From 5d1f4c9c2fa0f8e9d867c0c9d01c4b15a1c30d09 Mon Sep 17 00:00:00 2001
From: Abhiix0 <24r21a6778@mlrit.ac.in>
Date: Wed, 8 Jul 2026 13:57:15 +0530
Subject: [PATCH 01/10] Rag content

---
 src/spawn/templates/rag/__init__.py |   1 +
 src/spawn/templates/rag/content.py  | 340 ++++++++++++++++++++++++++++
 2 files changed, 341 insertions(+)
 create mode 100644 src/spawn/templates/rag/__init__.py
 create mode 100644 src/spawn/templates/rag/content.py

diff --git a/src/spawn/templates/rag/__init__.py b/src/spawn/templates/rag/__init__.py
new file mode 100644
index 0000000..49a0292
--- /dev/null
+++ b/src/spawn/templates/rag/__init__.py
@@ -0,0 +1 @@
+# RAG template
diff --git a/src/spawn/templates/rag/content.py b/src/spawn/templates/rag/content.py
new file mode 100644
index 0000000..5b36bed
--- /dev/null
+++ b/src/spawn/templates/rag/content.py
@@ -0,0 +1,340 @@
+INIT_CONTENT = ""
+
+# ─── Knowledge base ───────────────────────────────────────────────────────
+
+SAMPLE_KNOWLEDGE_CONTENT = """\
+# Spawn Knowledge Base
+
+## What is Spawn?
+
+Spawn is an intent-based project generator that helps developers create
+production-friendly project foundations in seconds. Instead of manually
+creating folders, installing dependencies, and configuring tools, developers
+run one command and get a complete, immediately runnable project.
+
+## Spawn Intents
+
+Spawn supports the following project intents:
+
+- Backend API: FastAPI, Flask, or Django with production structure
+- CLI Application: Typer, Click, or Argparse command-line tools
+- Automation Tool: Workflow-based automation with logging
+- AI Chatbot: Conversational AI with PydanticAI, OpenAI SDK, or LiteLLM
+- AI Agent: Tool-calling agents with PydanticAI or OpenAI Agents SDK
+- RAG System: Retrieval-Augmented Generation with LlamaIndex and ChromaDB
+
+## How Spawn Works
+
+Run `spawn create`, select your intent, choose your framework and provider,
+pick any extras (ruff, pytest, github-actions), and Spawn generates the full
+project structure, installs dependencies via uv, and shows you the exact
+commands to run next. The entire setup takes under 30 seconds.
+
+## RAG System Intent
+
+The RAG System intent (added in v0.8.0) generates a complete
+Retrieval-Augmented Generation application using LlamaIndex and ChromaDB.
+It ingests documents from the data/ directory, creates embeddings using
+OpenAI's text-embedding-3-small model, stores them in a local ChromaDB
+vector database, and answers questions using retrieved context. On first
+run the ingestion step is triggered automatically before the Q&A loop starts.
+
+## Version History
+
+- v0.6.0: Initial release with Backend API, CLI Application, Automation Tool,
+  and AI Chatbot intents.
+- v0.7.0: Added AI Agent intent with PydanticAI and OpenAI Agents SDK support,
+  plus Groq provider across all AI intents.
+- v0.8.0: Added RAG System intent with LlamaIndex, ChromaDB, and OpenAI.
+"""
+
+# ─── Config ───────────────────────────────────────────────────────────────
+
+SETTINGS_CONTENT = """\
+import os
+from pathlib import Path
+
+from dotenv import load_dotenv
+from llama_index.core import Settings
+from llama_index.embeddings.openai import OpenAIEmbedding
+from llama_index.llms.openai import OpenAI
+
+
+def load_env() -> None:
+    load_dotenv()
+
+
+def configure_llm() -> None:
+    api_key = os.getenv("OPENAI_API_KEY", "")
+    model = os.getenv("OPENAI_MODEL", "gpt-4o-mini")
+    Settings.llm = OpenAI(model=model, api_key=api_key)
+    Settings.embed_model = OpenAIEmbedding(
+        model="text-embedding-3-small",
+        api_key=api_key,
+    )
+"""
+
+# ─── Knowledge index ──────────────────────────────────────────────────────
+
+KNOWLEDGE_INDEX_CONTENT = """\
+from pathlib import Path
+
+import chromadb
+from llama_index.core import StorageContext
+from llama_index.vector_stores.chroma import ChromaVectorStore
+
+CHROMA_PATH = Path("chroma_db")
+COLLECTION_NAME = "{project_name}"
+
+
+def get_vector_store() -> ChromaVectorStore:
+    client = chromadb.PersistentClient(path=str(CHROMA_PATH))
+    collection = client.get_or_create_collection(COLLECTION_NAME)
+    return ChromaVectorStore(chroma_collection=collection)
+
+
+def get_storage_context() -> StorageContext:
+    return StorageContext.from_defaults(vector_store=get_vector_store())
+
+
+def index_exists() -> bool:
+    if not CHROMA_PATH.exists():
+        return False
+    return any(CHROMA_PATH.iterdir())
+"""
+
+# ─── Ingestion ────────────────────────────────────────────────────────────
+
+INGESTION_CONTENT = """\
+from pathlib import Path
+
+from llama_index.core import SimpleDirectoryReader, VectorStoreIndex
+
+from src.knowledge.index import get_storage_context
+
+DATA_PATH = Path("data")
+
+
+def ingest_documents() -> VectorStoreIndex:
+    print("Ingesting documents from data/...")
+    documents = SimpleDirectoryReader(
+        input_dir=str(DATA_PATH),
+        required_exts=[".txt", ".md"],
+        recursive=True,
+    ).load_data()
+    print(f"Loaded {{len(documents)}} document(s).")
+    storage_context = get_storage_context()
+    index = VectorStoreIndex.from_documents(
+        documents,
+        storage_context=storage_context,
+        show_progress=True,
+    )
+    print("Ingestion complete. Index stored in chroma_db/")
+    return index
+"""
+
+# ─── Retrieval ────────────────────────────────────────────────────────────
+
+RETRIEVAL_CONTENT = """\
+from llama_index.core import VectorStoreIndex
+
+from src.knowledge.index import get_storage_context, get_vector_store
+
+
+def load_index() -> VectorStoreIndex:
+    vector_store = get_vector_store()
+    storage_context = get_storage_context()
+    return VectorStoreIndex.from_vector_store(
+        vector_store,
+        storage_context=storage_context,
+    )
+
+
+def answer_question(question: str) -> str:
+    index = load_index()
+    query_engine = index.as_query_engine(
+        similarity_top_k=3,
+    )
+    response = query_engine.query(question)
+    return str(response)
+"""
+
+# ─── Main ─────────────────────────────────────────────────────────────────
+
+MAIN_CONTENT = """\
+from src.config.settings import configure_llm, load_env
+from src.ingestion.ingest import ingest_documents
+from src.knowledge.index import index_exists
+from src.retrieval.retrieve import answer_question
+
+
+def main() -> None:
+    load_env()
+    configure_llm()
+    print("{project_name} RAG System")
+    print("-" * 40)
+    if not index_exists():
+        print("No index found. Running ingestion...\\n")
+        ingest_documents()
+        print()
+    print("Ask a question (or type 'quit' to exit):\\n")
+    while True:
+        question = input("You: ").strip()
+        if not question:
+            continue
+        if question.lower() in ("quit", "exit"):
+            break
+        answer = answer_question(question)
+        print(f"\\nAnswer: {{answer}}\\n")
+
+
+if __name__ == "__main__":
+    main()
+"""
+
+# ─── Tests ────────────────────────────────────────────────────────────────
+
+CONFTEST_CONTENT = """\
+# conftest.py — shared test fixtures for RAG tests
+"""
+
+TEST_CONTENT = """\
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+
+def test_index_exists_false_when_no_dir(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    from src.knowledge.index import index_exists
+    assert not index_exists()
+
+
+def test_index_exists_false_when_empty_dir(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    (tmp_path / "chroma_db").mkdir()
+    from src.knowledge.index import index_exists
+    assert not index_exists()
+
+
+def test_index_exists_true_when_has_file(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    chroma = tmp_path / "chroma_db"
+    chroma.mkdir()
+    (chroma / "chroma.sqlite3").write_text("db")
+    from src.knowledge.index import index_exists
+    assert index_exists()
+
+
+def test_sample_knowledge_file_exists():
+    data_path = Path("data") / "sample_knowledge.md"
+    assert data_path.exists(), "data/sample_knowledge.md must exist"
+
+
+def test_answer_question_mock():
+    mock_engine = MagicMock()
+    mock_engine.query.return_value = "Spawn is a project generator."
+    mock_index = MagicMock()
+    mock_index.as_query_engine.return_value = mock_engine
+
+    with patch("src.retrieval.retrieve.load_index", return_value=mock_index):
+        from src.retrieval.retrieve import answer_question
+        result = answer_question("What is Spawn?")
+
+    assert isinstance(result, str)
+    assert len(result) > 0
+"""
+
+# ─── Env ──────────────────────────────────────────────────────────────────
+
+ENV_CONTENT = """\
+APP_NAME={project_name}
+OPENAI_API_KEY=
+OPENAI_MODEL=gpt-4o-mini
+"""
+
+# ─── README ───────────────────────────────────────────────────────────────
+
+
+def make_readme() -> str:
+    return (
+        "# {project_name}\n\n"
+        "A RAG system generated with Spawn using LlamaIndex and ChromaDB.\n\n"
+        "## Getting Started\n\n"
+        "1. Rename `.env.example` to `.env`\n\n"
+        "2. Add your `OPENAI_API_KEY` to `.env`:\n\n"
+        "```env\n"
+        "OPENAI_API_KEY=your-key\n"
+        "```\n\n"
+        "3. (Optional) Add your own `.txt` or `.md` files to `data/`\n\n"
+        "4. Run the RAG system:\n\n"
+        "```bash\n"
+        "uv run python -m src.main\n"
+        "```\n\n"
+        "On first run, documents in `data/` are automatically ingested.\n"
+        "Then ask questions about your knowledge base.\n\n"
+        "## Example\n\n"
+        "```\n"
+        "You: What is Spawn?\n"
+        "Answer: Spawn is an intent-based project generator...\n"
+        "```\n\n"
+        "## Adding Knowledge\n\n"
+        "Drop `.txt` or `.md` files into `data/` and delete `chroma_db/` to re-index:\n\n"
+        "```bash\n"
+        "rm -rf chroma_db/\n"
+        "uv run python -m src.main\n"
+        "```\n\n"
+        "## Project Structure\n\n"
+        "```\n"
+        "{project_name}/\n"
+        "├── data/                  # Knowledge documents\n"
+        "│   └── sample_knowledge.md\n"
+        "├── src/\n"
+        "│   ├── config/            # Settings and LLM configuration\n"
+        "│   ├── knowledge/         # ChromaDB index management\n"
+        "│   ├── ingestion/         # Document ingestion pipeline\n"
+        "│   ├── retrieval/         # Query engine and retrieval\n"
+        "│   └── main.py\n"
+        "├── tests/\n"
+        "├── chroma_db/             # Created on first run\n"
+        "├── .env.example\n"
+        "└── README.md\n"
+        "```\n\n"
+        "## Running Tests\n\n"
+        "```bash\n"
+        "uv run pytest\n"
+        "```\n"
+    )
+
+# ─── GitHub Actions ───────────────────────────────────────────────────────
+
+GITHUB_ACTIONS_CI_BASE = """\
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  ci:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: astral-sh/setup-uv@v5
+
+      - name: Install dependencies
+        run: uv sync
+"""
+
+GITHUB_ACTIONS_CI_RUFF_STEP = """\
+      - name: Lint
+        run: uv run ruff check .
+"""
+
+GITHUB_ACTIONS_CI_PYTEST_STEP = """\
+      - name: Test
+        run: uv run pytest
+"""

From fd63e81c6eb86001cc9226b3a2fc3315b8ad82fa Mon Sep 17 00:00:00 2001
From: Abhiix0 <24r21a6778@mlrit.ac.in>
Date: Wed, 8 Jul 2026 14:00:51 +0530
Subject: [PATCH 02/10]  RAGTemplate class

---
 src/spawn/templates/rag/__init__.py   | 113 +++++++++++++++++++++++++-
 src/spawn/templates/shared_content.py |   4 +
 2 files changed, 116 insertions(+), 1 deletion(-)

diff --git a/src/spawn/templates/rag/__init__.py b/src/spawn/templates/rag/__init__.py
index 49a0292..78f1a9e 100644
--- a/src/spawn/templates/rag/__init__.py
+++ b/src/spawn/templates/rag/__init__.py
@@ -1 +1,112 @@
-# RAG template
+from pathlib import Path
+
+from spawn.templates.base import BaseTemplate
+from spawn.templates.rag.content import (
+    INIT_CONTENT,
+    SAMPLE_KNOWLEDGE_CONTENT,
+    SETTINGS_CONTENT,
+    KNOWLEDGE_INDEX_CONTENT,
+    INGESTION_CONTENT,
+    RETRIEVAL_CONTENT,
+    MAIN_CONTENT,
+    TEST_CONTENT,
+    CONFTEST_CONTENT,
+    ENV_CONTENT,
+    GITHUB_ACTIONS_CI_BASE,
+    GITHUB_ACTIONS_CI_RUFF_STEP,
+    GITHUB_ACTIONS_CI_PYTEST_STEP,
+    make_readme,
+)
+
+RAG_FOLDERS = [
+    "data",
+    "chroma_db",
+    "src/ingestion",
+    "src/retrieval",
+    "src/knowledge",
+    "src/config",
+    "tests",
+]
+
+
+def _build_files() -> list:
+    return [
+        ("data/sample_knowledge.md",      SAMPLE_KNOWLEDGE_CONTENT),
+        ("src/__init__.py",               INIT_CONTENT),
+        ("src/config/__init__.py",        INIT_CONTENT),
+        ("src/config/settings.py",        SETTINGS_CONTENT),
+        ("src/knowledge/__init__.py",     INIT_CONTENT),
+        ("src/knowledge/index.py",        KNOWLEDGE_INDEX_CONTENT),
+        ("src/ingestion/__init__.py",     INIT_CONTENT),
+        ("src/ingestion/ingest.py",       INGESTION_CONTENT),
+        ("src/retrieval/__init__.py",     INIT_CONTENT),
+        ("src/retrieval/retrieve.py",     RETRIEVAL_CONTENT),
+        ("src/main.py",                   MAIN_CONTENT),
+        ("tests/__init__.py",             INIT_CONTENT),
+        ("tests/conftest.py",             CONFTEST_CONTENT),
+        ("tests/test_rag.py",             TEST_CONTENT),
+        (".env.example",                  ENV_CONTENT),
+    ]
+
+
+class RAGTemplate(BaseTemplate):
+    def __init__(self, extras: list[str] | None = None) -> None:
+        self.extras = extras or []
+
+        super().__init__(
+            name="RAG System",
+            folders=list(RAG_FOLDERS),
+            starter_files=_build_files(),
+            next_steps=[
+                "cd {project_name}",
+                "Rename .env.example to .env and add your OPENAI_API_KEY",
+                "uv run python -m src.main",
+            ],
+        )
+
+    def get_readme_content(self, context: dict) -> str | None:
+        return make_readme().format_map(context)
+
+    def get_dependencies(self) -> list[str]:
+        base = [
+            "llama-index-core",
+            "llama-index-vector-stores-chroma",
+            "llama-index-embeddings-openai",
+            "llama-index-llms-openai",
+            "chromadb",
+            "python-dotenv",
+        ]
+        if "pytest" in self.extras:
+            base.append("pytest")
+        if "ruff" in self.extras:
+            base.append("ruff")
+        return base
+
+    def post_install(self, project_path: Path) -> None:
+        pyproject = project_path / "pyproject.toml"
+        current   = pyproject.read_text(encoding="utf-8")
+        additions = ""
+
+        if "pytest" in self.extras:
+            additions += "\n[tool.pytest.ini_options]\ntestpaths = [\"tests\"]\n"
+
+        if "ruff" in self.extras:
+            additions += "\n[tool.ruff]\nline-length = 88\n"
+
+        if additions:
+            pyproject.write_text(current + additions, encoding="utf-8")
+
+        if "github-actions" in self.extras:
+            workflows_path = project_path / ".github" / "workflows"
+            workflows_path.mkdir(parents=True, exist_ok=True)
+            ci = GITHUB_ACTIONS_CI_BASE
+            if "ruff" in self.extras:
+                ci += GITHUB_ACTIONS_CI_RUFF_STEP
+            if "pytest" in self.extras:
+                ci += GITHUB_ACTIONS_CI_PYTEST_STEP
+            (workflows_path / "ci.yml").write_text(ci, encoding="utf-8")
+
+        # Write .gitkeep into chroma_db/ so git tracks the directory
+        # but the actual DB files are gitignored
+        gitkeep = project_path / "chroma_db" / ".gitkeep"
+        gitkeep.write_text("", encoding="utf-8")
diff --git a/src/spawn/templates/shared_content.py b/src/spawn/templates/shared_content.py
index 89ab95c..e843d50 100644
--- a/src/spawn/templates/shared_content.py
+++ b/src/spawn/templates/shared_content.py
@@ -50,4 +50,8 @@
 
 # Logs
 logs/*.log
+
+# ChromaDB vector store (regenerate with: delete chroma_db/ and re-run)
+chroma_db/
+!chroma_db/.gitkeep
 """

From 7cb5d4e7a4782d66b62577f8ef026a0e334fe80e Mon Sep 17 00:00:00 2001
From: Abhiix0 <24r21a6778@mlrit.ac.in>
Date: Wed, 8 Jul 2026 14:04:56 +0530
Subject: [PATCH 03/10] Registry + Version Bump

---
 pyproject.toml                | 2 +-
 src/spawn/__init__.py         | 2 +-
 src/spawn/core/registry.py    | 8 ++++++++
 tests/test_agent_generator.py | 2 +-
 tests/test_registry.py        | 2 +-
 uv.lock                       | 2 +-
 6 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index e79f9ea..1ca9457 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "spawn"
-version = "0.7.0"
+version = "0.8.0"
 description = "Spawn a ready-to-use Python project in seconds"
 readme = "README.md"
 requires-python = ">=3.12"
diff --git a/src/spawn/__init__.py b/src/spawn/__init__.py
index d20f58e..d7e5a6c 100644
--- a/src/spawn/__init__.py
+++ b/src/spawn/__init__.py
@@ -3,4 +3,4 @@
 try:
     __version__ = version("spawn")
 except PackageNotFoundError:
-    __version__ = "0.7.0"
+    __version__ = "0.8.0"
diff --git a/src/spawn/core/registry.py b/src/spawn/core/registry.py
index 1e775c8..fc32cdd 100644
--- a/src/spawn/core/registry.py
+++ b/src/spawn/core/registry.py
@@ -11,6 +11,7 @@
 from spawn.templates.automation import AutomationTemplate
 from spawn.templates.chatbot import ChatbotTemplate
 from spawn.templates.agent import AgentTemplate
+from spawn.templates.rag import RAGTemplate
 from spawn.templates.base import BaseTemplate
 
 
@@ -74,6 +75,13 @@ class TemplateMetadata:
         available_providers=["openai", "anthropic", "gemini", "openrouter", "ollama", "groq"],
         available_extras=["ruff", "pytest", "github-actions"],
     ),
+    "rag": TemplateMetadata(
+        slug="rag",
+        display_name="RAG System",
+        description="Retrieval-Augmented Generation with LlamaIndex and ChromaDB",
+        template_class=RAGTemplate,
+        available_extras=["ruff", "pytest", "github-actions"],
+    ),
 }
 
 
diff --git a/tests/test_agent_generator.py b/tests/test_agent_generator.py
index 785eba6..55b93ad 100644
--- a/tests/test_agent_generator.py
+++ b/tests/test_agent_generator.py
@@ -173,7 +173,7 @@ def test_agent_meta_json_has_correct_intent(tmp_path, monkeypatch):
     assert meta["intent"] == "agent"
     assert meta["framework"] == "pydantic-ai"
     assert meta["provider"] == "openai"
-    assert meta["spawn_version"] == "0.7.0"
+    assert meta["spawn_version"] == "0.8.0"
 
 
 def test_agent_meta_json_openai_agents(tmp_path, monkeypatch):
diff --git a/tests/test_registry.py b/tests/test_registry.py
index 86c9734..53dde72 100644
--- a/tests/test_registry.py
+++ b/tests/test_registry.py
@@ -25,7 +25,7 @@ def test_list_templates_returns_all():
     assert "cli" in slugs
     assert "automation" in slugs
     assert "chatbot" in slugs
-    assert len(slugs) == 5
+    assert len(slugs) == 6
 
 
 def test_get_metadata_returns_none_for_unknown():
diff --git a/uv.lock b/uv.lock
index c1bfbaa..7ad066d 100644
--- a/uv.lock
+++ b/uv.lock
@@ -142,7 +142,7 @@ wheels = [
 
 [[package]]
 name = "spawn"
-version = "0.7.0"
+version = "0.8.0"
 source = { editable = "." }
 dependencies = [
     { name = "rich" },

From d8bf36354256b997a9df77d1c7d246a0a37bb9ea Mon Sep 17 00:00:00 2001
From: Abhiix0 <24r21a6778@mlrit.ac.in>
Date: Wed, 8 Jul 2026 14:15:11 +0530
Subject: [PATCH 04/10] New tests for Rag

---
 tests/test_rag_generator.py | 193 ++++++++++++++++++++++++++
 tests/test_rag_template.py  | 268 ++++++++++++++++++++++++++++++++++++
 tests/test_registry.py      |  18 +++
 3 files changed, 479 insertions(+)
 create mode 100644 tests/test_rag_generator.py
 create mode 100644 tests/test_rag_template.py

diff --git a/tests/test_rag_generator.py b/tests/test_rag_generator.py
new file mode 100644
index 0000000..7875dff
--- /dev/null
+++ b/tests/test_rag_generator.py
@@ -0,0 +1,193 @@
+import json
+from contextlib import contextmanager
+from unittest.mock import patch
+
+from spawn.core.models import ProjectConfig
+from spawn.generators.project_generator import ProjectGenerator
+from spawn.templates.rag import RAGTemplate
+
+
+def _cfg(
+    name: str = "my-rag",
+    extras: list[str] | None = None,
+) -> ProjectConfig:
+    return ProjectConfig(
+        name=name,
+        template="rag",
+        use_git=False,
+        extras=extras or [],
+    )
+
+
+@contextmanager
+def _mock_uv_and_install():
+    with patch("spawn.generators.project_generator.install_packages"), \
+         patch("spawn.generators.project_generator.initialize_uv"), \
+         patch.object(RAGTemplate, "post_install"):
+        yield
+
+
+# ─── Structure ───────────────────────────────────────────────────────────
+
+
+def test_rag_creates_root(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag").is_dir()
+
+
+def test_rag_creates_data_dir(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag" / "data").is_dir()
+
+
+def test_rag_creates_chroma_dir(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag" / "chroma_db").is_dir()
+
+
+def test_rag_creates_knowledge_dir(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag" / "src" / "knowledge").is_dir()
+
+
+def test_rag_creates_ingestion_dir(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag" / "src" / "ingestion").is_dir()
+
+
+def test_rag_creates_retrieval_dir(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag" / "src" / "retrieval").is_dir()
+
+
+# ─── Files ───────────────────────────────────────────────────────────────
+
+
+def test_rag_creates_sample_knowledge(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag" / "data" / "sample_knowledge.md").exists()
+
+
+def test_rag_creates_index_py(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag" / "src" / "knowledge" / "index.py").exists()
+
+
+def test_rag_creates_ingest_py(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag" / "src" / "ingestion" / "ingest.py").exists()
+
+
+def test_rag_creates_retrieve_py(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag" / "src" / "retrieval" / "retrieve.py").exists()
+
+
+def test_rag_creates_main(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag" / "src" / "main.py").exists()
+
+
+def test_rag_creates_test_file(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag" / "tests" / "test_rag.py").exists()
+
+
+def test_rag_creates_env_example(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    assert (tmp_path / "my-rag" / ".env.example").exists()
+
+
+# ─── Content ─────────────────────────────────────────────────────────────
+
+
+def test_rag_readme_has_project_name(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg(name="my-knowledge-base"))
+    readme = (tmp_path / "my-knowledge-base" / "README.md").read_text(encoding="utf-8")
+    assert "my-knowledge-base" in readme
+
+
+def test_rag_env_has_openai_key(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    env = (tmp_path / "my-rag" / ".env.example").read_text(encoding="utf-8")
+    assert "OPENAI_API_KEY" in env
+
+
+def test_rag_gitignore_has_chroma(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    gitignore = (tmp_path / "my-rag" / ".gitignore").read_text(encoding="utf-8")
+    assert "chroma_db/" in gitignore
+
+
+def test_rag_sample_knowledge_contains_spawn(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    knowledge = (tmp_path / "my-rag" / "data" / "sample_knowledge.md").read_text(
+        encoding="utf-8"
+    )
+    assert "Spawn" in knowledge
+
+
+# ─── meta.json ───────────────────────────────────────────────────────────
+
+
+def test_rag_meta_json(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with _mock_uv_and_install():
+        ProjectGenerator().generate(_cfg())
+    meta = json.loads(
+        (tmp_path / "my-rag" / ".spawn" / "meta.json").read_text(encoding="utf-8")
+    )
+    assert meta["intent"] == "rag"
+    assert meta["framework"] is None
+    assert meta["provider"] is None
+    assert meta["spawn_version"] == "0.8.0"
+
+
+# ─── Dependencies ────────────────────────────────────────────────────────
+
+
+def test_rag_install_packages_called_with_correct_deps(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    with patch("spawn.generators.project_generator.install_packages") as mock_install, \
+         patch("spawn.generators.project_generator.initialize_uv"), \
+         patch.object(RAGTemplate, "post_install"):
+        ProjectGenerator().generate(_cfg())
+    args = mock_install.call_args[0][1]
+    assert "llama-index-core" in args
+    assert "chromadb" in args
+    assert "llama-index-embeddings-openai" in args
+    assert "python-dotenv" in args
diff --git a/tests/test_rag_template.py b/tests/test_rag_template.py
new file mode 100644
index 0000000..1e155a5
--- /dev/null
+++ b/tests/test_rag_template.py
@@ -0,0 +1,268 @@
+import os
+import py_compile
+import re
+import tempfile
+
+import pytest
+
+from spawn.templates.rag import RAGTemplate
+
+# ─── Basic instantiation ──────────────────────────────────────────────────
+
+
+def test_rag_template_name():
+    t = RAGTemplate()
+    assert t.name == "RAG System"
+
+
+def test_rag_template_no_framework():
+    t = RAGTemplate()
+    assert not hasattr(t, "framework") or getattr(t, "framework", None) is None
+
+
+def test_rag_template_default_extras():
+    t = RAGTemplate()
+    assert t.extras == []
+
+
+# ─── Folders ─────────────────────────────────────────────────────────────
+
+
+def test_rag_folders_complete():
+    t = RAGTemplate()
+    for required in [
+        "data", "chroma_db", "src/ingestion",
+        "src/retrieval", "src/knowledge", "src/config", "tests",
+    ]:
+        assert required in t.folders, f"Missing folder: {required}"
+
+
+# ─── Files ───────────────────────────────────────────────────────────────
+
+REQUIRED_FILES = [
+    "data/sample_knowledge.md",
+    "src/__init__.py",
+    "src/config/settings.py",
+    "src/knowledge/index.py",
+    "src/ingestion/ingest.py",
+    "src/retrieval/retrieve.py",
+    "src/main.py",
+    "tests/conftest.py",
+    "tests/test_rag.py",
+    ".env.example",
+]
+
+
+def test_rag_required_files():
+    t = RAGTemplate()
+    paths = [p for p, _ in t.starter_files]
+    for f in REQUIRED_FILES:
+        assert f in paths, f"Missing file: {f}"
+
+
+def test_rag_has_no_utils_dir():
+    t = RAGTemplate()
+    assert "src/utils" not in t.folders
+
+
+# ─── Content checks ──────────────────────────────────────────────────────
+
+
+def test_settings_configures_openai_embedding():
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    settings = files["src/config/settings.py"]
+    assert "OpenAIEmbedding" in settings
+    assert "text-embedding-3-small" in settings
+
+
+def test_settings_configures_llm():
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    settings = files["src/config/settings.py"]
+    assert "Settings.llm" in settings
+    assert "Settings.embed_model" in settings
+
+
+def test_knowledge_index_uses_persistent_client():
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    index = files["src/knowledge/index.py"]
+    assert "PersistentClient" in index
+    assert "chroma_db" in index
+
+
+def test_knowledge_index_has_exists_check():
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    index = files["src/knowledge/index.py"]
+    assert "index_exists" in index
+
+
+def test_ingestion_loads_txt_and_md():
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    ingest = files["src/ingestion/ingest.py"]
+    assert ".txt" in ingest
+    assert ".md" in ingest
+
+
+def test_ingestion_uses_vector_store_index():
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    ingest = files["src/ingestion/ingest.py"]
+    assert "VectorStoreIndex" in ingest
+
+
+def test_retrieval_uses_query_engine():
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    retrieve = files["src/retrieval/retrieve.py"]
+    assert "as_query_engine" in retrieve
+    assert "similarity_top_k" in retrieve
+
+
+def test_main_auto_ingests_on_first_run():
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    main = files["src/main.py"]
+    assert "index_exists" in main
+    assert "ingest_documents" in main
+
+
+def test_env_has_openai_key():
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    env = files[".env.example"].format_map({"project_name": "test"})
+    assert "OPENAI_API_KEY" in env
+    assert "OPENAI_MODEL" in env
+
+
+def test_sample_knowledge_mentions_spawn():
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    knowledge = files["data/sample_knowledge.md"]
+    assert "Spawn" in knowledge
+    assert len(knowledge) > 100
+
+
+# ─── Compile checks ──────────────────────────────────────────────────────
+
+PYTHON_FILES = [
+    "src/config/settings.py",
+    "src/knowledge/index.py",
+    "src/ingestion/ingest.py",
+    "src/retrieval/retrieve.py",
+    "src/main.py",
+    "tests/test_rag.py",
+]
+
+
+@pytest.mark.parametrize("filepath", PYTHON_FILES)
+def test_file_is_valid_python(filepath):
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    content = files[filepath].format_map({"project_name": "test-rag"})
+    with tempfile.NamedTemporaryFile(
+        mode="w", suffix=".py", delete=False, encoding="utf-8"
+    ) as f:
+        f.write(content)
+        fname = f.name
+    try:
+        py_compile.compile(fname, doraise=True)
+    except py_compile.PyCompileError as e:
+        raise AssertionError(f"{filepath} is not valid Python: {e}") from e
+    finally:
+        os.unlink(fname)
+
+
+@pytest.mark.parametrize("filepath", PYTHON_FILES)
+def test_no_unescaped_braces(filepath):
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    content = files[filepath]
+    singles = re.findall(r"(?<!\{)\{(?!\{)([^}]*)\}(?!\})", content)
+    bad = [s for s in singles if s != "project_name"]
+    assert not bad, f"{filepath} has unescaped braces: {bad}"
+
+
+# ─── Dependencies ────────────────────────────────────────────────────────
+
+
+def test_rag_core_dependencies():
+    t = RAGTemplate()
+    deps = t.get_dependencies()
+    for required in [
+        "llama-index-core",
+        "llama-index-vector-stores-chroma",
+        "llama-index-embeddings-openai",
+        "llama-index-llms-openai",
+        "chromadb",
+        "python-dotenv",
+    ]:
+        assert required in deps, f"Missing dep: {required}"
+
+
+def test_rag_no_framework_deps_by_default():
+    t = RAGTemplate()
+    deps = t.get_dependencies()
+    assert "llama-index" not in deps   # meta-package, too heavy
+    assert "openai" not in deps        # pulled transitively by llama-index-llms-openai
+
+
+def test_rag_pytest_extra():
+    t = RAGTemplate(extras=["pytest"])
+    assert "pytest" in t.get_dependencies()
+
+
+def test_rag_ruff_extra():
+    t = RAGTemplate(extras=["ruff"])
+    assert "ruff" in t.get_dependencies()
+
+
+# ─── Readme ──────────────────────────────────────────────────────────────
+
+
+def test_rag_readme_contains_project_name():
+    t = RAGTemplate()
+    readme = t.get_readme_content({"project_name": "my-rag"})
+    assert readme is not None
+    assert "my-rag" in readme
+
+
+def test_rag_readme_has_openai_key_instruction():
+    t = RAGTemplate()
+    readme = t.get_readme_content({"project_name": "x"})
+    assert "OPENAI_API_KEY" in readme
+
+
+def test_rag_readme_explains_re_indexing():
+    t = RAGTemplate()
+    readme = t.get_readme_content({"project_name": "x"})
+    assert "chroma_db" in readme
+
+
+# ─── next_steps ──────────────────────────────────────────────────────────
+
+
+def test_rag_next_steps_has_rename():
+    t = RAGTemplate()
+    assert any("Rename" in s for s in t.next_steps)
+
+
+def test_rag_next_steps_has_run():
+    t = RAGTemplate()
+    assert any("src.main" in s for s in t.next_steps)
+
+
+# ─── gitignore ───────────────────────────────────────────────────────────
+
+
+def test_gitignore_excludes_chroma_db():
+    from spawn.templates.shared_content import GITIGNORE_CONTENT
+    assert "chroma_db/" in GITIGNORE_CONTENT
+
+
+def test_gitignore_keeps_gitkeep():
+    from spawn.templates.shared_content import GITIGNORE_CONTENT
+    assert "!chroma_db/.gitkeep" in GITIGNORE_CONTENT
diff --git a/tests/test_registry.py b/tests/test_registry.py
index 53dde72..f873a32 100644
--- a/tests/test_registry.py
+++ b/tests/test_registry.py
@@ -166,3 +166,21 @@ def test_agent_metadata():
     assert meta.display_name == "AI Agent"
     assert "pydantic-ai" in meta.available_frameworks
     assert "openai-agents" in meta.available_frameworks
+
+
+def test_rag_is_registered():
+    from spawn.templates.rag import RAGTemplate
+    t = get_template("rag")
+    assert t is not None
+    assert isinstance(t, RAGTemplate)
+
+
+def test_rag_metadata():
+    meta = get_metadata("rag")
+    assert meta is not None
+    assert meta.slug == "rag"
+    assert meta.display_name == "RAG System"
+    assert not meta.available_frameworks
+    assert not meta.available_providers
+    assert "ruff" in meta.available_extras
+    assert "pytest" in meta.available_extras

From a75f1b550e54cea68f9aa1773c4b629301b7a6b9 Mon Sep 17 00:00:00 2001
From: Abhiix0 <24r21a6778@mlrit.ac.in>
Date: Wed, 8 Jul 2026 20:25:54 +0530
Subject: [PATCH 05/10] Polish: Readme

---
 README.md | 127 +++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 120 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index 2e93773..8e3ea2a 100644
--- a/README.md
+++ b/README.md
@@ -37,7 +37,7 @@ It's repetitive. It's inconsistent. And you haven't written a single line of *re
 
 | Feature | What it does |
 |---|---|
-| **Intent-based templates** | Backend API (FastAPI / Flask / Django), CLI Application (Typer / Click / Argparse), Automation Tool, AI Chatbot |
+| **Intent-based templates** | Backend API (FastAPI / Flask / Django), CLI Application (Typer / Click / Argparse), Automation Tool, AI Chatbot, AI Agent, RAG System |
 | **Extras system** | Opt-in ruff, pytest, Docker, GitHub Actions — installed and wired automatically |
 | **Dependency installation** | `uv add` runs automatically with the right packages for your choices |
 | **Git + uv** | Optionally runs `git init`, `uv init`, and `uv venv` |
@@ -92,8 +92,10 @@ Spawn rejects names with spaces or special characters, and tells you immediately
   2  CLI Application
   3  Automation Tool
   4  AI Chatbot
+  5  AI Agent
+  6  RAG System
 
-Choose Template [1-4]: 1
+Choose Template [1-6]: 1
 ```
 
 **Step 3 — Additional prompts** *(template-dependent)*
@@ -284,7 +286,8 @@ my-chatbot/
 │   ├── chatbot/
 │   ├── providers/
 │   ├── prompts/
-│   ├── utils/
+│   ├── memory/
+│   ├── config/
 │   └── main.py
 ├── tests/
 ├── .env.example
@@ -293,10 +296,120 @@ my-chatbot/
 
 ```bash
 cd my-chatbot
-# Add API_KEY to .env
+# Add API key to .env
+uv run python -m src.main
+```
+
+**AI Chatbot — Framework and provider**
+
+```
+  1  pydantic-ai
+  2  openai-sdk
+  3  litellm
+
+Choose Framework [1-3]: 1
+
+  1  openai
+  2  anthropic
+  3  gemini
+  4  openrouter
+  5  ollama
+  6  groq
+
+Choose Provider [1-6]: 1
+```
+
+---
+
+### `[5]` AI Agent
+
+Best for: task automation, research assistants, tool-calling workflows.
+
+```
+my-agent/
+├── src/
+│   ├── agent/
+│   ├── tools/
+│   ├── prompts/
+│   ├── config/
+│   └── main.py
+├── tests/
+├── .env.example
+└── README.md
+```
+
+```bash
+cd my-agent
+# Add API key to .env
 uv run python -m src.main
 ```
 
+**AI Agent — Framework and provider**
+
+```
+  1  pydantic-ai
+  2  openai-agents
+
+Choose Framework [1-2]: 1
+
+  1  openai
+  2  anthropic
+  3  gemini
+  4  openrouter
+  5  ollama
+  6  groq
+
+Choose Provider [1-6]: 1
+```
+
+Note: if you pick `openai-agents`, only `openai` and `openrouter` appear as provider choices — the list is filtered per framework.
+
+Every generated AI Agent project ships with one working tool (a calculator) so you can see tool-calling work immediately, with no external services or extra API keys required beyond your chosen provider.
+
+---
+
+### `[6]` RAG System
+
+Best for: documentation Q&A, knowledge base search, document retrieval.
+
+```
+my-rag/
+├── data/
+│   └── sample_knowledge.md
+├── src/
+│   ├── knowledge/
+│   ├── ingestion/
+│   ├── retrieval/
+│   ├── config/
+│   └── main.py
+├── tests/
+├── chroma_db/        # created on first run
+├── .env.example
+└── README.md
+```
+
+```bash
+cd my-rag
+# Add OPENAI_API_KEY to .env
+uv run python -m src.main
+# Documents are ingested automatically on first run
+```
+
+**RAG System — Extras only, no framework/provider prompt**
+
+```
+  1  ruff
+  2  pytest
+  3  github-actions
+
+  Enter numbers separated by commas, or press Enter to skip
+Extras []: 1,2
+```
+
+RAG System uses a fixed stack (LlamaIndex + ChromaDB + OpenAI) — there's no framework or provider choice. On first run, it automatically ingests documents from `data/` into a local ChromaDB index, then lets you ask questions against them.
+
+Requires an `OPENAI_API_KEY` (used for both the LLM and embeddings).
+
 ---
 
 ## Other Commands
@@ -341,7 +454,7 @@ spawn doctor ./path/to/project
 
 ```bash
 spawn version
-# → Spawn v0.6.0
+# → Spawn v0.8.0
 ```
 
 ### Publish to GitHub
@@ -378,8 +491,8 @@ All tests should pass. If they don't, please [open an issue](https://github.com/
 - [x] **CLI Application intent** — Typer, Click, Argparse with Utility/Interactive sub-types (v0.4.0)
 - [x] **Automation Tool intent** — workflow-based automation with logging, tasks, and integrations (v0.5.0)
 - [x] **AI Chatbot intent** — PydanticAI and OpenAI SDK with provider abstraction (v0.6.0)
-- [ ] **AI Agent intent** — tool-calling agent scaffold (v0.7.0)
-- [ ] **RAG System intent** — retrieval-augmented generation scaffold (v0.8.0)
+- [x] **AI Agent intent** — tool-calling agent scaffold with PydanticAI and OpenAI Agents SDK (v0.7.0)
+- [x] **RAG System intent** — retrieval-augmented generation with LlamaIndex and ChromaDB (v0.8.0)
 - [ ] **Data Project intent** — analysis, dashboard, ETL, ML sub-options (v0.9.0)
 
 ---

From ff081b003bbcdfceab78bff06017194a1f2ad25a Mon Sep 17 00:00:00 2001
From: Abhiix0 <24r21a6778@mlrit.ac.in>
Date: Wed, 8 Jul 2026 20:35:23 +0530
Subject: [PATCH 06/10] Update: Changelog

---
 docs/changelog.md | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/docs/changelog.md b/docs/changelog.md
index 062824a..b1b0428 100644
--- a/docs/changelog.md
+++ b/docs/changelog.md
@@ -3,6 +3,41 @@
 All notable changes to Spawn are documented here.
 Format follows [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
+## v0.8.0 — 2026
+
+### New Features
+
+- **RAG System intent** — generates a fully runnable Retrieval-Augmented Generation
+  project using a fixed stack: LlamaIndex + ChromaDB + OpenAI
+- **Fixed stack, no framework/provider prompt** — RAG skips the framework/provider
+  selection entirely; `spawn create` goes straight from intent to extras
+- **Auto-ingestion on first run** — if `chroma_db/` is empty, `src/main.py` ingests
+  everything in `data/` automatically before accepting questions; no separate ingest
+  command required
+- **Sample knowledge base** — every generated project ships with
+  `data/sample_knowledge.md` so users get a working Q&A demo immediately, with zero
+  setup beyond an API key
+- **Local vector persistence** — `src/knowledge/index.py` owns a
+  `chromadb.PersistentClient` writing to `chroma_db/`, shared by both ingestion and
+  retrieval
+- **Correct modern LlamaIndex packaging** — installs `llama-index-core`,
+  `llama-index-vector-stores-chroma`, `llama-index-embeddings-openai`,
+  `llama-index-llms-openai`, and `chromadb` explicitly, instead of the heavy
+  `llama-index` meta-package
+- **`chroma_db/` gitignored correctly** — binary ChromaDB files are excluded via
+  `.gitignore`, while a `.gitkeep` keeps the directory tracked in git
+
+### Internal
+
+- Registry: `rag` slug added with `available_extras` only — no `available_frameworks`
+  or `available_providers`
+- `RAGTemplate` follows the same `BaseTemplate` contract as other intents
+  (`get_dependencies()`, `get_readme_content()`, `post_install()`, `next_steps`)
+- `prompts.py` required no changes — empty `available_frameworks` and
+  `available_providers` already skip those prompts automatically
+- `shared_content.py`'s `GITIGNORE_CONTENT` extended with a `chroma_db/` rule
+- Version bumped to `0.8.0`
+
 ## v0.7.0 — 2026
 
 ### New Features

From cce4e25827bc7d8febe4f5731ca0d8042f019879 Mon Sep 17 00:00:00 2001
From: Abhiix0 <24r21a6778@mlrit.ac.in>
Date: Thu, 9 Jul 2026 20:23:56 +0530
Subject: [PATCH 07/10]  Python traceback ERROR

---
 src/spawn/templates/rag/content.py | 75 ++++++++++++++++++++++++++++--
 1 file changed, 71 insertions(+), 4 deletions(-)

diff --git a/src/spawn/templates/rag/content.py b/src/spawn/templates/rag/content.py
index 5b36bed..21c5582 100644
--- a/src/spawn/templates/rag/content.py
+++ b/src/spawn/templates/rag/content.py
@@ -137,6 +137,7 @@ def ingest_documents() -> VectorStoreIndex:
 
 RETRIEVAL_CONTENT = """\
 from llama_index.core import VectorStoreIndex
+from openai import APIError, AuthenticationError, RateLimitError
 
 from src.knowledge.index import get_storage_context, get_vector_store
 
@@ -155,7 +156,23 @@ def answer_question(question: str) -> str:
     query_engine = index.as_query_engine(
         similarity_top_k=3,
     )
-    response = query_engine.query(question)
+    try:
+        response = query_engine.query(question)
+    except AuthenticationError:
+        raise RuntimeError(
+            "OpenAI rejected your API key. Check OPENAI_API_KEY in .env."
+        ) from None
+    except RateLimitError as e:
+        if "insufficient_quota" in str(e):
+            raise RuntimeError(
+                "Your OpenAI account has no available quota/credits. "
+                "Check billing at https://platform.openai.com/settings/organization/billing"
+            ) from None
+        raise RuntimeError(
+            "OpenAI rate limit hit. Wait a moment and try again."
+        ) from None
+    except APIError as e:
+        raise RuntimeError(f"OpenAI API error: {{e}}") from None
     return str(response)
 """
 
@@ -175,7 +192,11 @@ def main() -> None:
     print("-" * 40)
     if not index_exists():
         print("No index found. Running ingestion...\\n")
-        ingest_documents()
+        try:
+            ingest_documents()
+        except RuntimeError as e:
+            print(f"\\n[Error] {{e}}\\n")
+            return
         print()
     print("Ask a question (or type 'quit' to exit):\\n")
     while True:
@@ -184,8 +205,12 @@ def main() -> None:
             continue
         if question.lower() in ("quit", "exit"):
             break
-        answer = answer_question(question)
-        print(f"\\nAnswer: {{answer}}\\n")
+        try:
+            answer = answer_question(question)
+            print(f"\\nAnswer: {{answer}}\\n")
+        except RuntimeError as e:
+            print(f"\\n[Error] {{e}}\\n")
+            continue
 
 
 if __name__ == "__main__":
@@ -242,6 +267,48 @@ def test_answer_question_mock():
 
     assert isinstance(result, str)
     assert len(result) > 0
+
+
+def test_answer_question_rate_limit_raises_runtime_error():
+    from openai import RateLimitError
+
+    mock_engine = MagicMock()
+    mock_response = MagicMock()
+    mock_response.status_code = 429
+    mock_engine.query.side_effect = RateLimitError(
+        "insufficient_quota", response=mock_response, body=None
+    )
+    mock_index = MagicMock()
+    mock_index.as_query_engine.return_value = mock_engine
+
+    with patch("src.retrieval.retrieve.load_index", return_value=mock_index):
+        from src.retrieval.retrieve import answer_question
+        try:
+            answer_question("What is Spawn?")
+            assert False, "Expected RuntimeError"
+        except RuntimeError as e:
+            assert "quota" in str(e).lower() or "rate limit" in str(e).lower()
+
+
+def test_answer_question_api_error_raises_runtime_error():
+    from openai import APIError
+
+    mock_engine = MagicMock()
+    mock_response = MagicMock()
+    mock_response.status_code = 500
+    mock_engine.query.side_effect = APIError(
+        "server error", response=mock_response, body=None
+    )
+    mock_index = MagicMock()
+    mock_index.as_query_engine.return_value = mock_engine
+
+    with patch("src.retrieval.retrieve.load_index", return_value=mock_index):
+        from src.retrieval.retrieve import answer_question
+        try:
+            answer_question("What is Spawn?")
+            assert False, "Expected RuntimeError"
+        except RuntimeError as e:
+            assert "OpenAI API error" in str(e)
 """
 
 # ─── Env ──────────────────────────────────────────────────────────────────

From 16c24e53c0a94508dcf89dae8fefd921cf543cac Mon Sep 17 00:00:00 2001
From: Abhiix0 <24r21a6778@mlrit.ac.in>
Date: Thu, 9 Jul 2026 22:06:39 +0530
Subject: [PATCH 08/10] Sanitize ChromaDB collection name

---
 src/spawn/templates/rag/content.py | 14 +++++++-
 tests/test_rag_template.py         | 53 ++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+), 1 deletion(-)

diff --git a/src/spawn/templates/rag/content.py b/src/spawn/templates/rag/content.py
index 21c5582..3767b61 100644
--- a/src/spawn/templates/rag/content.py
+++ b/src/spawn/templates/rag/content.py
@@ -77,14 +77,26 @@ def configure_llm() -> None:
 # ─── Knowledge index ──────────────────────────────────────────────────────
 
 KNOWLEDGE_INDEX_CONTENT = """\
+import re
 from pathlib import Path
 
 import chromadb
 from llama_index.core import StorageContext
 from llama_index.vector_stores.chroma import ChromaVectorStore
 
+
+def _sanitize_collection_name(name: str) -> str:
+    cleaned = re.sub(r"[^a-zA-Z0-9._-]", "-", name)
+    cleaned = cleaned.strip("-._")
+    if len(cleaned) < 3:
+        cleaned = f"rag-{{cleaned}}".strip("-._")
+    if len(cleaned) < 3:
+        cleaned = "rag-collection"
+    return cleaned[:512]
+
+
 CHROMA_PATH = Path("chroma_db")
-COLLECTION_NAME = "{project_name}"
+COLLECTION_NAME = _sanitize_collection_name("{project_name}")
 
 
 def get_vector_store() -> ChromaVectorStore:
diff --git a/tests/test_rag_template.py b/tests/test_rag_template.py
index 1e155a5..a1c519d 100644
--- a/tests/test_rag_template.py
+++ b/tests/test_rag_template.py
@@ -266,3 +266,56 @@ def test_gitignore_excludes_chroma_db():
 def test_gitignore_keeps_gitkeep():
     from spawn.templates.shared_content import GITIGNORE_CONTENT
     assert "!chroma_db/.gitkeep" in GITIGNORE_CONTENT
+
+
+# ─── Collection name sanitizer ───────────────────────────────────────────
+
+
+def test_collection_name_is_valid_for_various_project_names():
+    import re
+    import types
+
+    t = RAGTemplate()
+    files = dict(t.starter_files)
+    raw_index = files["src/knowledge/index.py"]
+
+    pattern = re.compile(r"^[a-zA-Z0-9][a-zA-Z0-9._-]{1,510}[a-zA-Z0-9]$")
+
+    for project_name in ["my-rag", "ab", "x", "my rag project"]:
+        rendered = raw_index.format_map({"project_name": project_name})
+        ns: dict = {}
+        # Stub out heavy imports so exec works without llama-index installed
+        for mod in [
+            "chromadb", "llama_index", "llama_index.core",
+            "llama_index.vector_stores", "llama_index.vector_stores.chroma",
+        ]:
+            ns[mod] = types.ModuleType(mod)
+        import sys
+        stubs = {}
+        for mod in [
+            "chromadb", "llama_index", "llama_index.core",
+            "llama_index.vector_stores", "llama_index.vector_stores.chroma",
+        ]:
+            stubs[mod] = sys.modules.get(mod)
+            sys.modules[mod] = types.ModuleType(mod)
+        # Provide minimal fakes so the module-level code executes
+        import types as _types
+        llama_core = _types.ModuleType("llama_index.core")
+        llama_core.StorageContext = object  # type: ignore[attr-defined]
+        sys.modules["llama_index.core"] = llama_core
+        vs_fake = _types.ModuleType("llama_index.vector_stores.chroma")
+        vs_fake.ChromaVectorStore = object  # type: ignore[attr-defined]
+        sys.modules["llama_index.vector_stores.chroma"] = vs_fake
+        try:
+            exec(compile(rendered, "<string>", "exec"), ns)  # noqa: S102
+        finally:
+            for mod, orig in stubs.items():
+                if orig is None:
+                    sys.modules.pop(mod, None)
+                else:
+                    sys.modules[mod] = orig
+        collection_name = ns.get("COLLECTION_NAME", "")
+        assert pattern.match(collection_name), (
+            f"project_name={project_name!r} → COLLECTION_NAME={collection_name!r} "
+            "does not match ChromaDB constraints"
+        )

From 9d348b8e164762b56c73981bf81a8c65afb33209 Mon Sep 17 00:00:00 2001
From: Abhiix0 <24r21a6778@mlrit.ac.in>
Date: Thu, 9 Jul 2026 22:08:51 +0530
Subject: [PATCH 09/10] Give ingestion the same error handling as retrieval,
 fix the phantom-index trap

---
 src/spawn/templates/rag/content.py | 42 +++++++++++++++++++++++++-----
 tests/test_rag_template.py         |  3 +++
 2 files changed, 39 insertions(+), 6 deletions(-)

diff --git a/src/spawn/templates/rag/content.py b/src/spawn/templates/rag/content.py
index 3767b61..859ac9b 100644
--- a/src/spawn/templates/rag/content.py
+++ b/src/spawn/templates/rag/content.py
@@ -112,7 +112,8 @@ def get_storage_context() -> StorageContext:
 def index_exists() -> bool:
     if not CHROMA_PATH.exists():
         return False
-    return any(CHROMA_PATH.iterdir())
+    sqlite_file = CHROMA_PATH / "chroma.sqlite3"
+    return sqlite_file.exists() and sqlite_file.stat().st_size > 0
 """
 
 # ─── Ingestion ────────────────────────────────────────────────────────────
@@ -121,6 +122,7 @@ def index_exists() -> bool:
 from pathlib import Path
 
 from llama_index.core import SimpleDirectoryReader, VectorStoreIndex
+from openai import APIError, AuthenticationError, RateLimitError
 
 from src.knowledge.index import get_storage_context
 
@@ -136,11 +138,27 @@ def ingest_documents() -> VectorStoreIndex:
     ).load_data()
     print(f"Loaded {{len(documents)}} document(s).")
     storage_context = get_storage_context()
-    index = VectorStoreIndex.from_documents(
-        documents,
-        storage_context=storage_context,
-        show_progress=True,
-    )
+    try:
+        index = VectorStoreIndex.from_documents(
+            documents,
+            storage_context=storage_context,
+            show_progress=True,
+        )
+    except AuthenticationError:
+        raise RuntimeError(
+            "OpenAI rejected your API key. Check OPENAI_API_KEY in .env."
+        ) from None
+    except RateLimitError as e:
+        if "insufficient_quota" in str(e):
+            raise RuntimeError(
+                "Your OpenAI account has no available quota/credits. "
+                "Check billing at https://platform.openai.com/settings/organization/billing"
+            ) from None
+        raise RuntimeError(
+            "OpenAI rate limit hit. Wait a moment and try again."
+        ) from None
+    except APIError as e:
+        raise RuntimeError(f"OpenAI API error: {{e}}") from None
     print("Ingestion complete. Index stored in chroma_db/")
     return index
 """
@@ -208,6 +226,9 @@ def main() -> None:
             ingest_documents()
         except RuntimeError as e:
             print(f"\\n[Error] {{e}}\\n")
+            import shutil
+            from pathlib import Path
+            shutil.rmtree(Path("chroma_db"), ignore_errors=True)
             return
         print()
     print("Ask a question (or type 'quit' to exit):\\n")
@@ -262,6 +283,15 @@ def test_index_exists_true_when_has_file(tmp_path, monkeypatch):
     assert index_exists()
 
 
+def test_index_exists_false_when_sqlite_file_empty(tmp_path, monkeypatch):
+    monkeypatch.chdir(tmp_path)
+    chroma = tmp_path / "chroma_db"
+    chroma.mkdir()
+    (chroma / "chroma.sqlite3").write_bytes(b"")
+    from src.knowledge.index import index_exists
+    assert not index_exists()
+
+
 def test_sample_knowledge_file_exists():
     data_path = Path("data") / "sample_knowledge.md"
     assert data_path.exists(), "data/sample_knowledge.md must exist"
diff --git a/tests/test_rag_template.py b/tests/test_rag_template.py
index a1c519d..0b24cfe 100644
--- a/tests/test_rag_template.py
+++ b/tests/test_rag_template.py
@@ -97,6 +97,9 @@ def test_knowledge_index_has_exists_check():
     files = dict(t.starter_files)
     index = files["src/knowledge/index.py"]
     assert "index_exists" in index
+    # Verify it checks for the specific sqlite marker, not "any file"
+    assert "chroma.sqlite3" in index
+    assert "st_size" in index
 
 
 def test_ingestion_loads_txt_and_md():

From 85ccc43d399ab39d6e76435fba3c8e7e0193075d Mon Sep 17 00:00:00 2001
From: Abhiix0 <24r21a6778@mlrit.ac.in>
Date: Thu, 9 Jul 2026 22:10:59 +0530
Subject: [PATCH 10/10]  Fix .gitignore so chroma_db/ contents are actually
 excluded

---
 src/spawn/templates/rag/__init__.py |  8 ++++++++
 tests/test_rag_generator.py         | 18 ++++++++++++++++++
 2 files changed, 26 insertions(+)

diff --git a/src/spawn/templates/rag/__init__.py b/src/spawn/templates/rag/__init__.py
index 78f1a9e..57a28b5 100644
--- a/src/spawn/templates/rag/__init__.py
+++ b/src/spawn/templates/rag/__init__.py
@@ -110,3 +110,11 @@ def post_install(self, project_path: Path) -> None:
         # but the actual DB files are gitignored
         gitkeep = project_path / "chroma_db" / ".gitkeep"
         gitkeep.write_text("", encoding="utf-8")
+
+        gitignore_path = project_path / ".gitignore"
+        current_gitignore = gitignore_path.read_text(encoding="utf-8")
+        rag_ignore_rules = "\n# RAG vector database\nchroma_db/*\n!chroma_db/.gitkeep\n"
+        if "chroma_db/*" not in current_gitignore:
+            gitignore_path.write_text(
+                current_gitignore + rag_ignore_rules, encoding="utf-8"
+            )
diff --git a/tests/test_rag_generator.py b/tests/test_rag_generator.py
index 7875dff..85e555a 100644
--- a/tests/test_rag_generator.py
+++ b/tests/test_rag_generator.py
@@ -191,3 +191,21 @@ def test_rag_install_packages_called_with_correct_deps(tmp_path, monkeypatch):
     assert "chromadb" in args
     assert "llama-index-embeddings-openai" in args
     assert "python-dotenv" in args
+
+
+def test_rag_gitignore_has_chroma_wildcard_rule(tmp_path, monkeypatch):
+    """post_install must append chroma_db/* and !chroma_db/.gitkeep to .gitignore."""
+    monkeypatch.chdir(tmp_path)
+    with patch("spawn.generators.project_generator.install_packages"), \
+         patch("spawn.generators.project_generator.initialize_uv") as mock_uv:
+        # initialize_uv needs to create a minimal pyproject.toml so post_install
+        # can read it without error
+        def fake_uv(p):
+            (p / "pyproject.toml").write_text(
+                '[project]\nname="x"\nversion="0.1.0"\n', encoding="utf-8"
+            )
+        mock_uv.side_effect = fake_uv
+        ProjectGenerator().generate(_cfg())
+    gitignore = (tmp_path / "my-rag" / ".gitignore").read_text(encoding="utf-8")
+    assert "chroma_db/*" in gitignore
+    assert "!chroma_db/.gitkeep" in gitignore