Add Docusaurus version latest

  - Created version snapshot in versioned_docs/version-latest/
  - Updated versions.json with new version
  - Built and deployed multi-version site

  🤖 Generated by Docusaurus versioning workflow

Author: github-actions[bot]

versioned_docs/version-v0.3.3/getting_started/quickstart.mdx

@@ -42,68 +42,27 @@ Now open up a new terminal and copy the following script into a file named `demo
 # 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")
+import io, requests
+from openai import OpenAI
 
-models = client.models.list()
+url="https://www.paulgraham.com/greatwork.html"
+client = OpenAI(base_url="http://localhost:8321/v1/", api_key="none")
 
-# 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"]
+vs = client.vector_stores.create()
+response = requests.get(url)
+pseudo_file = io.BytesIO(str(response.content).encode('utf-8'))
+uploaded_file = client.files.create(file=(url, pseudo_file, "text/html"), purpose="assistants")
+client.vector_stores.files.create(vector_store_id=vs.id, file_id=uploaded_file.id)
 
-vector_db = client.vector_dbs.register(
-    vector_db_id=vector_db_id,
-    embedding_model=embedding_model_id,
-    embedding_dimension=embedding_dimension,
-    provider_id="faiss",
-)
-vector_db_id = vector_db.identifier
-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=100,
-)
-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)
-
-use_stream = True
-response = agent.create_turn(
-    messages=[{"role": "user", "content": prompt}],
-    session_id=agent.create_session("rag_session"),
-    stream=use_stream,
+resp = client.responses.create(
+    model="openai/gpt-4o",
+    input="How do you do great work? Use the existing knowledge_search tool.",
+    tools=[{"type": "file_search", "vector_store_ids": [vs.id]}],
+    include=["file_search_call.results"],
 )
 
-# Only call `AgentEventLogger().log(response)` for streaming responses.
-if use_stream:
-    for log in AgentEventLogger().log(response):
-        log.print()
-else:
-    print(response)
+print(resp)
 ```
 We will use `uv` to run the script
 ```