pip install "langchain-google-community[bigquery]" langchain langchain-google-genai langgraph

import os
from datetime import datetime

from langchain.agents import create_agent
from langchain.messages import HumanMessage
from langchain.tools import tool
from langchain_google_community.callbacks.bigquery_callback import (
    BigQueryCallbackHandler,
    BigQueryLoggerConfig,
)
from langchain_google_genai import ChatGoogleGenerativeAI

# 1. Define tools for the agent
@tool
def get_current_time() -> str:
    """Returns the current local time."""
    now = datetime.now()
    return f"Current time: {now.strftime('%I:%M:%S %p')} on {now.strftime('%B %d, %Y')}"

@tool
def get_weather(city: str) -> str:
    """Returns the current weather for a specific city."""
    # Simulated weather data (use real API in production)
    weather_data = {
        "new york": {"temp": 22, "condition": "Clear"},
        "tokyo": {"temp": 24, "condition": "Sunny"},
        "london": {"temp": 14, "condition": "Overcast"},
    }
    city_lower = city.lower()
    if city_lower in weather_data:
        data = weather_data[city_lower]
        return f"Weather in {city.title()}: {data['temp']}°C, {data['condition']}"
    return f"Weather data for '{city}' not available."

@tool
def convert_currency(amount: float, from_currency: str, to_currency: str) -> str:
    """Convert an amount between currencies."""
    rates = {"USD": 1.0, "EUR": 1.08, "GBP": 1.27, "JPY": 0.0067}
    from_curr, to_curr = from_currency.upper(), to_currency.upper()
    if from_curr not in rates or to_curr not in rates:
        return f"Unknown currency"
    result = amount * rates[from_curr] / rates[to_curr]
    return f"{amount} {from_curr} = {result:.2f} {to_curr}"

def run_agent_example(project_id: str):
    """Run a LangGraph agent with BigQuery logging."""

    dataset_id = "agent_analytics"

    # 2. Configure the callback handler.
    # `table_id` defaults to "agent_events"; pass it explicitly only if you
    # want a different table. The handler creates the table and the
    # per-event-type `v_*` analytics views on first run.
    config = BigQueryLoggerConfig(
        batch_size=1,
        batch_flush_interval=0.5,
        custom_tags={"env": "prod", "service": "travel"},  # static tags on every event
    )

    handler = BigQueryCallbackHandler(
        project_id=project_id,
        dataset_id=dataset_id,
        config=config,
        graph_name="travel_assistant",  # used for INVOCATION_* events + root_agent_name
    )

    # 3. Create the LLM and agent
    # Use project parameter for Gemini Enterprise Agent Platform, or api_key for Gemini Developer API
    llm = ChatGoogleGenerativeAI(
        model="gemini-2.5-flash",
        project=project_id,  # For Gemini Enterprise Agent Platform
    )
    tools = [get_current_time, get_weather, convert_currency]
    agent = create_agent(llm, tools)

    # 4. Run with graph_context for INVOCATION_STARTING / INVOCATION_COMPLETED
    query = "What time is it? What's the weather in Tokyo? How much is 100 USD in EUR?"

    run_metadata = {
        "session_id": "session-001",
        "user_id": "user-123",
        # `agent` is optional — when omitted the handler falls back to
        # metadata['langgraph_node'] for per-sub-agent attribution.
    }

    with handler.graph_context("travel_assistant", metadata=run_metadata):
        result = agent.invoke(
            {"messages": [HumanMessage(content=query)]},
            config={
                "callbacks": [handler],
                "metadata": run_metadata,
            },
        )

    print(f"Response: {result['messages'][-1].content}")

    # 5. Block until pending rows are written (between request boundaries).
    # Does NOT shut the handler down — subsequent invocations still work.
    handler.flush(timeout=5.0)

    # 6. Final cleanup at process exit.
    handler.shutdown()

if __name__ == "__main__":
    project_id = os.environ.get("GCP_PROJECT_ID", "your-project-id")
    run_agent_example(project_id)

from langchain_google_community.callbacks.bigquery_callback import (
    BigQueryCallbackHandler,
    BigQueryLoggerConfig,
)

# 1. Configure BigQueryLoggerConfig
config = BigQueryLoggerConfig(
    enabled=True,
    event_allowlist=["LLM_REQUEST", "LLM_RESPONSE"],  # Only log these specific events
    shutdown_timeout=10.0,  # Wait up to 10s for logs to flush on exit
    max_content_length=500,  # Truncate content to 500 characters
)

# 2. Initialize the Callback Handler
handler = BigQueryCallbackHandler(
    project_id="your-project-id",
    dataset_id="your_dataset",
    table_id="your_table",
    config=config,
)

CREATE TABLE `your-gcp-project-id.adk_agent_logs.agent_events`
(
  timestamp TIMESTAMP NOT NULL OPTIONS(description="The UTC timestamp when the event occurred."),
  event_type STRING OPTIONS(description="The category of the event."),
  agent STRING OPTIONS(description="The name of the agent."),
  session_id STRING OPTIONS(description="A unique identifier for the conversation session."),
  invocation_id STRING OPTIONS(description="A unique identifier for a single turn."),
  user_id STRING OPTIONS(description="The identifier of the end-user."),
  trace_id STRING OPTIONS(description="OpenTelemetry trace ID."),
  span_id STRING OPTIONS(description="OpenTelemetry span ID."),
  parent_span_id STRING OPTIONS(description="OpenTelemetry parent span ID."),
  content JSON OPTIONS(description="The primary payload of the event."),
  content_parts ARRAY<STRUCT<
    mime_type STRING,
    uri STRING,
    object_ref STRUCT<
      uri STRING,
      version STRING,
      authorizer STRING,
      details JSON
    >,
    text STRING,
    part_index INT64,
    part_attributes STRING,
    storage_mode STRING
  >> OPTIONS(description="For multi-modal events, contains a list of content parts."),
  attributes JSON OPTIONS(description="Arbitrary key-value pairs."),
  latency_ms JSON OPTIONS(description="Latency measurements."),
  status STRING OPTIONS(description="The outcome of the event."),
  error_message STRING OPTIONS(description="Detailed error message."),
  is_truncated BOOLEAN OPTIONS(description="Flag indicating if content was truncated.")
)
PARTITION BY DATE(timestamp)
CLUSTER BY event_type, agent, user_id;

-- With the auto-view
SELECT agent, SUM(usage_total_tokens) AS tokens
FROM `PROJECT.DATASET.v_llm_response`
GROUP BY agent;

-- Equivalent against the raw table
SELECT agent,
       SUM(CAST(JSON_VALUE(attributes, '$.usage.total_tokens') AS INT64)) AS tokens
FROM `PROJECT.DATASET.agent_events`
WHERE event_type = 'LLM_RESPONSE'
GROUP BY agent;

SELECT
  timestamp,
  event_type,
  span_id,
  parent_span_id,
  -- Extract summary or specific content based on event type
  COALESCE(
    JSON_VALUE(content, '$.messages[0].content'),
    JSON_VALUE(content, '$.summary'),
    JSON_VALUE(content)
  ) AS summary,
  JSON_VALUE(latency_ms, '$.total_ms') AS duration_ms
FROM
  `your-gcp-project-id.adk_agent_logs.agent_events`
WHERE
    -- Replace with a specific trace_id from your logs
  trace_id = '019bb986-a0db-7da1-802d-2725795ab340'
ORDER BY
  timestamp ASC;

SELECT
  JSON_VALUE(attributes, '$.model') AS model,
  COUNT(*) AS total_calls,
  AVG(CAST(JSON_VALUE(latency_ms, '$.total_ms') AS FLOAT64)) AS avg_latency_ms,
  SUM(CAST(JSON_VALUE(attributes, '$.usage.total_tokens') AS INT64)) AS total_tokens
FROM
  `your-gcp-project-id.adk_agent_logs.agent_events`
WHERE
  event_type = 'LLM_RESPONSE'
GROUP BY
  1;

SELECT
  logs.session_id,
  -- Get a signed URL for the image (optional, for viewing)
  STRING(OBJ.GET_ACCESS_URL(parts.object_ref, "r").access_urls.read_url) as signed_url,
  -- Analyze the image using a remote model (e.g., gemini-2.5-flash)
  AI.GENERATE(
    ('Describe this image briefly. What company logo?', parts.object_ref)
  ) AS generated_result
FROM
  `your-gcp-project-id.adk_agent_logs.agent_events` logs,
  UNNEST(logs.content_parts) AS parts
WHERE
  parts.mime_type LIKE 'image/%'
ORDER BY logs.timestamp DESC
LIMIT 1;

SELECT
  span_id,
  parent_span_id,
  event_type,
  timestamp,
  -- Extract duration from latency_ms for completed operations
  CAST(JSON_VALUE(latency_ms, '$.total_ms') AS INT64) as duration_ms,
  -- Identify the specific tool or operation
  COALESCE(
    JSON_VALUE(content, '$.tool'),
    'LLM_CALL'
  ) as operation
FROM `your-gcp-project-id.adk_agent_logs.agent_events`
WHERE trace_id = 'your-trace-id'
  AND event_type IN ('LLM_RESPONSE', 'TOOL_COMPLETED')
ORDER BY timestamp ASC;

SELECT
  timestamp,
  event_type,
  part.mime_type,
  part.storage_mode,
  part.object_ref.uri AS gcs_uri,
  -- Generate a signed URL to read the content directly (requires connection_id configuration)
  STRING(OBJ.GET_ACCESS_URL(part.object_ref, 'r').access_urls.read_url) AS signed_url
FROM `your-gcp-project-id.adk_agent_logs.agent_events`,
UNNEST(content_parts) AS part
WHERE part.storage_mode = 'GCS_REFERENCE'
ORDER BY timestamp DESC
LIMIT 10;

-- 1. Sessionize Conversation History (Create View)
-- Consolidates all events into a single row per session with a formatted history.
CREATE OR REPLACE VIEW `your-project.your-dataset.agent_sessions` AS
SELECT
  session_id,
  user_id,
  MIN(timestamp) AS session_start,
  MAX(timestamp) AS session_end,
  ARRAY_AGG(
    STRUCT(timestamp, event_type, TO_JSON_STRING(content) as content, error_message)
    ORDER BY timestamp ASC
  ) AS events,
  STRING_AGG(
      CASE
          -- LLM_REQUEST carries the user's prompt under content.messages
          WHEN event_type = 'LLM_REQUEST' THEN CONCAT('User: ', JSON_VALUE(content, '$.summary'))
          WHEN event_type = 'LLM_RESPONSE' THEN CONCAT('Agent: ', JSON_VALUE(content, '$.summary'))
          WHEN event_type = 'TOOL_STARTING' THEN CONCAT('SYS: Calling ', JSON_VALUE(content, '$.tool'))
          WHEN event_type = 'TOOL_COMPLETED' THEN CONCAT('SYS: Result from ', JSON_VALUE(content, '$.tool'))
          WHEN event_type = 'TOOL_ERROR' THEN CONCAT('SYS: ERROR in ', JSON_VALUE(content, '$.tool'))
          ELSE NULL
      END,
      '\n' ORDER BY timestamp ASC
  ) AS full_conversation
FROM
  `your-project.your-dataset.agent_events`
GROUP BY
  session_id, user_id;

-- 2. Tool Usage Analysis
-- Extract tool names from content (the auto-view `v_tool_completed`
-- exposes `tool_name` directly if you'd rather skip the JSON_VALUE).
SELECT
  JSON_VALUE(content, '$.tool') AS tool_name,
  event_type,
  COUNT(*) as count
FROM `your-project.your-dataset.agent_events`
WHERE event_type IN ('TOOL_STARTING', 'TOOL_COMPLETED', 'TOOL_ERROR')
GROUP BY 1, 2
ORDER BY tool_name, event_type;

-- 3. Granular Cost & Token Estimation
-- Estimate tokens based on content character length (approx 4 chars/token)
SELECT
  session_id,
  COUNT(*) as interaction_count,
  SUM(LENGTH(TO_JSON_STRING(content))) / 4 AS estimated_tokens,
  -- Example cost: $0.0001 per 1k tokens
  ROUND((SUM(LENGTH(TO_JSON_STRING(content))) / 4) / 1000 * 0.0001, 6) AS estimated_cost_usd
FROM `your-project.your-dataset.agent_events`
GROUP BY session_id
ORDER BY estimated_cost_usd DESC
LIMIT 5;

-- 4. AI-Powered Root Cause Analysis (Requires BigQuery ML)
-- Use Gemini to analyze failed sessions
SELECT
  session_id,
  AI.GENERATE(
    ('Analyze this conversation and explain the failure root cause. Log: ', full_conversation),
    connection_id => 'your-project.us.bqml_connection',
    endpoint => 'gemini-2.5-flash'
  ).result AS root_cause_explanation
FROM `your-project.your-dataset.agent_sessions`
WHERE error_message IS NOT NULL
LIMIT 5;

https://lookerstudio.google.com/reporting/create?c.reportId=f1c5b513-3095-44f8-90a2-54953d41b125&ds.ds3.connector=bigQuery&ds.ds3.type=TABLE&ds.ds3.projectId=<your-project-id>&ds.ds3.datasetId=<your-dataset-id>&ds.ds3.tableId=<your-table-id>

from langchain.agents import create_agent
from langchain.messages import HumanMessage
from langchain_google_community.callbacks.bigquery_callback import (
    BigQueryCallbackHandler,
    BigQueryLoggerConfig,
)

# Initialize handler with graph name
handler = BigQueryCallbackHandler(
    project_id="your-project-id",
    dataset_id="agent_analytics",
    table_id="agent_events",
    graph_name="my_agent",
)

# Create your agent
agent = create_agent(llm, tools)

# Use the graph context manager for proper INVOCATION_STARTING/INVOCATION_COMPLETED events
run_metadata = {
    "session_id": "session-123",
    "user_id": "user-456",
    "agent": "my_agent",
}

with handler.graph_context("my_agent", metadata=run_metadata):
    result = agent.invoke(
        {"messages": [HumanMessage(content="What is the weather in Tokyo?")]},
        config={
            "callbacks": [handler],
            "metadata": run_metadata,
        },
    )

-- Query latency by event type
SELECT
    event_type,
    agent,
    COUNT(*) as count,
    ROUND(AVG(CAST(JSON_EXTRACT_SCALAR(latency_ms, '$.total_ms') AS FLOAT64)), 2) as avg_latency_ms,
    ROUND(APPROX_QUANTILES(CAST(JSON_EXTRACT_SCALAR(latency_ms, '$.total_ms') AS FLOAT64), 100)[OFFSET(95)], 2) as p95_latency_ms
FROM `your-project.your-dataset.agent_events`
WHERE DATE(timestamp) = CURRENT_DATE()
  AND event_type IN ('LLM_RESPONSE', 'TOOL_COMPLETED', 'INVOCATION_COMPLETED')
GROUP BY event_type, agent
ORDER BY avg_latency_ms DESC;

from langchain_google_community.callbacks.bigquery_callback import (
    BigQueryCallbackHandler,
    BigQueryLoggerConfig,
)

# Production config: Only log important events
config = BigQueryLoggerConfig(
    event_allowlist=[
        "LLM_RESPONSE",
        "LLM_ERROR",
        "TOOL_COMPLETED",
        "TOOL_ERROR",
        "INVOCATION_COMPLETED",
        "INVOCATION_ERROR",
    ],
)

handler = BigQueryCallbackHandler(
    project_id="your-project-id",
    dataset_id="agent_analytics",
    config=config,
)

# Exclude chain events but log everything else
config = BigQueryLoggerConfig(
    event_denylist=["CHAIN_START", "CHAIN_END"],
)

# Run the dashboard
cd libs/community/examples/bigquery_callback/webapp
pip install -r requirements.txt
uvicorn main:app --port 8001
# Open http://localhost:8001