llmcachex-ai 0.1.1

Drop-in semantic + exact caching layer for LLM applications

🚀 llmcachex-ai

pip install llmcachex-ai

Drop-in caching + retrieval layer for LLM applications (RAG, agents, chatbots)

Stop paying for repeated LLM calls. Automatically reuse responses using exact + semantic caching with zero changes to your business logic.

---

⚡ Installation

pip install llmcachex-ai

---

✨ Why llmcachex-ai?

Most LLM applications repeatedly call the model for:

• Slightly rephrased questions
• Agent/tool loops
• Chat history variations

👉 This leads to higher latency + unnecessary cost

llmcachex-ai solves this automatically by caching intelligently.

---

🔥 Features

• ⚡ Exact cache (Redis-backed)
• 🧠 Semantic cache (FAISS + embeddings)
• 🔍 Hybrid retrieval (BM25 + vector search)
• 🧬 Cross-encoder reranking
• 🤖 Agent + tool compatible
• 🧵 Memory-aware context support
• 💰 Token + cost tracking
• 🧩 Plug-and-play decorator API

---

🏗️ How It Works

User Query
   ↓
llm_cache decorator
   ├── Exact Cache (Redis)
   ├── Semantic Engine
   │     ├── FAISS (vector)
   │     ├── BM25 (lexical)
   │     └── CrossEncoder (rerank)
   └── LLM / Agent

---

🚀 Quick Start

from llmcachex_ai import llm_cache, CacheConfig

@llm_cache(CacheConfig())
def ask_llm(prompt):
    return llm(prompt)

print(ask_llm("What is AI?"))      # LLM call
print(ask_llm("Explain AI"))       # Semantic cache hit

---

🤖 Agent Example

Works seamlessly with tools:

@llm_cache(CacheConfig())
def agent(raw_query, full_prompt):

    if "calculate" in raw_query:
        return str(eval(raw_query.replace("calculate", "").strip()))

    if "search" in raw_query:
        return f"[TOOL SEARCH RESULT] {raw_query}"

    return llm(full_prompt)

---

🧠 Semantic Cache (Why it’s powerful)

Unlike basic caching:

"What is AI?"
"Explain artificial intelligence"

👉 Both return the same cached response 👉 No LLM call needed

---

⚙️ Configuration

CacheConfig(
    enable_exact=True,
    enable_semantic=True,
    similarity_threshold=0.7,
    top_k=3,
    model_name="gpt-4o-mini",
    enable_metrics=True,
    enable_token_cost=True
)

---

📊 Metrics

from llmcachex_ai import metrics

print(metrics.summary())

Example output:

{
  "hits": 2,
  "misses": 1,
  "hit_rate": 66.67,
  "avg_llm_latency_ms": 2000,
  "avg_cache_latency_ms": 30,
  "total_cost_rupees": 0.01
}

---

📁 Project Structure

llm_cachex/
├── api/            # decorator layer
├── core/           # cache, metrics, memory
├── semantic/       # hybrid search + reranker
├── embedding/      # embeddings
├── index/          # FAISS index
├── similarity/     # similarity utils
├── utils/          # helpers

---

🧭 Roadmap

• Async support
• Streaming support
• Batch inference
• Multi-model caching
• Pluggable vector DBs (Chroma / Pinecone)
• Observability dashboard

---

🤝 Contributing

PRs welcome. Open an issue to discuss ideas.

---

📜 License

MIT License

---

👤 Author

Himanshu Singh

---

⭐ If this helps you

Give it a star ⭐ — it helps the project grow.