Initial commit

gacerioni · gacerioni · commit ddf6e9482bb1 · 2025-08-11T18:07:23.000-03:00
diff --git a/.env.EXAMPLE b/.env.EXAMPLE
@@ -0,0 +1,6 @@
+OPENAI_API_KEY=sk-proj-<...>
+OPENAI_MODEL=gpt-4o
+
+LANGCACHE_SERVICE_KEY=wy4ECQMIW<...>KKmDb
+LANGCACHE_CACHE_ID=eb438<...>
+LANGCACHE_BASE_URL=https://gcp-us-east4.langcache.redis.io
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,165 @@
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+.env
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
diff --git a/README.md b/README.md
@@ -0,0 +1,102 @@
+# Redis LangCache Demo
+
+A minimal Python demo showing how to use [Redis LangCache](https://redis.io/docs/latest/solutions/semantic-caching/langcache/) with OpenAI to implement semantic caching for LLM queries.  
+This example caches responses based on semantic similarity, reducing latency and API usage costs.
+
+---
+
+## 📂 Project Structure
+
+```
+.
+├── main.py              # Main script for running the demo
+├── requirements.txt     # Python dependencies
+├── .env.EXAMPLE         # Example environment variable configuration
+└── .env                 # Your actual environment variables (not committed)
+```
+
+---
+
+## 🚀 Prerequisites
+
+- Python **3.10+**
+- A Redis LangCache instance (Redis Cloud)
+- An OpenAI API key
+
+---
+
+## ⚙️ Setup
+
+1. **Clone this repository**
+   ```bash
+   git clone https://github.com/<your-repo>/gabs-redis-langcache.git
+   cd gabs-redis-langcache
+   ```
+
+2. **Create and activate a virtual environment**
+   ```bash
+   python3 -m venv .venv
+   source .venv/bin/activate  # Mac/Linux
+   .venv\Scripts\activate     # Windows
+   ```
+
+3. **Install dependencies**
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+4. **Configure environment variables**
+   - Copy `.env.EXAMPLE` to `.env`
+   - Fill in your credentials:
+     ```env
+     OPENAI_API_KEY=sk-proj-<your-openai-key>
+     OPENAI_MODEL=gpt-4o
+
+     LANGCACHE_SERVICE_KEY=<your-langcache-service-key>
+     LANGCACHE_CACHE_ID=<your-langcache-cache-id>
+     LANGCACHE_BASE_URL=https://gcp-us-east4.langcache.redis.io
+     ```
+
+---
+
+## ▶️ Usage
+
+Run the demo:
+
+```bash
+python main.py
+```
+
+Example interaction:
+
+```
+LangCache Semantic Cache Chat - Type 'exit' to quit.
+
+Ask something: What is Redis LangCache?
+[CACHE MISS]
+[Latency] Cache miss search took 0.023 seconds
+[Latency] OpenAI response took 0.882 seconds
+Response: Redis LangCache is a semantic caching solution...
+------------------------------------------------------------
+Ask something: Tell me about LangCache
+[CACHE HIT]
+[Latency] Cache hit in 0.002 seconds
+Response: Redis LangCache is a semantic caching solution...
+------------------------------------------------------------
+```
+
+---
+
+## 🧠 How It Works
+
+1. **Search** in Redis LangCache for a semantically similar question.
+2. If a **cache hit** is found (above the similarity threshold), return it instantly.
+3. If a **cache miss** occurs:
+   - Query OpenAI.
+   - Store the response in Redis LangCache for future reuse.
+
+---
+
+## 📄 License
+
+MIT
diff --git a/main.py b/main.py
@@ -0,0 +1,71 @@
+import os
+import time
+from dotenv import load_dotenv
+from openai import OpenAI
+from langcache import LangCache
+
+# === Load environment variables ===
+load_dotenv()
+
+# === LangCache Configuration ===
+LANGCACHE_SERVICE_KEY = os.getenv("LANGCACHE_SERVICE_KEY")
+LANGCACHE_CACHE_ID = os.getenv("LANGCACHE_CACHE_ID")
+LANGCACHE_BASE_URL = os.getenv("LANGCACHE_BASE_URL", "https://gcp-us-east4.langcache.redis.io")
+
+# === OpenAI Configuration ===
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+OPENAI_MODEL = os.getenv("OPENAI_MODEL", "gpt-4o")
+openai_client = OpenAI(api_key=OPENAI_API_KEY)
+
+
+def call_openai_llm(prompt: str) -> str:
+    try:
+        response = openai_client.chat.completions.create(
+            model=OPENAI_MODEL,
+            messages=[{"role": "user", "content": prompt}],
+            temperature=0.7
+        )
+        return response.choices[0].message.content.strip()
+    except Exception as e:
+        return f"[ERROR] OpenAI request failed: {e}"
+
+
+def main():
+    print("LangCache Semantic Cache Chat - Type 'exit' to quit.\n")
+
+    with LangCache(
+        server_url=LANGCACHE_BASE_URL,
+        cache_id=LANGCACHE_CACHE_ID,
+        service_key=LANGCACHE_SERVICE_KEY
+    ) as lang_cache:
+
+        while True:
+            query = input("Ask something: ").strip()
+            if query.lower() in {"exit", "quit"}:
+                break
+
+            start_time = time.perf_counter()
+            results = lang_cache.search(prompt=query, similarity_threshold=0.7)
+            elapsed_time = time.perf_counter() - start_time
+
+            if results and results.data:
+                print("[CACHE HIT]")
+                print(f"[Latency] Cache hit in {elapsed_time:.3f} seconds")
+                print("Response:", results.data[0].response)
+            else:
+                print("[CACHE MISS]")
+                print(f"[Latency] Cache miss search took {elapsed_time:.3f} seconds")
+
+                start_llm = time.perf_counter()
+                response = call_openai_llm(query)
+                lang_cache.set(prompt=query, response=response)
+                elapsed_llm = time.perf_counter() - start_llm
+
+                print(f"[Latency] OpenAI response took {elapsed_llm:.3f} seconds")
+                print("Response:", response)
+
+            print("-" * 60)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/requirements.txt b/requirements.txt
@@ -0,0 +1,22 @@
+annotated-types==0.7.0
+anyio==4.9.0
+certifi==2025.7.9
+charset-normalizer==3.4.2
+distro==1.9.0
+dotenv==0.9.9
+h11==0.16.0
+httpcore==1.0.9
+httpx==0.28.1
+idna==3.10
+jiter==0.10.0
+langcache==0.8.0
+openai==1.95.0
+pydantic==2.11.7
+pydantic_core==2.33.2
+python-dotenv==1.1.1
+requests==2.32.4
+sniffio==1.3.1
+tqdm==4.67.1
+typing-inspection==0.4.1
+typing_extensions==4.14.1
+urllib3==2.5.0
