Develop a LlamaIndex Query Pipeline agent

This page shows you how to develop an agent using the LlamaIndex Query Pipelines template (the LlamaIndexQueryPipelineAgent class in the Vertex AI SDK for Python). This agent is designed to answer questions using Retrieval-Augmented Generation (RAG), such as the following query: "What is Paul Graham's life in college?"

Use the following steps to develop an agent using LlamaIndex Query Pipelines:

1. Define and configure a model
2. Define and use a retriever
3. Define and use a response synthesizer
4. (Optional) Customize the prompt template
5. (Optional) Customize the orchestration

Before you begin

Make sure your environment is set up by following the steps in Set up your environment.

Define and configure a model

Define and configure a model for your LlamaIndex Query Pipeline agent to use.

1. Define the model version:

   model = "gemini-2.0-flash"
   

2. (Optional) Specify model parameters:

   model_kwargs = {
    # vertexai_config (dict): By providing the region and project_id parameters,
    # you can enable model usage through Vertex AI.
    "vertexai_config": {
    "project": "PROJECT_ID",
    "location": "LOCATION"
    },
    # temperature (float): The sampling temperature controls the degree of
    # randomness in token selection.
    "temperature": 0.28,
    # context_window (int): The context window of the model.
    # If not provided, the default context window is 200000.
    "context_window": 200000,
    # max_tokens (int): Token limit determines the maximum
    # amount of text output from one prompt. If not provided,
    # the default max_tokens is 256.
    "max_tokens": 256,
   }
   

3. Create a LlamaIndexQueryPipelineAgent using the following model configurations:

   fromvertexai.previewimport reasoning_engines
   agent = reasoning_engines.LlamaIndexQueryPipelineAgent(
    model=model, # Required.
    model_kwargs=model_kwargs, # Optional.
   )
   

4. If you are running in an interactive environment (such as the terminal or Colab notebook), you can query the agent:

   response = agent.query(input="What is Paul Graham's life in college?")
   print(response)
   

   You should receive a response similar to the following:

   {'message': {'role': 'assistant',
    'additional_kwargs': {},
    'blocks': [{'block_type': 'text',
    'text': "Unfortunately, there's not a lot of publicly available information about Paul Graham's personal life in college. ..."}]},
    'raw': {'content': {'parts': [{'video_metadata': None,
    'thought': None,
    'code_execution_result': None,
    'executable_code': None,
    'file_data': None,
    'function_call': None,
    'function_response': None,
    'inline_data': None,
    'text': "Unfortunately, there's not a lot of publicly available information about Paul Graham's personal life in college. ..."}],
    'role': 'model'},
    'citation_metadata': None,
    'finish_message': None,
    'token_count': None,
    'avg_logprobs': -0.1468650027438327,
    'finish_reason': 'STOP',
    'grounding_metadata': None,
    'index': None,
    'logprobs_result': None,
    'safety_ratings': [{'blocked': None,
    'category': 'HARM_CATEGORY_HATE_SPEECH',
    'probability': 'NEGLIGIBLE',
    'probability_score': 0.022949219,
    'severity': 'HARM_SEVERITY_NEGLIGIBLE',
    'severity_score': 0.014038086},
    {'blocked': None,
    'category': 'HARM_CATEGORY_DANGEROUS_CONTENT',
    'probability': 'NEGLIGIBLE',
    'probability_score': 0.056640625,
    'severity': 'HARM_SEVERITY_NEGLIGIBLE',
    'severity_score': 0.029296875},
    {'blocked': None,
    'category': 'HARM_CATEGORY_HARASSMENT',
    'probability': 'NEGLIGIBLE',
    'probability_score': 0.071777344,
    'severity': 'HARM_SEVERITY_NEGLIGIBLE',
    'severity_score': 0.024047852},
    {'blocked': None,
    'category': 'HARM_CATEGORY_SEXUALLY_EXPLICIT',
    'probability': 'NEGLIGIBLE',
    'probability_score': 0.103515625,
    'severity': 'HARM_SEVERITY_NEGLIGIBLE',
    'severity_score': 0.05102539}],
    'usage_metadata': {'cached_content_token_count': None,
    'candidates_token_count': 222,
    'prompt_token_count': 10,
    'total_token_count': 232}},
    'delta': None,
    'logprobs': None,
    'additional_kwargs': {}}
   

(Optional) Customize your model

The LlamaIndexQueryPipelineAgent template uses Google GenAI by default to provide access to all foundational models available in Google Cloud. To use a model that isn't available through Google GenAI, define model_builder= as follows:

fromtypingimport Optional
defmodel_builder(
 *,
 model_name: str, # Required. The name of the model
 model_kwargs: Optional[dict] = None, # Optional. The model keyword arguments.
 **kwargs, # Optional. The remaining keyword arguments to be ignored.
):

For a list of the chat models supported in LlamaIndexQueryPipeline and their capabilities, see Available LLM integrations. Each chat model uses their own set of supported values for model= and model_kwargs=.

fromvertexai.previewimport reasoning_engines
agent = reasoning_engines.LlamaIndexQueryPipelineAgent(
 model=model, # Required.
 model_kwargs=model_kwargs, # Optional.
)

Define and use a retriever

After you define your model, define the retriever that your model uses for reasoning. A retriever can be built on top of indexes, but can also be defined comprehensively. You should test your retriever locally.

1. Define a retriever that returns relevant documents and similarity scores:

   defretriever_builder(model, retriever_kwargs=None):
    importos
    importrequests
    fromllama_index.coreimport (
    StorageContext,
    VectorStoreIndex,
    load_index_from_storage,
    )
    fromllama_index.coreimport SimpleDirectoryReader
    fromllama_index.embeddings.verteximport VertexTextEmbedding
    importgoogle.auth
    credentials, _ = google.auth.default()
    embed_model = VertexTextEmbedding(
    model_name="text-embedding-005", project="PROJECT_ID", credentials=credentials
    )
    data_dir = "data/paul_graham"
    essay_file = os.path.join(data_dir, "paul_graham_essay.txt")
    storage_dir = "storage"
    # --- Simple Download (if needed) ---
    if not os.path.exists(essay_file):
    os.makedirs(data_dir, exist_ok=True) # Make sure the directory exists
    essay_url = "https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt"
    try:
    response = requests.get(essay_url)
    response.raise_for_status() # Check for download errors
    with open(essay_file, "wb") as f:
    f.write(response.content)
    print("Essay downloaded.")
    except requests.exceptions.RequestException as e:
    print(f"Download failed: {e}")
    # --- Build/Load Index ---
    if not os.path.exists(storage_dir):
    print("Creating new index...")
    # --- Load Data ---
    reader = SimpleDirectoryReader(data_dir)
    docs = reader.load_data()
    index = VectorStoreIndex.from_documents(docs, model=model, embed_model=embed_model)
    index.storage_context.persist(persist_dir=storage_dir)
    else:
    print("Loading existing index...")
    storage_context = StorageContext.from_defaults(persist_dir=storage_dir)
    index = load_index_from_storage(storage_context, embed_model=embed_model)
    return index.as_retriever()
   

2. Test the retriever:

   fromllama_index.llms.google_genaiimport GoogleGenAI
   model = GoogleGenAI(
    model=model,
    **model_kwargs
   )
   retriever = retriever_builder(model)
   retrieved_response = retriever.retrieve("What is Paul Graham's life in College?")
   

   The retrieved response should be similar to the following:

   [
    NodeWithScore(
    node=TextNode(
    id_='692a5d5c-cd56-4ed0-8e29-ecadf6eb9933',
    embedding=None,
    metadata={'file_path': '/content/data/paul_graham/paul_graham_essay.txt', 'file_name': 'paul_graham_essay.txt', 'file_type': 'text/plain', 'file_size': 75042, 'creation_date': '2025-03-24', 'last_modified_date': '2025-03-24'},
    excluded_embed_metadata_keys=['file_name', 'file_type', 'file_size', 'creation_date', 'last_modified_date', 'last_accessed_date'],
    excluded_llm_metadata_keys=['file_name', 'file_type', 'file_size', 'creation_date', 'last_modified_date', 'last_accessed_date'],
    relationships={
    <NodeRelationship.SOURCE: '1'>: RelatedNodeInfo(node_id='3e1c4d73-1e1d-4e83-bd16-2dae24abb231', node_type='4', metadata={'file_path': '/content/data/paul_graham/paul_graham_essay.txt', 'file_name': 'paul_graham_essay.txt', 'file_type': 'text/plain', 'file_size': 75042, 'creation_date': '2025-03-24', 'last_modified_date': '2025-03-24'}, hash='0c3c3f46cac874b495d944dfc4b920f6b68817dbbb1699ecc955d1fafb2bf87b'), <NodeRelationship.PREVIOUS: '2'>: RelatedNodeInfo(node_id='782c5787-8753-4f65-85ed-c2833ea6d4d8', node_type='1', metadata={'file_path': '/content/data/paul_graham/paul_graham_essay.txt', 'file_name': 'paul_graham_essay.txt', 'file_type': 'text/plain', 'file_size': 75042, 'creation_date': '2025-03-24', 'last_modified_date': '2025-03-24'}, hash='b8e6463833887a8a2b13f1b5a623672819faedc1b725d9565ba003223628db0e'), <NodeRelationship.NEXT: '3'>: RelatedNodeInfo(node_id='f7d2cb7e-fa0c-40bf-b8e7-b888e36b87f9', node_type='1', metadata={}, hash='db7cc1a67fa3afd1e5f24c8c61583781ce6a00c444da8f25a5374468c17b7de0')
    },
    metadata_template='{key}: {value}',
    metadata_separator='\n',
    text='So I looked around to see what I could salvage from the wreckage of my plans, and there was Lisp...',
    mimetype='text/plain',
    start_char_idx=7166,
    end_char_idx=11549,
    metadata_separator='\n',
    text_template='{metadata_str}\n\n{content}'
    ),
    score=0.7403571819090398
    )
   ]
   

3. To use the retriever inside LlamaIndexQueryPipelineAgent, add it under the retriever_builder= argument:

   fromvertexai.previewimport reasoning_engines
   agent = reasoning_engines.LlamaIndexQueryPipelineAgent(
    model=model, # Required.
    model_kwargs=model_kwargs, # Optional.
    retriever_builder=retriever_builder, # Optional.
   )
   

4. Test the agent locally by performing test queries:

   response = agent.query(
    input="What is Paul Graham's life in College?"
   )
   

   The response is a JSON serializable list of nodes with scores.

   [{'node': {'id_': '692a5d5c-cd56-4ed0-8e29-ecadf6eb9933',
    'embedding': None,
    'metadata': {'file_path': '/content/data/paul_graham/paul_graham_essay.txt',
    'file_name': 'paul_graham_essay.txt',
    'file_type': 'text/plain',
    'file_size': 75042,
    'creation_date': '2025-03-12',
    'last_modified_date': '2025-03-12'},
    'excluded_embed_metadata_keys': ['file_name',
    'file_type',
    'file_size',
    'creation_date',
    'last_modified_date',
    'last_accessed_date'],
    'excluded_llm_metadata_keys': ['file_name',
    'file_type',
    'file_size',
    'creation_date',
    'last_modified_date',
    'last_accessed_date'],
    'relationships': {'1': {'node_id': '07ee9574-04c8-46c7-b023-b22ba9558a1f',
    'node_type': '1',
    'metadata': {},
    'hash': '44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a',
    'class_name': 'RelatedNodeInfo'},
    '2': {'node_id': 'ac7e54aa-6fff-40b5-a15e-89c5eb234936',
    'node_type': '1',
    'metadata': {'file_path': '/content/data/paul_graham/paul_graham_essay.txt',
    'file_name': 'paul_graham_essay.txt',
    'file_type': 'text/plain',
    'file_size': 75042,
    'creation_date': '2025-03-12',
    'last_modified_date': '2025-03-12'},
    'hash': '755327a01efe7104db771e4e6f9683417884ea6895d878da882d2b21a6b66442',
    'class_name': 'RelatedNodeInfo'},
    '3': {'node_id': '3a04be27-ac46-4acd-a8c6-031689508982',
    'node_type': '1',
    'metadata': {},
    'hash': 'db7cc1a67fa3afd1e5f24c8c61583781ce6a00c444da8f25a5374468c17b7de0',
    'class_name': 'RelatedNodeInfo'}},
    'metadata_template': '{key}: {value}',
    'metadata_separator': '\n',
    'text': 'So I looked around to see what I could salvage from the wreckage of my plans, and there was Lisp...',
    'mimetype': 'text/plain',
    'start_char_idx': 7164,
    'end_char_idx': 11547,
    'metadata_separator': '\n',
    'text_template': '{metadata_str}\n\n{content}',
    'class_name': 'TextNode'},
    'score': 0.25325886336265013,
    'class_name': 'NodeWithScore'}
   ]
   

Define and use a response synthesizer

After you define your model and retriever, define the response-synthesizer that generates a response from an LLM using a user query and a given set of text chunks. You can use the default get_response_synthesizer or configure the response mode.

1. Define a response synthesizer that returns the answer:

   defresponse_synthesizer_builder(model, response_synthesizer_kwargs=None):
    fromllama_index.core.response_synthesizersimport SimpleSummarize
    return SimpleSummarize(llm=model)
   

2. Test the function:

   response_synthesizer = response_synthesizer_builder(model=model)
   response = response_synthesizer.get_response(
    "What is Paul Graham's life in College?",
    [node.model_dump_json() for node in retrieved_response],
   )
   

   The response should be similar to the following:

   "While in a PhD program for computer science, he took art classes and worked on a book about Lisp hacking. He applied to art schools, got accepted to RISD, and later got an invitation to take the entrance exam at the Accademia di Belli Arti in Florence. He was accepted to both. He attended the Accademia, but was disappointed by the lack of instruction."
   

3. To use the response synthesizer inside LlamaIndexQueryPipelineAgent, add it under the response_synthesizer_builder= argument:

   fromvertexai.previewimport reasoning_engines
   agent = reasoning_engines.LlamaIndexQueryPipelineAgent(
    model=model, # Required.
    model_kwargs=model_kwargs, # Optional.
    retriever_builder=retriever_builder, # Optional.
    response_synthesizer_builder=response_synthesizer_builder, # Optional.
   )
   

4. Test the full RAG query pipeline locally by running test queries:

   response = agent.query(
    input="What is Paul Graham's life in College?"
   )
   

   The response is a dictionary that is similar to the following:

   {
    'response': "While in college, he was drawn to McCarthy's 1960 Lisp, although he didn't fully grasp the reasons for his interest at the time. He also had a brief encounter with surplus Xerox Dandelions in the computer lab but found them too slow for his liking. \n",
    'source_nodes': [
    '{"node":{"id_":"95889c30-53c7-43d0-bf91-930dbb23bde6"...,"score":0.7077213268404997,"class_name":"NodeWithScore"}'
    ],
    'metadata': {
    '95889c30-53c7-43d0-bf91-930dbb23bde6': {
    'file_path': '/content/data/paul_graham/paul_graham_essay.txt',
    'file_name': 'paul_graham_essay.txt',
    'file_type': 'text/plain',
    'file_size': 75042,
    'creation_date': '2025-03-25',
    'last_modified_date': '2025-03-25'
    }
    }
   }
   

(Optional) Customize the prompt template

Prompt templates translate user input into model instructions, guiding responses for contextually relevant and coherent output. See Prompts for details.

The default prompt template is organized sequentially into the following sections:

The default prompt template is generated if you create the agent without specifying your own prompt template, and looks like the following:

fromllama_index.coreimport prompts
fromllama_index.core.base.llmsimport types
message_templates = [
 types.ChatMessage(role=types.MessageRole.SYSTEM, content=system_instruction),
 types.ChatMessage(role=types.MessageRole.USER, content="{input}"),
]
prompts.ChatPromptTemplate(message_templates=message_templates)

You can use the full prompt template when you instantiate the agent in the following example:

 fromvertexai.previewimport reasoning_engines
 system_instruction = "I help to find what is Paul Graham's life in College"
 agent = reasoning_engines.LlamaIndexQueryPipelineAgent(
 model=model,
 system_instruction=system_instruction,
 )

You can override the default prompt template with your own prompt template, and use it when constructing the agent:

prompt_str = "Please answer {question} about {name}"
prompt_tmpl = PromptTemplate(prompt_str)
fromvertexai.previewimport reasoning_engines
agent = reasoning_engines.LlamaIndexQueryPipelineAgent(
 model = model,
 prompt = prompt_tmpl,
)
agent.query(
 input={
 "name": "Paul Graham",
 "question": "What is the life in college?",
 }
)

(Optional) Customize the orchestration

All LlamaIndexQueryPipeline components implement the Query Component interface, which provides input and output schemas for orchestration. The LlamaIndexQueryPipelineAgent class requires a runnable to be built for it to respond to queries. By default, LlamaIndexQueryPipelineAgent builds a sequential chain or Directed Acyclic Graph (DAG) using Query Pipeline.

You might want to customize the orchestration if you intend to do either of the following:

• Implement an agent that extends the RAG pipeline (such as extending an existing Prompt, Model, Retriever, Response Synthesizer module to Query Engine, Query Transformer, Output Parsers, Postprocessor/Rerankers or Custom Query Component).

• Prompt the agent using ReAct to execute tools and annotate each step with comments for why it performed that step. To do so, override the default runnable when creating LlamaIndexQueryPipelineAgent by specifying the runnable_builder= argument:

  fromtypingimport Optional
  fromllama_index.core.llmsimport function_calling
  defrunnable_builder(
   model: function_calling.FunctionCallingLLM,
   *,
   system_instruction: Optional[str] = None,
   prompt: Optional[query.QUERY_COMPONENT_TYPE] = None,
   retriever: Optional[query.QUERY_COMPONENT_TYPE] = None,
   response_synthesizer: Optional[query.QUERY_COMPONENT_TYPE] = None,
   runnable_kwargs: Optional[Mapping[str, Any]] = None,
  ):
  

  Where:

  • model corresponds to the chat model being returned from the model_builder (see Define and configure a model).
  • retriever and retriever_kwargs correspond to the retriever and configurations to be used (see Define a retriever).
  • response_synthesizer and response_synthesizer_kwargs correspond to the response synthesizer and configurations to be used (see Define a response synthesizer).
  • system_instruction and prompt correspond to the prompt configuration (see Customize the prompt template).
  • agent_executor_kwargs and runnable_kwargs are the keyword arguments you can use for customizing the runnable.

You can customize the orchestration logic using a custom pipeline or ReAct:

What's next

• Use a LlamaIndex Query Pipeline agent.
• Evaluate an agent.
• Deploy an agent.
• Troubleshoot developing an agent.
• Get support.