:

# Before: serial, ~1000 * per_call_latency
await chain.abatch(inputs)

# After: 10x throughput at 10 providers' worth of concurrency
await chain.abatch(inputs, config={"max_concurrency": 10})

Other silent regressions in the same pain catalog: P48 (invoke inside async def blocks the FastAPI event loop), P22 (InMemoryChatMessageHistory loses every user's chat on restart), P62 (RedisSemanticCache at the default score_threshold=0.95 returns under 5% hit rate), P59 (async retrievers leak connections on cancellation), P60 (BackgroundTasks fires after the response — wrong for per-token SSE), P01 (streaming token counts are only reliable on the on_chat_model_end event).

This skill wires a production performance baseline: explicit batch concurrency, async-only code paths, Redis-backed caches tuned on a golden set, persistent chat history with TTL, and TTFT instrumentation from astream_events(version="v2").

Prerequisites

• Python 3.11+ with langchain>=1.0,<2, langgraph>=1.0,<2, langchain-openai or langchain-anthropic, langchain-community, langchain-redis or redis>=5.
• A working LangChain 1.0 chain or LangGraph 1.0 graph that already passes functional tests.
• Redis 7+ reachable from the app for cache and history (local Docker is fine for dev).
• A FastAPI / Starlette async endpoint, or an equivalent async entrypoint.
• Observability: a place to emit metrics (Prometheus, OpenTelemetry, or LangSmith) — needed to measure TTFT, p95, and cache hit rate.

Instructions