diff --git a/.env.example b/.env.example
new file mode 100644
index 0000000..69ac776
--- /dev/null
+++ b/.env.example
@@ -0,0 +1,28 @@
+# OpenAI API authentication (required)
+OPENAI_API_KEY=sk-...
+
+# Qdrant configuration
+QDRANT_URL=http://localhost:6333
+QDRANT_API_KEY=
+
+# Fixed models (not configurable per strategy)
+EMBEDDING_MODEL=text-embedding-3-small
+LLM_MODEL=gpt-4o-mini
+
+# Retrieval defaults
+TOP_K=5
+
+# LLM generation parameters
+TEMPERATURE=0.0
+MAX_TOKENS=1024
+
+# Chunking defaults
+CHUNK_SIZE=512
+CHUNK_OVERLAP=50
+
+# Semantic chunking parameters
+SEMANTIC_THRESHOLD=0.3
+SEMANTIC_MIN_CHUNK_SIZE=3
+
+# SQLite database path
+DATABASE_URL=sqlite:///./data/chunking_benchmark.db
\ No newline at end of file
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..0dd70ff
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,31 @@
+[build-system]
+requires = ["setuptools>=68.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "chunking-strategies-evaluation"
+version = "0.1.0"
+description = "Benchmarking application comparing chunking strategies on regulatory documents"
+requires-python = ">=3.11"
+dependencies = [
+    "fastapi>=0.109.0",
+    "uvicorn[standard]>=0.25.0",
+    "pydantic>=2.5.0",
+    "pydantic-settings>=2.1.0",
+    "python-docx>=1.0.0",
+    "openai>=1.6.0",
+    "qdrant-client>=1.7.0",
+    "tiktoken>=0.5.0",
+    "jinja2>=3.1.0",
+    "python-multipart>=0.0.6",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.4.0",
+    "pytest-asyncio>=0.23.0",
+    "httpx>=0.25.0",
+]
+
+[tool.setuptools.packages.find]
+where = ["src"]
\ No newline at end of file