From 2bc96613f918316a5df85925b0c7872127947cae Mon Sep 17 00:00:00 2001
From: Francisco Arceo <arceofrancisco@gmail.com>
Date: Mon, 21 Jul 2025 22:53:32 -0400
Subject: [PATCH] chore: Adding demo script and importing it into the docs
 (#2848)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

# What does this PR do?
This PR adds the quickstart as a file to the docs so that it can be more
easily maintained and run, as mentioned in
https://github.com/meta-llama/llama-stack/pull/2800.

## Test Plan
I could add this as a test in the CI but I wasn't sure if we wanted to
add additional jobs there. 😅

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
---
 docs/source/getting_started/demo_script.py | 62 ++++++++++++++++++++++
 docs/source/getting_started/quickstart.md  | 59 +-------------------
 2 files changed, 64 insertions(+), 57 deletions(-)
 create mode 100644 docs/source/getting_started/demo_script.py

diff --git a/docs/source/getting_started/demo_script.py b/docs/source/getting_started/demo_script.py
new file mode 100644
index 000000000..298fd9899
--- /dev/null
+++ b/docs/source/getting_started/demo_script.py
@@ -0,0 +1,62 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from llama_stack_client import Agent, AgentEventLogger, RAGDocument, LlamaStackClient
+
+vector_db_id = "my_demo_vector_db"
+client = LlamaStackClient(base_url="http://localhost:8321")
+
+models = client.models.list()
+
+# Select the first LLM and first embedding models
+model_id = next(m for m in models if m.model_type == "llm").identifier
+embedding_model_id = (
+    em := next(m for m in models if m.model_type == "embedding")
+).identifier
+embedding_dimension = em.metadata["embedding_dimension"]
+
+_ = client.vector_dbs.register(
+    vector_db_id=vector_db_id,
+    embedding_model=embedding_model_id,
+    embedding_dimension=embedding_dimension,
+    provider_id="faiss",
+)
+source = "https://www.paulgraham.com/greatwork.html"
+print("rag_tool> Ingesting document:", source)
+document = RAGDocument(
+    document_id="document_1",
+    content=source,
+    mime_type="text/html",
+    metadata={},
+)
+client.tool_runtime.rag_tool.insert(
+    documents=[document],
+    vector_db_id=vector_db_id,
+    chunk_size_in_tokens=50,
+)
+agent = Agent(
+    client,
+    model=model_id,
+    instructions="You are a helpful assistant",
+    tools=[
+        {
+            "name": "builtin::rag/knowledge_search",
+            "args": {"vector_db_ids": [vector_db_id]},
+        }
+    ],
+)
+
+prompt = "How do you do great work?"
+print("prompt>", prompt)
+
+response = agent.create_turn(
+    messages=[{"role": "user", "content": prompt}],
+    session_id=agent.create_session("rag_session"),
+    stream=True,
+)
+
+for log in AgentEventLogger().log(response):
+    log.print()
diff --git a/docs/source/getting_started/quickstart.md b/docs/source/getting_started/quickstart.md
index 59791643d..5549f412c 100644
--- a/docs/source/getting_started/quickstart.md
+++ b/docs/source/getting_started/quickstart.md
@@ -24,63 +24,8 @@ ENABLE_OLLAMA=ollama OLLAMA_INFERENCE_MODEL=llama3.2:3b uv run --with llama-stac
 #### Step 3: Run the demo
 Now open up a new terminal and copy the following script into a file named `demo_script.py`.
 
-```python
-from llama_stack_client import Agent, AgentEventLogger, RAGDocument, LlamaStackClient
-
-vector_db_id = "my_demo_vector_db"
-client = LlamaStackClient(base_url="http://localhost:8321")
-
-models = client.models.list()
-
-# Select the first LLM and first embedding models
-model_id = next(m for m in models if m.model_type == "llm").identifier
-embedding_model_id = (
-    em := next(m for m in models if m.model_type == "embedding")
-).identifier
-embedding_dimension = em.metadata["embedding_dimension"]
-
-_ = client.vector_dbs.register(
-    vector_db_id=vector_db_id,
-    embedding_model=embedding_model_id,
-    embedding_dimension=embedding_dimension,
-    provider_id="faiss",
-)
-source = "https://www.paulgraham.com/greatwork.html"
-print("rag_tool> Ingesting document:", source)
-document = RAGDocument(
-    document_id="document_1",
-    content=source,
-    mime_type="text/html",
-    metadata={},
-)
-client.tool_runtime.rag_tool.insert(
-    documents=[document],
-    vector_db_id=vector_db_id,
-    chunk_size_in_tokens=50,
-)
-agent = Agent(
-    client,
-    model=model_id,
-    instructions="You are a helpful assistant",
-    tools=[
-        {
-            "name": "builtin::rag/knowledge_search",
-            "args": {"vector_db_ids": [vector_db_id]},
-        }
-    ],
-)
-
-prompt = "How do you do great work?"
-print("prompt>", prompt)
-
-response = agent.create_turn(
-    messages=[{"role": "user", "content": prompt}],
-    session_id=agent.create_session("rag_session"),
-    stream=True,
-)
-
-for log in AgentEventLogger().log(response):
-    log.print()
+```{literalinclude} ./demo_script.py
+:language: python
 ```
 We will use `uv` to run the script
 ```