feat: Phase 1.1 project setup with config, database, and models

- Add requirements.txt with all dependencies
- Add .env.example with required environment variables
- Add Pydantic Settings (config.py) with .env loading
- Add ChromaDB persistent client (database.py)
- Add Pydantic schemas (ingest.py) for request/response
- Add FastAPI main.py with CORS middleware
- Add package __init__.py files
- Add tests: test_phase1_config.py, test_phase1_database.py
- All 5 tests pass

backend/.env.example

@@ -0,0 +1,6 @@
+LLM_BASE_URL=https://openrouter.ai/api/v1
+LLM_API_KEY=your_openrouter_key_here
+LLM_MODEL_NAME=qwen/qwen3.5-35b-a3b
+EMBEDDING_MODEL=qwen/qwen3-embedding-4b
+EMBEDDING_BASE_URL=https://openrouter.ai/api/v1
+CHROMA_DB_PATH=./chroma_db

backend/app/core/config.py

@@ -0,0 +1,20 @@
+from functools import lru_cache
+from pathlib import Path
+
+from pydantic_settings import BaseSettings
+
+
+class Settings(BaseSettings):
+    llm_base_url: str = "https://openrouter.ai/api/v1"
+    llm_api_key: str = ""
+    llm_model_name: str = "qwen/qwen3.5-35b-a3b"
+    embedding_model: str = "qwen/qwen3-embedding-4b"
+    embedding_base_url: str = "https://openrouter.ai/api/v1"
+    chroma_db_path: str = "./chroma_db"
+
+    model_config = {"env_file": ".env", "env_file_encoding": "utf-8"}
+
+
+@lru_cache
+def get_settings() -> Settings:
+    return Settings()

backend/app/core/database.py

@@ -0,0 +1,16 @@
+from pathlib import Path
+
+import chromadb
+
+from app.core.config import get_settings
+
+
+def get_chroma_client() -> chromadb.Client:
+    settings = get_settings()
+    persist_dir = Path(settings.chroma_db_path)
+    persist_dir.mkdir(parents=True, exist_ok=True)
+    return chromadb.PersistentClient(path=str(persist_dir))
+
+
+def get_or_create_collection(client: chromadb.Client, name: str):
+    return client.get_or_create_collection(name=name)

backend/app/main.py

@@ -0,0 +1,17 @@
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+
+app = FastAPI(title="RAG Video Q&A", version="1.0.0")
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["http://localhost:5173", "http://localhost:3000"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.get("/health")
+def health_check():
+    return {"status": "ok"}

backend/app/models/ingest.py

@@ -0,0 +1,27 @@
+from datetime import datetime
+from typing import List
+
+from pydantic import BaseModel
+
+
+class SourceMetadata(BaseModel):
+    filename: str
+    upload_date: datetime
+    content_summary: str
+    chunk_index: int
+
+
+class IngestResponse(BaseModel):
+    document_id: str
+    chunk_count: int
+    filename: str
+
+
+class QueryRequest(BaseModel):
+    question: str
+
+
+class QueryResponse(BaseModel):
+    keywords: List[str]
+    answer: str
+    sources: List[SourceMetadata]

backend/app/test/test_phase1_config.py

@@ -0,0 +1,33 @@
+import pytest
+import os
+from pathlib import Path
+
+
+def test_config_loads_from_env(tmp_path, monkeypatch):
+    env_file = tmp_path / ".env"
+    env_file.write_text(
+        "LLM_BASE_URL=https://openrouter.ai/api/v1\n"
+        "LLM_API_KEY=test_key_123\n"
+        "LLM_MODEL_NAME=qwen/qwen3.5-35b-a3b\n"
+        "EMBEDDING_MODEL=qwen/qwen3-embedding-4b\n"
+        "EMBEDDING_BASE_URL=https://openrouter.ai/api/v1\n"
+        "CHROMA_DB_PATH=./test_chroma\n"
+    )
+    
+    monkeypatch.chdir(tmp_path)
+    from app.core.config import Settings
+    
+    settings = Settings()
+    assert settings.llm_base_url == "https://openrouter.ai/api/v1"
+    assert settings.llm_api_key == "test_key_123"
+    assert settings.llm_model_name == "qwen/qwen3.5-35b-a3b"
+    assert settings.chroma_db_path == "./test_chroma"
+
+
+def test_config_default_values(monkeypatch):
+    monkeypatch.delenv("LLM_BASE_URL", raising=False)
+    from app.core.config import Settings
+    
+    settings = Settings()
+    assert settings.llm_base_url == "https://openrouter.ai/api/v1"
+    assert settings.llm_model_name == "qwen/qwen3.5-35b-a3b"

backend/app/test/test_phase1_database.py

@@ -0,0 +1,39 @@
+import pytest
+from pathlib import Path
+
+
+def test_chroma_client_creates_persist_directory(tmp_path):
+    import os
+    os.environ["CHROMA_DB_PATH"] = str(tmp_path / "test_chroma")
+    
+    from app.core.database import get_chroma_client
+    
+    client = get_chroma_client()
+    assert client is not None
+    assert (tmp_path / "test_chroma").exists()
+
+
+def test_chroma_client_creates_new_collection(tmp_path):
+    import os
+    os.environ["CHROMA_DB_PATH"] = str(tmp_path / "test_chroma")
+    
+    from app.core.database import get_chroma_client, get_or_create_collection
+    
+    client = get_chroma_client()
+    collection = get_or_create_collection(client, "test_docs")
+    assert collection.name == "test_docs"
+    assert collection.count() == 0
+
+
+def test_chroma_client_returns_existing_collection(tmp_path):
+    import os
+    os.environ["CHROMA_DB_PATH"] = str(tmp_path / "test_chroma")
+    
+    from app.core.database import get_chroma_client, get_or_create_collection
+    
+    client = get_chroma_client()
+    collection1 = get_or_create_collection(client, "test_docs")
+    collection1.add(documents=["test"], ids=["1"])
+    
+    collection2 = get_or_create_collection(client, "test_docs")
+    assert collection2.count() == 1

backend/requirements.txt

@@ -0,0 +1,14 @@
+fastapi==0.109.0
+uvicorn[standard]==0.27.0
+pydantic==2.5.3
+pydantic-settings==2.1.0
+chromadb==0.4.22
+sentence-transformers==2.3.1
+python-docx==1.1.0
+pypdf==4.0.2
+python-dotenv==1.0.0
+httpx==0.26.0
+pytest==8.0.0
+pytest-asyncio==0.23.4
+tiktoken==0.5.2
+python-multipart==0.0.6