entroplain 0.1.0 → 0.2.0

package/pyproject.toml

@@ -1,85 +1,96 @@
-[build-system]
-requires = ["setuptools>=61.0", "wheel"]
-build-backend = "setuptools.build_meta"
-
-[project]
-name = "entroplain"
-version = "0.1.0"
-description = "Entropy-based early exit for efficient agent reasoning"
-readme = "README.md"
-license = "MIT"
-authors = [
-    {name = "Entroplain Contributors"}
-]
-keywords = ["llm", "agent", "entropy", "early-exit", "efficiency", "reasoning"]
-classifiers = [
-    "Development Status :: 3 - Alpha",
-    "Intended Audience :: Developers",
-    "Intended Audience :: Science/Research",
-    "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.8",
-    "Programming Language :: Python :: 3.9",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Topic :: Scientific/Engineering :: Artificial Intelligence",
-    "Topic :: Software Development :: Libraries :: Python Modules",
-]
-requires-python = ">=3.8"
-dependencies = [
-    "typing-extensions>=4.0.0;python_version<'3.10'",
-]
-
-[project.optional-dependencies]
-openai = ["openai>=1.0.0"]
-anthropic = ["anthropic>=0.25.0"]
-google = ["google-generativeai>=0.3.0"]
-nvidia = ["requests>=2.28.0", "aiohttp>=3.8.0"]
-ollama = ["requests>=2.28.0", "aiohttp>=3.8.0"]
-llama-cpp = ["llama-cpp-python>=0.2.0"]
-all = [
-    "openai>=1.0.0",
-    "anthropic>=0.25.0",
-    "google-generativeai>=0.3.0",
-    "requests>=2.28.0",
-    "aiohttp>=3.8.0",
-    "llama-cpp-python>=0.2.0",
-]
-dev = [
-    "pytest>=7.0.0",
-    "pytest-asyncio>=0.21.0",
-    "black>=23.0.0",
-    "isort>=5.0.0",
-    "mypy>=1.0.0",
-]
-
-[project.urls]
-Homepage = "https://github.com/entroplain/entroplain"
-Documentation = "https://github.com/entroplain/entroplain#readme"
-Repository = "https://github.com/entroplain/entroplain.git"
-Issues = "https://github.com/entroplain/entroplain/issues"
-
-[project.scripts]
-entroplain = "entroplain.cli:main"
-
-[tool.setuptools.packages.find]
-where = ["."]
-include = ["entroplain*"]
-
-[tool.black]
-line-length = 100
-target-version = ["py38", "py39", "py310", "py311", "py312"]
-
-[tool.isort]
-profile = "black"
-line_length = 100
-
-[tool.mypy]
-python_version = "3.8"
-warn_return_any = true
-warn_unused_configs = true
-disallow_untyped_defs = true
-
-[tool.pytest.ini_options]
-asyncio_mode = "auto"
-testpaths = ["tests"]
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "entroplain"
+version = "0.2.0"
+description = "Entropy-based early exit for efficient agent reasoning"
+readme = "README.md"
+license = "MIT"
+authors = [
+    {name = "Entroplain Contributors"}
+]
+keywords = ["llm", "agent", "entropy", "early-exit", "efficiency", "reasoning"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+requires-python = ">=3.8"
+dependencies = [
+    "typing-extensions>=4.0.0;python_version<'3.10'",
+]
+
+[project.optional-dependencies]
+openai = ["openai>=1.0.0"]
+anthropic = ["anthropic>=0.25.0"]
+google = ["google-generativeai>=0.3.0"]
+nvidia = ["requests>=2.28.0", "aiohttp>=3.8.0"]
+ollama = ["requests>=2.28.0", "aiohttp>=3.8.0"]
+llama-cpp = ["llama-cpp-python>=0.2.0"]
+all = [
+    "openai>=1.0.0",
+    "anthropic>=0.25.0",
+    "google-generativeai>=0.3.0",
+    "requests>=2.28.0",
+    "aiohttp>=3.8.0",
+    "llama-cpp-python>=0.2.0",
+    "fastapi>=0.100.0",
+    "uvicorn>=0.23.0",
+    "httpx>=0.24.0",
+]
+
+proxy = [
+    "fastapi>=0.100.0",
+    "uvicorn>=0.23.0",
+    "httpx>=0.24.0",
+]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-asyncio>=0.21.0",
+    "black>=23.0.0",
+    "isort>=5.0.0",
+    "mypy>=1.0.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/entroplain/entroplain"
+Documentation = "https://github.com/entroplain/entroplain#readme"
+Repository = "https://github.com/entroplain/entroplain.git"
+Issues = "https://github.com/entroplain/entroplain/issues"
+
+[project.scripts]
+entroplain = "entroplain.cli:main"
+entroplain-proxy = "entroplain.proxy:main"
+entroplain-dashboard = "entroplain.dashboard:main"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["entroplain*"]
+
+[tool.black]
+line-length = 100
+target-version = ["py38", "py39", "py310", "py311", "py312"]
+
+[tool.isort]
+profile = "black"
+line_length = 100
+
+[tool.mypy]
+python_version = "3.8"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = true
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]

package/test_nvidia.py

@@ -0,0 +1,56 @@
+"""Test the proxy with NVIDIA API."""
+
+import requests
+import json
+import os
+
+# Get API key from environment
+api_key = os.environ.get("NVIDIA_API_KEY", "")
+
+if not api_key:
+    print("ERROR: NVIDIA_API_KEY not set")
+    exit(1)
+
+# Make request through proxy
+response = requests.post(
+    "http://localhost:8767/v1/chat/completions",
+    headers={
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {api_key}"
+    },
+    json={
+        "model": "meta/llama-3.1-70b-instruct",
+        "messages": [{"role": "user", "content": "What is 2+2? Just answer the number."}],
+        "max_tokens": 50,
+        "temperature": 0.1,
+        "stream": True
+    },
+    stream=True
+)
+
+print(f"Status: {response.status_code}")
+print("Streaming response:")
+print("-" * 40)
+
+for line in response.iter_lines():
+    if line:
+        line = line.decode('utf-8')
+        if line.startswith("data: "):
+            data = line[6:]
+            if data == "[DONE]":
+                print("\n[DONE]")
+                break
+            try:
+                chunk = json.loads(data)
+                if chunk.get("choices"):
+                    delta = chunk["choices"][0].get("delta", {})
+                    if delta.get("content"):
+                        print(delta["content"], end="", flush=True)
+            except json.JSONDecodeError:
+                pass
+
+print("\n" + "-" * 40)
+
+# Check proxy health
+health = requests.get("http://localhost:8767/health")
+print(f"\nProxy stats: {health.json()}")

package/test_proxy.py

@@ -0,0 +1,16 @@
+"""Test the proxy with a real API call."""
+
+import requests
+import json
+
+# Test health endpoint
+try:
+    response = requests.get("http://localhost:8765/health")
+    print(f"Health check: {response.status_code}")
+    print(response.json())
+except Exception as e:
+    print(f"Proxy not running: {e}")
+    print("\nTo test the proxy, run:")
+    print("  entroplain-proxy --port 8765")
+    print("\nThen in another terminal:")
+    print("  python test_proxy.py")