Introducing the Agent Snap
Flashback: What’s an Agent? “Agents are autonomous LLM-based processes that can interact with external systems to carry out a high-level goal.” Agents are LLM-based systems that can perform actions based on the user’s request and the scenario, determined by the LLM of the Agent system. A minimal agent consists of 1. an LLM component, and 2. tools that the Agent can use. Think of the Agent as a Robot with a brain (LLM) + robotic arms (Tools). Based on the request, the brain can “decide” to do something, and then the arm will carry out the action decided by the brain. Then, depending on the scenario, the brain can determine if more action is needed, or end if the request is complete. The process of an agent We previously introduced the “Agent Driver and Agent Worker“ pipeline pattern, which clearly defines every single operation that would occur in an Agent process. The process of the pattern can be described as follows Agent Driver Define the instruction of the Agent. (System prompt) Format the user’s request into a conversation. (Messages array) Define tools to make available to the Agent. Send all information above into a “loop“, run the Agent worker until the process is complete. Agent Worker Call the LLM with the instructions, conversation, and tool definitions LLM decides… If it is able to complete the request, end the conversation and go to step 7. If tool calls are required, go to step 3. Call the tools. Format the tool result. Add the tool results to the conversation Back to step 1. Request is complete, the agent responds. The rationale From the Agent Driver and the Agent Worker pipeline, here’s an observation: The driver pipeline handles all of the “configuration“ of the Agent. The worker pipeline handles the “operation“ of the Agent. Now, imagine this: If we can package the “Agent operation” into a single module, so that we can create Agents just by providing instructions, and tools. Wouldn’t this be great? This is exactly what Agent Snap does. The Agent Snap combines the PipeLoop Snap and the Agent Worker pipeline, so all of the agent operations happen in a single Snap. Information and prerequisites Now, before dreaming about having your own company of agents, since building agents is now so simple, there is some information to know about and conditions to be met before this can happen. 1. Agent Snaps are model-specific The Agent Snap is a combination of the “loop” and the Agent Worker, therefore, the LLM provider to be used for an Agent Snap is also fixed. This design allows users to stick to their favorite combination of customized model parameters. 2. Function(Tool) definitions must be linked to a pipeline to carry out the execution Previously, in an Agent Worker pipeline, the Tool Calling Snap is connected to Pipeline Execute Snaps to carry out tool calls, but this is no longer the case with the Agent Snap. Instead, a function definition should include the path of the pipeline to carry out the execution if this tool is called. This way, we can ensure every tool call can be performed successfully. If the user does not provide a tool pipeline with the function definition, the Agent Snap will not proceed. 3. Expected Input and Output of a tool pipeline When a tool call is requested by an LLM, the LLM will provide the name of the tool to call and the corresponding parameters to call. The Agent Snap will unwrap the parameters and send them directly to the tool pipeline. Here’s an example: I have a tool get_weather, which takes city: string as a parameter. The LLM decides to call the tool get_weather with the following payload: { "name": "get_weather", "parameters": { "city": "New York City" }, "sl_tool_metadata": { ... } } For this to work, my tool pipeline must be able to accept the input document : {"city": "New York City"} On a side note, the sl_tool_metadata object will also be available to the tool pipeline as the input for APIM and OpenAPI tools. Now, assume my tool pipeline has successfully retrieved the weather of New York City, It’s time for the Agent Snap to collect the result of this tool call. The Agent Snap will collect everything from the output document of the tool pipeline as the tool call result*. So that the LLM can determine the next steps properly. *Note: with one exception, if the output of a “tool pipeline“ contains the field “messages“ or "contents", it will be treated as the conversational history of the “child agent”, which will be filtered and will not be included. Build an Agent with Agent Snap We’ve understood the idea, we’ve gone through the prerequisites, and it’s time to build an Agent. In this example, we have an Agent with 2 tools: a weather tool and a calendar tool. We first start with a prompt generator to format the user input. Then define the tools the Agent can access. Let’s look into one of the tool definitions. In this example tool, we can see the name of the tool, the description of the tool, the parameters, and the path of the tool pipeline to carry out this task. This satisfies the requirement of a tool to be used by an Agent Snap. After we have the tools set, let’s look at the Agent Snap, using the Amazon Bedrock Converse API Agent Snap as an example. The configuration of an Agent Snap is similar to its corresponding Tool calling Snap, except for some extra fields, such as a button to visualize the agent flow, and a section to configure the operation of the Agent, such as iteration limit and number of threads for tool pipeline executions. The Agent Snap handles the whole executional process, and terminates when 1. The request is complete (no more tool calls are required) or 2. An error occurred. Voila! You have created an agent. After the Agent pipeline completes a round of execution, the user can use the “Visualize Agent Flow“ button in the Agent Snap to see the tools that are called by the LLM. Tips and Tricks for the Agent Snap Let’s take a look at the features built into the Agent Snap. Reuse pipelines Most agentic tool calls are processes that can be reused. To minimize execution load, we can use the “Reuse tool pipeline“ feature. This feature allows tool pipeline instances to be reused, so that the Agent will not need to spawn a pipeline every time a tool is called. To use this feature, the tool pipeline to be reused must be “Ultra compatible“; otherwise, the pipeline execution would hang, and the Agent Snap would eventually timeout. Tool call monitoring Agents can be long-running; it’s not rare to have an Agent run multiple iterations. To see what’s happening in the process, Agent Snap has built in monitoring during validation. The user will be able to see the iteration index, the tool that is currently being called, and the parameters that are used for the tool call in the pipeline statistics status bar. Selecting the “Monitor tool call“ option includes the parameter in the status update, which is an opt-in feature. If the user does not wish to expose the information to SnapLogic, the user should disable this. Warnings Agent configuration is a delicate process; a mistake can potentially lead to errors. The Agent Snap has a bunch of built-in warning capabilities, so the user can be better aware of what could go wrong. 1. Agent process completed before all tool calls completed In the Agent Snap, there is an Iteration limit setting, which limits the number of iterations the Agent can run. If the user provided a smaller limit, which caused the Agent to stop while the LLM is still awaiting tool calls, this warning would pop up to signal the user that the execution is incomplete. 2. Tool pipeline path is not defined A function (tool) definition to be used by the Agent Snap should include a tool pipeline path, so the Agent Snap can link to the actual pipeline that carries out the execution. If the pipeline path is not included in the function definition, this warning will pop up to signal the user that the Agent will not proceed. 3. Duplicate tool naming As we try to add more and more tools to the Agent Snap, two tools likely share the same name. The Agent Snap has the ability to rename the tools being sent to the LLM, and then still link to the correct pipeline. There will also be a warning available in the pipeline statistics to alert the user about a change in the behavior. Release Timeframes The Agent Snap is the foundation of the next-generation SnapLogic Agent. We will be releasing 4 Agent Snaps in the November release: Amazon Bedrock Converse API Agent OpenAI Chat Completions Agent Azure OpenAI Chat Completions Agent Google Gemini API Agent To better use the Agent Snaps, we will be introducing new capabilities to some of our Function Generators as well. Here is the list of Function Generator Snaps that will be modified soon: APIM Function Generator Snap OpenAPI Function Generator Snap MCP Function Generator Snap We hope you are as excited as we are about this one.
SnapLogic Test Automation with Robot Framework: A Complete Testing Solution
Introduction In today's fast-paced integration landscape, ensuring the reliability and performance of your SnapLogic pipelines is crucial. We're excited to introduce a comprehensive test automation framework that combines the power of Robot Framework with SnapLogic's APIs to deliver a robust, scalable, and easy-to-use testing solution. This approach leverages the snaplogic-common-robot [PyPI-published library] to provide prebuilt Robot Framework keywords for interacting with SnapLogic Public APIs, integrated within a Docker-based environment.. This lets teams spin up full SnapLogic environments on demand—including Groundplex, databases, and messaging services—so tests run the same way everywhere This blog post explores two key components of our testing ecosystem: snaplogic-common-robot: A PyPI-published library https://pypi.org/project/snaplogic-common-robot/ providing reusable Robot Framework keywords for SnapLogic automation snaplogic-robotframework-examples: A public repository providing a complete testing framework with baseline test suites and Docker-based infrastructure for comprehensive end-to-end pipeline validation Key Features and Benefits 1. Template-Based Testing The framework supports template-driven test cases, allowing you to: Define reusable test patterns Parameterize test execution Maintain consistency across similar test scenarios 2. Intelligent Environment Management The framework automatically: Loads environment variables from multiple .env files Auto-detects JSON values and converts them to appropriate Robot Framework variables Validates required environment variables before test execution Why Robot Framework for SnapLogic Testing? Robot Framework offers several advantages for SnapLogic test automation: Human-readable syntax: Tests are written in plain English, making them accessible to both technical and non-technical team members Keyword-driven approach: Promotes reusability and reduces code duplication Extensive ecosystem: Integrates seamlessly with databases, APIs, and various testing tools Comprehensive reporting: Built-in HTML reports with detailed execution logs CI/CD friendly: Easy integration with Jenkins, GitLab CI, and other automation platforms The Power of Docker-Based Testing Infrastructure One of the most powerful features of our framework is its Docker-based architecture. Isolated Test Environments: Each test run operates in its own containerized environment Groundplex Control: Automatically spin up and tear down Groundplex instances for testing Database Services: Pre-configured containers for Oracle, PostgreSQL, MySQL, SQL Server, DB2, and more Message Queue Systems: Integrated support for Kafka, ActiveMQ, and other messaging platforms Storage Services: MinIO for S3-compatible object storage testing This architecture allows below capabilities: Test in production-like environments without affecting actual production systems Quickly provision and tear down complete testing stacks Run parallel tests with isolated resources Ensure consistency across different testing environments snaplogic-common-robot Library Installation The snaplogic-common-robot library is published on PyPI, making installation straightforward https://pypi.org/project/snaplogic-common-robot/ pip install snaplogic-common-robot Core Components The library provides the below components SnapLogic APIs: Low-level keywords for direct API interactions SnapLogic Keywords: High-level business-oriented keywords for common operations Common Utilities: Database connections, file operations, and utility functions. Dependency Libraries: Install all necessary dependency libraries to run Robot Framework tests for SnapLogic. These libraries support API testing, database operations, Docker container testing, JMS messaging, and AWS integration tools. The following libraries are automatically installed as dependencies when you install snaplogic-common-robot, providing comprehensive API support. This library ecosystem continues to expand as we add support for additional features and capabilities. Snaplogic RobotFramework-examples Repository The snaplogic-robotframework-examples repository demonstrates how to build a complete testing framework using the snaplogic common library.https://github.com/SnapLogic/snaplogic-robotframework-examples Framework Overview Note: This project structure is continuously evolving! We're actively working to make the framework easier and more efficient to use,The structure is subject to change as we iterate on improvements to enhance developer experience and framework efficiency. The framework follows a modular architecture with clear separation of concerns: Configuration Layer .env and .env.example manage environment variables for sensitive credentials and URLs env_files/ folder have all details required for creating accounts Makefile provides a central command interface for all build and test operations docker-compose.yml orchestrates the entire multi-container environment with a single command Build Automation makefiles/ directory contains modular scripts organized by service type (databases, messaging, mocks) Each service category has dedicated makefiles for independent lifecycle management Infrastructure docker/ holds Docker configurations for all services (Groundplex, Oracle, PostgreSQL, Kafka) env_files/ stores service-specific environment variables to isolate configuration Containerized approach ensures reproducible test environments across all systems Test Organization test/suite/ contains Robot Framework test suites organized by pipeline functionality test/test_data/ provides input files and expected outputs for validation Tests are grouped logically (Oracle, PostgreSQL+S3, Kafka) for easy maintenance Pipeline Assets src/pipelines/ stores the actual SnapLogic SLP files being tested src/tools/ includes helper utilities and requirements.txt with Python dependencies The snaplogic-common-robot library is installed via requirements.txt, providing reusable keywords Test Reporting Robot Framework automatically generates comprehensive test reports after each execution report.html provides a high-level summary with pass/fail statistics and execution timeline log.html offers detailed step-by-step execution logs with keyword-level information output.xml contains structured test results in XML format for CI/CD integration Reports include screenshots, error messages, and detailed traceability for debugging All reports are timestamped and can be archived for historical analysis Supporting Components travis_scripts/ enables CI/CD automation for continuous testing README/ holds project documentation and setup guides Key Architecture Benefits Modular design allows independent service management Docker isolation ensures consistent test environments Makefile automation simplifies complex operations Clear directory structure improves maintainability CI/CD integration enables automated testing workflows Integration with CI/CD Pipelines One of the most powerful aspects of our Robot Framework testing solution is its seamless integration with CI/CD pipelines. This enables continuous testing, ensuring that every code change is automatically validated against your SnapLogic integrations. Why CI/CD Integration Matters In modern DevOps practices, manual testing becomes a bottleneck. By integrating our Robot Framework tests into your CI/CD pipeline, you achieve: Automatic Test Execution: Tests run automatically on every commit, pull request, or scheduled interval Early Bug Detection: Issues are caught immediately, not days or weeks later in production Consistent Testing: The same tests run every time, eliminating human error and variability Fast Feedback Loop: Developers know within minutes if their changes broke existing integrations Quality Gates: Prevent deployments if tests fail, ensuring only validated code reaches production Jenkins is one of the most popular CI/CD tools, and integrating our Robot Framework tests is straightforward. How It Works? Stage 1: Prepare Environment Install SnapLogic common Robot library and required dependencies Stage 2: Start Docker Services Launches Groundplex, Oracle DB, Kafka, and MinIO containers Stage 3: Run Robot Framework Tests Execute test suites in parallel across 4 threads using pabot Stage 4: Publish Test Results Generate HTML reports, XML results, and test artifacts and can upload to S3. Stage 5: Send Notifications Distributes test results via Slack. Post: Cleanup Tears down containers, removes temp files, archives logs Slack Notifications include the below details Our CI/CD pipeline automatically sends detailed test execution reports to Slack, providing immediate visibility into test results for the entire team. HTML Reports have the below details Robot Framework automatically generates comprehensive HTML reports after each test execution, providing detailed insights into test results, performance, and execution patterns. Real-World Benefits Here's what this means for your team: For Developers Push code with confidence - Tests run automatically Get feedback in minutes - No waiting for QA cycles Fix issues immediately - While the code is still fresh in your mind For QA Teams Focus on exploratory testing - Let automation handle regression Better test coverage - Tests run on every single change Clear reports - See exactly what's tested and what's not Future Enhancements We're continuously improving the framework with planned features include: Enhanced support for more end points Integration with cloud storage services Advanced performance testing capabilities Enhanced security testing features Conclusion The combination of snaplogic-common-robot library and snaplogic-robotframework-examples framework provides a powerful, scalable solution for SnapLogic test automation. By leveraging Docker's containerization capabilities, Robot Framework's simplicity, and SnapLogic's robust APIs, teams can: Reduce testing time from hours to minutes Increase test coverage with automated end-to-end scenarios Improve reliability through consistent, repeatable tests Enable continuous testing in CI/CD pipelines Whether you're testing simple pipeline transformations or complex multi-system integrations, this framework provides the tools and patterns needed for comprehensive SnapLogic testing. Getting Involved We welcome contributions from the SnapLogic community! Here's how you can get involved: Try the Framework: Install snaplogic-common-robot and run the example tests Report Issues: Help us improve by reporting bugs or suggesting enhancements Contribute Code: Submit pull requests with new keywords or test patterns Share Your Experience: Let us know how you're using the framework in your organization Resources snaplogic-common-robot on PyPI: pip install snaplogic-common-robot https://pypi.org/project/snaplogic-common-robot/ snaplogic-robotframework-example repo: https://github.com/SnapLogic/snaplogic-robotframework-examples Documentation: Comprehensive HTML documentation available after installation via README folder Community Support: Join the discussion in SnapLogic Community forums Start automating your SnapLogic tests today and experience the power of comprehensive, containerized test automation! Questions? We're Here to Help! We hope this comprehensive guide helps you get started with automated testing for your SnapLogic integrations. The combination of snaplogic-common-robot and Docker-based infrastructure provides a powerful foundation for building reliable, scalable test automation. Have questions or need assistance implementing this framework? The SLIM (SnapLogic Intelligent Modernization) team is here to support you! We'd love to hear about your use cases, help you overcome any challenges, or discuss how this framework can be customized for your specific needs. Contact the SLIM Team: Reach out to us directly through the SnapLogic Community forums Tag us in your questions with @slim-team Email us at: slim-team@snaplogic.com We're committed to helping you achieve testing excellence and look forward to seeing how you leverage this framework to enhance your SnapLogic automation journey! Happy Testing! The SLIM TeamSnapLogic MCP Support
Introduction Since the inception of the Model Context Protocol (MCP), we've been envisioning and designing how it can be integrated into the SnapLogic platform. We've recently received a significant number of inquiries about MCP, and we're excited to share our progress, the features we'll be supporting, our release timeline, and how you can get started creating MCP servers and clients within SnapLogic. If you're interested, we encourage you to reach out! Understanding the MCP Protocol The MCP protocol allows tools, data resources, and prompts to be published by an MCP server in a way that Large Language Models (LLMs) can understand. This empowers LLMs to autonomously interact with these resources via an MCP client, expanding their capabilities to perform actions, retrieve information, and execute complex workflows. MCP Protocol primarily supports: Tools: Functions an LLM can invoke (e.g., data lookups, operational tasks). Resources: File-like data an LLM can read (e.g., API responses, file contents). Prompts: Pre-written templates to guide LLM interaction with the server. Sampling (not widely used): Allows client-hosted LLMs to be used by remote MCP servers. An MCP client can, therefore, request to list available tools, call specific tools, list resources, or read resource content from a server. Transport and Authentication MCP protocol offers flexible transport options, including STDIO or HTTP (SSE or Streamable-HTTP) for local deployments, and HTTP (SSE or Streamable-HTTP) for remote deployments. While the protocol proposes OAuth 2.1 for authentication, an MCP server can also use custom headers for security. Release Timeline We're excited to bring MCP support to SnapLogic with two key releases: August Release: MCP Client Support We'll be releasing two new snaps: the MCP Function Generator Snap and the MCP Invoke Snap. These will be available in the AgentCreator Experimental (Beta) Snap Pack. With these Snaps, your SnapLogic agent can access the services and resources available on the public MCP server. Late Q3 Release: MCP Server Support Our initial MCP server support will focus on tool operations, including the ability to list tools and call tools. For authentication, it will support custom header-based authentication. Users will be able to leverage the MCP Server functionality by subscribing to this feature. If you're eager to be among the first to test these new capabilities and provide feedback, please reach out to the Project Manager Team, at pm-team@snaplogic.com. We're looking forward to seeing what you build with SnapLogic MCP. SnapLogic MCP Client MCP Clients in SnapLogic enable users to connect to MCP servers as part of their Agent. An example can be connecting to the Firecrawl MCP server for a data scraping Agent, or other use cases that can leverage the created MCP servers. The MCP Client support in SnapLogic consists of two Snaps, the MCP Function Generator Snap and the MCP Invoke Snap. From a high-level perspective, the MCP Function generator Snap allows users to list available tools from an MCP server, and the MCP Invoke Snap allows users to perform operations such as call tools, list resources, and read resources from an MCP server. Let’s dive into the individual pieces. MCP SSE Account To connect to an MCP Server, we will need an account to specify the URI of the server to connect to. Properties URI The URI of the server to connect to. Don’t need to include the /sse path Additional headers Additional HTTP headers to be sent to the server Timeout The timeout value in seconds, if the result is not returned within the timeout, the Snap will return an error. MCP Function Generator Snap The MCP Function Generator Snap enables users to retrieve the list of tools as SnapLogic function definitions to be used in a Tool Calling Snap. Properties Account An MCP SSE account is required to connect to an MCP Server. Expose Tools List all available tools from an MCP server as SnapLogic function definitions Expose Resources Add list_resources, read_resource as SnapLogic function definitions to allow LLMs to use resources/read and resources/list (MCP Resources). Definitions for list resource and read resource [ { "sl_type": "function", "name": "list_resources", "description": "This function lists all available resources on the MCP server. Return a list of resources with their URIs.", "strict": false, "sl_tool_metadata": { "operation": "resources/list" } }, { "sl_type": "function", "name": "read_resource", "description": "This function returns the content of the resource from the MCP server given the URI of the resource.", "strict": false, "sl_tool_metadata": { "operation": "resources/read" }, "parameters": [ { "name": "uri", "type": "STRING", "description": "Unique identifier for the resource", "required": true } ] } ] MCP Invoke Snap The MCP Invoke Snap enables users to perform operations such as tools/call, resources/list, and resources/read to an MCP server. Properties Account An account is required to use the MCP Invoke Snap Operation The operation to perform on the MCP server. The operation must be one of tools/call, resources/list, or resources/read Tool Name The name of the tool to call. Only enabled and required when the operation is tools/call Parameters The parameters to be added to the operation. Only enabled for resources/read and tools/call. Required for resources/read, and optional for tools/call, based on the tool. MCP Agents in pipeline action MCP Agent Driver pipeline An MCP Agent Driver pipeline is like any other MCP Agent pipeline; we’ll need to provide the system prompt, user prompt, and run it with the PipeLoop Snap. MCP Agent Worker pipeline Here’s an example of an MCP Agent with a single MCP Server connection. The MCP Agent Worker is connected to one MCP Server. MCP Client Snaps can be used together with AgentCreator Snaps, such as the Multi-Pipeline Function Generator and Pipeline Execute Snap, as SnapLogic Functions, tools. This allows users to use tools provided by MCP servers and internal tools, without sacrificing safety and freedom when building an Agent. Agent Worker with MCP Client Snaps SnapLogic MCP Server In SnapLogic, an MCP Server allows you to expose SnapLogic pipelines as dynamic tools that can be discovered and invoked by language models or external systems. By registering an MCP Server, you effectively provide a API that language models and other clients can use to perform operations such as data retrieval, transformation, enrichment, or automation, all orchestrated through SnapLogic pipelines. For the initial phase, we'll support connections to the server via HTTP + SSE. Core Capabilities The MCP Server provides two core capabilities. The first is listing tools, which returns structured metadata that describes the available pipelines. This metadata includes the tool name, a description, the input schema in JSON Schema format, and any additional relevant information. This allows clients to dynamically discover which operations are available for invocation. The second capability is calling tools, where a specific pipeline is executed as a tool using structured input parameters, and the output is returned. Both of these operations—tool listing and tool calling—are exposed through standard JSON-RPC methods, specifically tools/list and tools/call, accessible over HTTP. Prerequisite You'll need to prepare your tool pipelines in advance. During the server creation process, these can be added and exposed as tools for external LLMs to use. MCP Server Pipeline Components A typical MCP server pipeline consists of four Snaps, each with a dedicated role: 1. Router What it does: Routes incoming JSON requests—which differ from direct JSON-RPC requests sent by an MCP client—to either the list tools branch or the call tool branch. How: Examines the request payload (typically the method field) to determine which action to perform. 2. Multi-Pipeline Function Generator (Listing Tools) What it does: Converts a list of pipeline references into tool metadata. This is where you define the pipelines you want the server to expose as tools. Output: For each pipeline, generates: Tool name Description Parameters (as JSON Schema) Other metadata Purpose: Allows clients (e.g., an LLM) to query what tools are available without prior knowledge. 3. Pipeline Execute (Calling Tools) What it does: Dynamically invokes the selected SnapLogic pipeline and returns structured outputs. How: Accepts parameters encoded in the request body, maps them to the pipeline’s expected inputs, and executes the pipeline. Purpose: Provides flexible runtime execution of tools based on user or model requests. 4. Union What it does: Merges the result streams from both branches (list and call) into a single output stream for consistent response formatting. Request Flows Below are example flows showing how requests are processed: 🟢 tools/list Client sends a JSON-RPC request with method = "tools/list". Router directs the request to the Multi-Pipeline Function Generator. Tool metadata is generated and returned in the response. Union Snap merges and outputs the content. ✅ Result: The client receives a JSON list describing all available tools. �� tools/call Client sends a JSON-RPC request with method = "tools/call" and the tool name + parameters. Router sends this to the Pipeline Execute Snap. The selected pipeline is invoked with the given parameters. Output is collected and merged via Union. ✅ Result: The client gets the execution result of the selected tool. Registering an MCP Server Once your MCP server pipeline is created: Create a Trigger Task and Register as an MCP Server Navigate to the Designer > Create Trigger Task Choose a Groundplex. (Note: This capability currently requires a Groundplex, not a Cloudplex.) Select your MCP pipeline. Click Register as MCP server Configure node and authentication. Find your MCP Server URL Navigate to the Manager > Tasks The Task Details page exposes a unique HTTP endpoint. This endpoint is treated as your MCP Server URL. After registration, clients such as AI models or orchestration engines can interact with the MCP Server by calling the /tools/list endpoint to discover the available tools, and the /tools/call endpoint to invoke a specific tool using a structured JSON payload. Connect to a SnapLogic MCP Server from a Client After the MCP server is successfully published, using the SnapLogic MCP server is no different from using other MCP servers running in SSE mode. It can be connected to by any MCP client that supports SSE mode; all you need is the MCP Server URL (and the Bearer Token if authentication is enabled during server registration). Configuration First, you need to add your MCP server in the settings of the MCP client. Taking Claude Desktop as an example, you'll need to modify your Claude Desktop configuration file. The configuration file is typically located at: macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json Add your remote MCP server configuration to the mcpServers section: { "mcpServers": { "SL_MCP_server": { "command": "npx", "args": [ "mcp-remote", "http://devhost9000.example.com:9000/mcp/6873ff343a91cab6b00014a5/sse", "--header", "Authorization: Bearer your_token_here" ] } } } Key Components Server Name: SL_MCP_server - A unique identifier for your MCP server Command: npx - Uses the Node.js package runner to execute the mcp-remote package URL: The SSE endpoint URL of your remote MCP server (note the /sse suffix) Authentication: Use the --header flag to include authorization tokens if the server enabled authentication Requirements Ensure you have Node.js installed on your system, as the configuration uses npx to run the mcp-remote package. Replace the example URL and authorization token with your actual server details before saving the configuration. After updating the configuration file, restart Claude Desktop for the changes to take effect. To conclude, the MCP Server in SnapLogic is a framework that allows you to expose pipelines as dynamic tools accessible through a single HTTP endpoint. This capability is designed for integration with language models and external systems that need to discover and invoke SnapLogic workflows at runtime. MCP Servers make it possible to build flexible, composable APIs that return structured results, supporting use cases such as conversational AI, automated data orchestration, and intelligent application workflows. Conclusion SnapLogic's integration of the MCP protocol marks a significant leap forward in empowering LLMs to dynamically discover and invoke SnapLogic pipelines as sophisticated tools, transforming how you build conversational AI, automate complex data orchestrations, and create truly intelligent applications. We're excited to see the innovative solutions you'll develop with these powerful new capabilities.
OpenAI Responses API
Introduction OpenAI announced the Responses API, their most advanced and versatile interface for building intelligent AI applications. Supporting both text and image inputs with rich text outputs, this API enables dynamic, stateful conversations that remember and build on previous interactions, making AI experiences more natural and context-aware. It also unlocks powerful capabilities through built-in tools such as web search, file search, code interpreter, and more, while enabling seamless integration with external systems via function calling. Its event-driven design delivers clear, structured updates at every step, making it easier than ever to create sophisticated, multi-step AI workflows. Key features include: Stateful conversations via the previous response ID Built-in tools like web search, file search, code interpreter, MCP, and others Access to advanced models available exclusively, such as o1-pro Enhanced support for reasoning models with reasoning summaries and efficient context management through previous response ID or encrypted reasoning items Clear, event-based outputs that simplify integration and control While the Chat Completions API remains fully supported and widely used, OpenAI plans to retire the Assistants API in the first half of 2026. To support the adoption of the Responses API, two new Snaps have been introduced: OpenAI Chat Completions ⇒ OpenAI Responses API Generation OpenAI Tool Calling ⇒ OpenAI Responses API Tool Calling Both Snaps are fully compatible with existing upstream and downstream utility Snaps, including the OpenAI Prompt Generator, OpenAI Multimodal Content Generator, all Function Generators (Multi-Pipeline, OpenAPI, and APIM), the Function Result Generator, and the Message Appender. This allows existing pipelines and familiar development patterns to be reused while gaining access to the advanced features of the Responses API. OpenAI Responses API Generation The OpenAI Responses API Generation Snap is designed to support OpenAI’s newest Responses API, enabling more structured, stateful, and tool-augmented interactions. While it builds upon the familiar interface of the Chat Completions Snap, several new properties and behavioral updates have been introduced to align with the Responses API’s capabilities. New properties Message: The input sent to the LLM. This field replaces the previous Use message payload, Message payload, and Prompt properties in the OpenAI Chat Completions Snap, consolidating them into a single input. It removes ambiguity between "prompt" as raw text and as a template, and supports both string and list formats. Previous response ID: The unique ID of the previous response to the model. Use this to create multi-turn conversations. Model parameters Reasoning summary: For reasoning models, provides a summary of the model’s reasoning process, aiding in debugging and understanding the model's reasoning process. The property can be none, auto, or detailed. Advanced prompt configurations Instructions: Applied only to the current response, making them useful for dynamically swapping instructions between turns. To persist instructions across turns when using previous_response_id, the developer message in the OpenAI Prompt Generator Snap should be used. Advanced response configurations Truncation: Defines how to handle input that exceeds the model’s context window. auto allows the model to truncate the middle of the conversation to fit, while disabled (default) causes the request to fail with a 400 error if the context limit is exceeded. Include reasoning encrypted content: Includes an encrypted version of reasoning tokens in the output, allowing reasoning items to persist when the store is disabled. Built-in tools Web search: Enables the model to access up-to-date information from the internet to answer queries beyond its training data. Web search type Search context size User location: an approximate user location including city, region, country, and timezone to deliver more relevant search results. File search: Allows the model to retrieve information from documents or files. Vector store IDs Maximum number of results Include search results: Determines whether raw search results are included in the response for transparency or debugging. Ranker Score threshold Filters: Additional metadata-based filters to refine search results. For more details on using filters, see Metadata Filtering. Advanced tool configuration Tool choice: A new option, SPECIFY A BUILT-IN TOOL, allows specifying that the model should use a built-in tool to generate a response. Note that the OpenAI Responses API Generation Snap does not support the response count or stop sequences properties, as these are not available in the Responses API. Additionally, the message user name, which may be specified in the Prompt Generator Snap, is not supported and will be ignored if included. Model response of Chat Completions vs Responses API Chat Completions API Responses API The Responses API introduces an event-driven output structure that significantly enhances how developers build and manage AI-powered applications compared to the traditional Chat Completions API. While the Chat Completions API returns a single, plain-text response within the choices array, the Responses API provides an output array containing a sequence of semantic event items—such as reasoning, message, function_call, web_search_call, and more—that clearly delineate each step in the model's reasoning and actions. This structured approach allows developers to easily track and interpret the model's behavior, facilitating more robust error handling and smoother integration with external tools. Moreover, the response from the Responses API includes the model parameters settings, providing additional context for developers. Pipeline examples Built-in tool: web search This example demonstrates how to use the built-in web search tool. In this pipeline, the user’s location is specified to ensure the web search targets relevant geographic results. System prompt: You are a friendly and helpful assistant. Please use your judge to decide whether to use the appropriate tools or not to answer questions from the user. Prompt: Can you recommend 2 good sushi restaurants near me? Output: As a result, the output contains both a web search call and a message. The model uses the web search to find and provide recommendations based on current data, tailored to the specified location. Built-in tool: File search This example demonstrates how the built-in file search tool enables the model to retrieve information from documents stored in a vector store during response generation. In this case, the file wildfire_stats.pdf has been uploaded. You can create and manage vector stores through the Vector Store management page. Prompt: What is the number of Federal wildfires in 2018 Output: The output array contains a file_search_call event, which includes search results in its results field. These results provide matched text, metadata, and relevance scores from the vector store. This is followed by a message event, where the model uses the retrieved information to generate a grounded response. The presence of detailed results in the file_search_call is enabled by selecting the Include file search results option. OpenAI Responses API Tool Calling The OpenAI Responses API Tool Calling Snap is designed to support function calling using OpenAI’s Responses API. It works similarly to the OpenAI Tool Calling Snap (which uses the Chat Completions API), but is adapted to the event-driven response structure of the Responses API and supports stateful interactions via the previous response ID. While it shares much of its configuration with the Responses API Generation Snap, it is purpose-built for workflows involving function calls. Existing LLM agent pipeline patterns and utility Snaps—such as the Function Generator and Function Result Generator—can continue to be used with this Snap, just as with the original OpenAI Tool Calling Snap. The primary difference lies in adapting the Snap configuration to accommodate the Responses API’s event-driven output, particularly the structured function_call event item in the output array. The Responses API Tool Calling Snap provides two output views, similar to the OpenAI Tool Calling Snap, with enhancements to simplify building agent pipelines and support stateful interactions using the previous response ID: Model response view: The complete API response, including extra fields: messages: an empty list if store is enabled, or the full message history—including messages payload and model response—if disabled (similar to the OpenAI Tool Calling Snap). When using stateful workflows, message history isn’t needed because the previous response ID is used to maintain context. has_tool_call: a boolean indicating whether the response includes a tool call. Since the Responses API no longer includes the finish_reason: "tool_calls" field, this new field makes it easier to create stop conditions in the pipeloop Snap within the agent driver pipeline. Tool call view: Displays the list of function calls made by the model during the interaction. Tool Call View of Chat Completions vs Responses API Uses id as the function call identifier when sending back the function result. Tool call properties (name, arguments) are nested inside the function field. Each tool call includes: • id: the unique event ID • call_id: used to reference the function call when returning the result The tool call structure is flat — name and arguments are top-level fields. Building LLM Agent Pipelines To build LLM agent pipelines with the OpenAI Responses API Tool Calling Snap, you can reuse the same agent pipeline pattern described in Introducing Tool Calling Snaps and LLM Agent Pipelines. Only minor configuration changes are needed to support the Responses API. Agent Driver Pipeline The primary change is in the PipeLoop Snap configuration, where the stop condition should now check the has_tool_call field, since the Responses API no longer includes the finish_reason:"tool_calls". Agent Worker Pipeline Fields mapping A Mapper Snap is used to prepare the related fields for the OpenAI Responses API Tool Calling Snap. OpenAI Responses API Tool Calling The key changes are in this Snap’s configuration to support the Responses API’s stateful interactions. There are two supported approaches: Option 1: Use Store (Recommended) Leverages the built-in state management of the Responses API. Enable Store Use Previous Response ID Send only the function call results as the input messages for the next round. (messages field in the Snap’s output will be an empty array, so you can still use it in the Message Appender Snap to collect tool results.) Option 2: Maintain Conversation History in Pipeline Similar to the approach used in the Chat Completions API. Disable Store Include the full message history in the input (messages field in the Snap’s output contains message history) (Optional) Enable Include Reasoning Encrypted Content (for reasoning models) to preserve reasoning context efficiently OpenAI Function Result Generator As explained in Tool Call View of Chat Completions vs Responses API section, the Responses API includes both an id and a call_id. You must use the call_id to construct the function call result when sending it back to the model. Conclusion The OpenAI Responses API makes AI workflows smarter and more adaptable, with stateful interactions and built-in tools. SnapLogic’s OpenAI Responses API Generation and Tool Calling Snaps bring these capabilities directly into your pipelines, letting you take advantage of advanced features like built-in tools and event-based outputs with only minimal adjustments. By integrating these Snaps, you can seamlessly enhance your workflows and fully unlock the potential of the Responses API.OpenAI Responses API
Introduction OpenAI announced the Responses API, their most advanced and versatile interface for building intelligent AI applications. Supporting both text and image inputs with rich text outputs, this API enables dynamic, stateful conversations that remember and build on previous interactions, making AI experiences more natural and context-aware. It also unlocks powerful capabilities through built-in tools such as web search, file search, code interpreter, and more, while enabling seamless integration with external systems via function calling. Its event-driven design delivers clear, structured updates at every step, making it easier than ever to create sophisticated, multi-step AI workflows. Key features include: Stateful conversations via the previous response ID Built-in tools like web search, file search, code interpreter, MCP, and others Access to advanced models available exclusively, such as o1-pro Enhanced support for reasoning models with reasoning summaries and efficient context management through previous response ID or encrypted reasoning items Clear, event-based outputs that simplify integration and control While the Chat Completions API remains fully supported and widely used, OpenAI plans to retire the Assistants API in the first half of 2026. To support the adoption of the Responses API, two new Snaps have been introduced: OpenAI Chat Completions ⇒ OpenAI Responses API Generation OpenAI Tool Calling ⇒ OpenAI Responses API Tool Calling Both Snaps are fully compatible with existing upstream and downstream utility Snaps, including the OpenAI Prompt Generator, OpenAI Multimodal Content Generator, all Function Generators (Multi-Pipeline, OpenAPI, and APIM), the Function Result Generator, and the Message Appender. This allows existing pipelines and familiar development patterns to be reused while gaining access to the advanced features of the Responses API. OpenAI Responses API Generation The OpenAI Responses API Generation Snap is designed to support OpenAI’s newest Responses API, enabling more structured, stateful, and tool-augmented interactions. While it builds upon the familiar interface of the Chat Completions Snap, several new properties and behavioral updates have been introduced to align with the Responses API’s capabilities. New properties Message: The input sent to the LLM. This field replaces the previous Use message payload, Message payload, and Prompt properties in the OpenAI Chat Completions Snap, consolidating them into a single input. It removes ambiguity between "prompt" as raw text and as a template, and supports both string and list formats. Previous response ID: The unique ID of the previous response to the model. Use this to create multi-turn conversations. Model parameters Reasoning summary: For reasoning models, provides a summary of the model’s reasoning process, aiding in debugging and understanding the model's reasoning process. The property can be none, auto, or detailed. Advanced prompt configurations Instructions: Applied only to the current response, making them useful for dynamically swapping instructions between turns. To persist instructions across turns when using previous_response_id, the developer message in the OpenAI Prompt Generator Snap should be used. Advanced response configurations Truncation: Defines how to handle input that exceeds the model’s context window. auto allows the model to truncate the middle of the conversation to fit, while disabled (default) causes the request to fail with a 400 error if the context limit is exceeded. Include reasoning encrypted content: Includes an encrypted version of reasoning tokens in the output, allowing reasoning items to persist when the store is disabled. Built-in tools Web search: Enables the model to access up-to-date information from the internet to answer queries beyond its training data. Web search type Search context size User location: an approximate user location including city, region, country, and timezone to deliver more relevant search results. File search: Allows the model to retrieve information from documents or files. Vector store IDs Maximum number of results Include search results: Determines whether raw search results are included in the response for transparency or debugging. Ranker Score threshold Filters: Additional metadata-based filters to refine search results. For more details on using filters, see Metadata Filtering. Advanced tool configuration Tool choice: A new option, SPECIFY A BUILT-IN TOOL, allows specifying that the model should use a built-in tool to generate a response. Note that the OpenAI Responses API Generation Snap does not support the response count or stop sequences properties, as these are not available in the Responses API. Additionally, the message user name, which may be specified in the Prompt Generator Snap, is not supported and will be ignored if included. Model response of Chat Completions vs Responses API Chat Completions API Responses API The Responses API introduces an event-driven output structure that significantly enhances how developers build and manage AI-powered applications compared to the traditional Chat Completions API. While the Chat Completions API returns a single, plain-text response within the choices array, the Responses API provides an output array containing a sequence of semantic event items—such as reasoning, message, function_call, web_search_call, and more—that clearly delineate each step in the model's reasoning and actions. This structured approach allows developers to easily track and interpret the model's behavior, facilitating more robust error handling and smoother integration with external tools. Moreover, the response from the Responses API includes the model parameters settings, providing additional context for developers. Pipeline examples Built-in tool: web search This example demonstrates how to use the built-in web search tool. In this pipeline, the user’s location is specified to ensure the web search targets relevant geographic results. System prompt: You are a friendly and helpful assistant. Please use your judge to decide whether to use the appropriate tools or not to answer questions from the user. Prompt: Can you recommend 2 good sushi restaurants near me? Output: As a result, the output contains both a web search call and a message. The model uses the web search to find and provide recommendations based on current data, tailored to the specified location. Built-in tool: File search This example demonstrates how the built-in file search tool enables the model to retrieve information from documents stored in a vector store during response generation. In this case, the file wildfire_stats.pdf has been uploaded. You can create and manage vector stores through the Vector Store management page. Prompt: What is the number of Federal wildfires in 2018 Output: The output array contains a file_search_call event, which includes search results in its results field. These results provide matched text, metadata, and relevance scores from the vector store. This is followed by a message event, where the model uses the retrieved information to generate a grounded response. The presence of detailed results in the file_search_call is enabled by selecting the Include file search results option. OpenAI Responses API Tool Calling The OpenAI Responses API Tool Calling Snap is designed to support function calling using OpenAI’s Responses API. It works similarly to the OpenAI Tool Calling Snap (which uses the Chat Completions API), but is adapted to the event-driven response structure of the Responses API and supports stateful interactions via the previous response ID. While it shares much of its configuration with the Responses API Generation Snap, it is purpose-built for workflows involving function calls. Existing LLM agent pipeline patterns and utility Snaps—such as the Function Generator and Function Result Generator—can continue to be used with this Snap, just as with the original OpenAI Tool Calling Snap. The primary difference lies in adapting the Snap configuration to accommodate the Responses API’s event-driven output, particularly the structured function_call event item in the output array. The Responses API Tool Calling Snap provides two output views, similar to the OpenAI Tool Calling Snap, with enhancements to simplify building agent pipelines and support stateful interactions using the previous response ID: Model response view: The complete API response, including extra fields: messages: an empty list if store is enabled, or the full message history—including messages payload and model response—if disabled (similar to the OpenAI Tool Calling Snap). When using stateful workflows, message history isn’t needed because the previous response ID is used to maintain context. has_tool_call: a boolean indicating whether the response includes a tool call. Since the Responses API no longer includes the finish_reason: "tool_calls" field, this new field makes it easier to create stop conditions in the pipeloop Snap within the agent driver pipeline. Tool call view: Displays the list of function calls made by the model during the interaction. Tool Call View of Chat Completions vs Responses API Uses id as the function call identifier when sending back the function result. Tool call properties (name, arguments) are nested inside the function field. Each tool call includes: • id: the unique event ID • call_id: used to reference the function call when returning the result The tool call structure is flat — name and arguments are top-level fields. Building LLM Agent Pipelines To build LLM agent pipelines with the OpenAI Responses API Tool Calling Snap, you can reuse the same agent pipeline pattern described in Introducing Tool Calling Snaps and LLM Agent Pipelines. Only minor configuration changes are needed to support the Responses API. Agent Driver Pipeline The primary change is in the PipeLoop Snap configuration, where the stop condition should now check the has_tool_call field, since the Responses API no longer includes the finish_reason:"tool_calls". Agent Worker Pipeline Fields mapping A Mapper Snap is used to prepare the related fields for the OpenAI Responses API Tool Calling Snap. OpenAI Responses API Tool Calling The key changes are in this Snap’s configuration to support the Responses API’s stateful interactions. There are two supported approaches: Option 1: Use Store (Recommended) Leverages the built-in state management of the Responses API. Enable Store Use Previous Response ID Send only the function call results as the input messages for the next round. (messages field in the Snap’s output will be an empty array, so you can still use it in the Message Appender Snap to collect tool results.) Option 2: Maintain Conversation History in Pipeline Similar to the approach used in the Chat Completions API. Disable Store Include the full message history in the input (messages field in the Snap’s output contains message history) (Optional) Enable Include Reasoning Encrypted Content (for reasoning models) to preserve reasoning context efficiently OpenAI Function Result Generator As explained in Tool Call View of Chat Completions vs Responses API section, the Responses API includes both an id and a call_id. You must use the call_id to construct the function call result when sending it back to the model. Conclusion The OpenAI Responses API makes AI workflows smarter and more adaptable, with stateful interactions and built-in tools. SnapLogic’s OpenAI Responses API Generation and Tool Calling Snaps bring these capabilities directly into your pipelines, letting you take advantage of advanced features like built-in tools and event-based outputs with only minimal adjustments. By integrating these Snaps, you can seamlessly enhance your workflows and fully unlock the potential of the Responses API.
Simplify Your LLM Workflows: Integrating Vertex AI RAG with SnapLogic
This document explores the integration of Google Cloud's Vertex AI Retrieval Augmented Generation (RAG) capabilities with SnapLogic. We will delve into how Vertex AI RAG functions, its benefits over traditional vector databases, and practical applications within the SnapLogic platform. The guide will cover setting up and utilizing Vertex AI RAG, automating knowledge feeds, and integrating with SnapLogic's Generate snaps for enhanced LLM performance. Vertex AI RAG Engine The Vertex AI RAG Engine streamlines the retrieval-augmented generation (RAG) process through two primary steps: Knowledge Management: The Vertex AI RAG Engine establishes and maintains a knowledge base by creating a corpus, which serves as an index for storing source files. Retrieval Query: Upon receiving a prompt, the Vertex AI RAG Engine efficiently searches this knowledge base to identify and retrieve information most relevant to the request. The Vertex AI RAG Engine integrates Google Cloud's Vertex AI with the RAG architecture to produce accurate and contextually relevant LLM responses. It covers tasks related to managing knowledge by creating a corpus as an index for source files. For processing, it efficiently retrieves relevant information from this knowledge base when a prompt is received, then leverages the LLM to generate a response based on the retrieved context. Difference between Vector Database While both traditional vector databases and the Vertex AI RAG Engine are designed to enhance LLM responses by providing external knowledge, they differ significantly in their approach and capabilities. Vector Databases Vector databases primarily focus on storing and querying vector embeddings. To use them with an LLM for RAG, you typically need to: Manually manage embedding generation: You are responsible for generating vector embeddings for your source data using an embedding model. Handle retrieval logic: You need to implement the logic for querying the vector database, retrieving relevant embeddings, and then mapping them back to the original source text. Integrate with LLM: The retrieved text then needs to be explicitly passed to the LLM as part of the prompt. No built-in LLM integration: They are agnostic to the LLM and require manual integration for RAG workflows. Vertex AI RAG Engine The Vertex AI RAG Engine offers a more integrated and streamlined solution, abstracting away much of the complexity. Key differences include: Integrated knowledge management: It handles the entire lifecycle of your knowledge base, from ingesting raw source files to indexing and managing the corpus. You don't need to manually generate embeddings or manage vector storage. Automated retrieval: The engine automatically performs the retrieval of relevant information from its corpus based on the user's prompt. Seamless LLM integration: It's designed to work directly with Vertex AI's LLMs, handling the contextualization of the prompt with retrieved information before passing it to the LLM. End-to-end solution: It provides a more comprehensive solution for RAG, simplifying the development and deployment of RAG-powered applications. In essence, a traditional vector database is a component that requires significant orchestration to implement RAG. In contrast, the Vertex AI RAG Engine is a more complete, managed service that simplifies the entire RAG workflow by providing integrated knowledge management, retrieval, and LLM integration. This fundamental benefit allows for a significant simplification of the often complex RAG processing pipeline. By streamlining this process, we can achieve greater efficiency, reduce potential points of failure, and ultimately deliver more accurate and relevant results when leveraging large language models (LLMs) for tasks that require external knowledge. This simplification not only improves performance but also enhances the overall manageability and scalability of RAG-based systems, making them more accessible and effective for a wider range of applications. Using Vertex AI's RAG Engine with Generative AI (instead of directly via the Gemini API) offers advantages. It enhances query-related information retrieval through built-in tools, streamlining data access for generative AI models. This native integration within Vertex AI optimizes information flow, reduces complexity, and leads to a more robust system for retrieval-augmented generation. Vertex AI RAG Engine in SnapLogic SnapLogic now includes a set of Snaps for utilizing the Vertex AI RAG Engine. Corpus Management The following Snaps are available for managing RAG corpora: Google Vertex AI RAG Create Corpus Google Vertex AI RAG List Corpus Google Vertex AI RAG Get Corpus Google Vertex AI RAG Delete Corpus File Management in Corpus The following Snaps enable file management within a RAG corpus: Google Vertex AI RAG Corpus Add File Google Vertex AI RAG Corpus List File Google Vertex AI RAG Corpus Get File Google Vertex AI RAG Corpus Remove File Retrieval For performing retrieval operations, use the following Snap: Google Vertex AI RAG Retrieval Query Try using Vertex AI RAG Let's walk through a practical example of how to leverage the Vertex AI RAG Engine within SnapLogic. This section will guide you through setting up a corpus, adding files, performing retrieval queries, and integrating the results into your LLM applications. Preparing step Before integration, two key steps are required: First, set up a Google Cloud project with enabled APIs, linked billing, and necessary permissions. List of required enabled Google API https://console.cloud.google.com/apis/library/cloudresourcemanager.googleapis.com https://console.cloud.google.com/apis/library/aiplatform.googleapis.com SnapLogic offers two primary methods for connecting to Google Cloud APIs: Service Account (recommended): SnapLogic can utilize an existing Service Account that possesses the necessary permissions. OAuth2: This method requires configuring OAuth2. Access Token: An Access Token is a temporary security credential to access Google Cloud APIs. It requires manual refreshing of the token when it expires. Create the corpus To build the corpus, use the Google Vertex AI RAG Create Corpus Snap. Place the Google Vertex AI RAG Create Corpus Snap. Create Google GenAI Service Account Upload the Service account JSON key file that you obtained from Google Cloud Platform, and then select the project and resource location you want to use. We recommend using the “us-central1” location. Edit the configuration by setting the display name and the Snap execution to "Validate & Execute." Validate the pipeline to obtain the corpus result in the output. If the result is similar to the image above, you now have the corpus ready to add the document. Upload the document To upload documents for Google Vertex AI RAG, integrate SnapLogic using a pipeline connecting the "Google Vertex AI RAG Corpus Add File" and "File Reader" Snaps. The "File Reader" accesses the document, passing its content to the "Google Vertex AI RAG Corpus Add File" Snap, which uploads it to a specified Vertex AI RAG corpus. Example Download the example document. Example file: Basics of SnapLogic.pdf Configure the File Reader Snap as follows: Configure the Corpus Add File Snap as follows: These steps will add the Basics of SnapLogic.pdf to the corpus in the previous section. If you run the pipeline successfully, the output will appear as follows. Retrieve query This section demonstrates how to use the Google Vertex AI RAG Retrieval Query Snap to fetch relevant information from the corpus. This snap takes a user query and returns the most pertinent documents or text snippets. Example From the existing corpus, we will query the question "What snap types does SnapLogic have?" and configure the snap accordingly. The result will display a list of text chunks related to the question, ordered by score value. The score value is calculated from the similarity or distance between the query and each text chunk. The similarity or distance depends on the vectorDB that you choose. By default, the score is the COSINE_DISTANCE. Generate the result Now that we have successfully retrieved relevant information from our corpus, the next crucial step is to leverage this retrieved context to generate a coherent and accurate response using an LLM. This section will demonstrate how to integrate the results from the Google Vertex AI RAG Retrieval Query Snap with a generative AI model, such as the Google Gemini Generate Snap, to produce a final answer based on the augmented information. Here's an example prompt to use in the prompt generator: The final answer will appear as follows: Additionally, the integration between Vertex AI RAG and SnapLogic provides the significant benefit of cross-model compatibility. This means that the established RAG workflows and data retrieval processes can be seamlessly adapted and utilized with different large language models beyond just Vertex AI, such as open-source models or other commercial LLMs. This flexibility allows organizations to leverage their investment in RAG infrastructure across a diverse ecosystem of AI models, enabling greater adaptability, future-proofing of applications, and the ability to choose the best-suited LLM for specific tasks without rebuilding the entire information retrieval pipeline. This cross-model benefit ensures that the RAG solution remains versatile and valuable, regardless of evolving LLM landscapes. Auto-retrieve query with the Vertex AI built-in tool Using the built-in tool in the Vertex AI Gemini Generate Snap for auto-retrieval significantly simplifies the RAG pipeline. Instead of manually performing a retrieval query and then passing the results to a separate generation step, this integrated approach allows the Gemini model to automatically consult the configured RAG corpus based on the input prompt. This reduces the number of steps and the complexity of the pipeline, as the retrieval and generation processes are seamlessly handled within a single Snap. It ensures that the LLM always has access to the most relevant contextual information from your knowledge base without requiring explicit orchestration, leading to more efficient and accurate content generation. The snap configuration example below demonstrates how to configure the Built-in tools section. Specifically, we select the vertexRagStore type and designate the target corpus. The final answer generated using the auto-retrieval process will be displayed below. The response includes grounding metadata for source tracking, allowing users to trace information origins. This feature enhances transparency, fact-verification, and builds trust in content accuracy and reliability. Users can delve into source material, cross-reference facts, and gain a complete understanding, boosting the system's utility and trustworthiness. Summary This document demonstrates how to integrate Google Cloud's Vertex AI Retrieval Augmented Generation (RAG) capabilities with SnapLogic to enhance LLM workflows. Key takeaways include: Streamlined RAG Process: Vertex AI RAG simplifies knowledge management and retrieval, abstracting away complexities like manual embedding generation and retrieval logic, which are typically required with traditional vector databases. Integrated Solution: Unlike standalone vector databases, Vertex AI RAG offers an end-to-end solution for RAG, handling everything from ingesting raw files to integrating with LLMs. SnapLogic Integration: SnapLogic provides dedicated Snaps for managing Vertex AI RAG corpora (creating, listing, getting, deleting), managing files within corpora (adding, listing, getting, removing), and performing retrieval queries. Practical Application: The guide provided a step-by-step example of setting up a corpus, uploading documents, performing retrieval queries using the Google Vertex AI RAG Retrieval Query Snap, and integrating the results with generative AI models like the Google Gemini Generate Snap for contextually accurate responses. Cross-Model Compatibility: A significant benefit of this integration is the ability to adapt established RAG workflows and data retrieval processes with various LLMs beyond just Vertex AI, including open-source and other commercial models, ensuring flexibility and future-proofing. Automated Retrieval with Built-in Tools: The integration allows for automated retrieval via built-in tools in the Vertex AI Gemini Generate Snap, simplifying the RAG pipeline by handling retrieval and generation seamlessly within a single step. By leveraging Vertex AI RAG with SnapLogic, organizations can simplify the development and deployment of RAG-powered applications, leading to more accurate, contextually relevant, and efficient LLM responses.More Than Just Fast: A Holistic Guide to High-Performance AI Agents
At SnapLogic, while building and refining an AI Agent for a large customer in the healthcare industry, we embarked on a journey of holistic performance optimization. We didn't just want to make it faster. We tried to make it better across the board. This journey taught us that significant gains are found by looking at the entire system, from the back-end data sources to the pixels on the user's screen. Here’s our playbook for building a truly high-performing AI agent, backed by real-world metrics. The Foundation: Data and Architecture Before you can tune an engine, you have to build it on a solid chassis. For an AI Agent, that chassis is its core architecture and its relationship with data. Choose the Right Brain for the Job: Not all LLMs are created equal. The "best" model depends entirely on the nature of the tasks your agent needs to perform. A simple agent with one or two tools has very different requirements from a complex agent that needs to reason, plan, and execute dynamic operations. Matching the model to the task complexity is key to balancing cost, speed, and capability. Task Complexity Model Type Characteristics & Best For Simple, Single-Tool Tasks Fast & Cost-Effective Goal: Executing a well-defined task with a limited toolset (e.g., simple data lookups, classification). These models are fast and cheap, perfect for high-volume, low-complexity actions. Multi-Tool Orchestration Balanced Goal: Reliably choosing the correct tool from several options and handling moderately complex user requests. These models offer a great blend of speed, cost, and improved instruction-following for a good user experience. Complex Reasoning & Dynamic Tasks High-Performance / Sophisticated Goal: Handling ambiguous requests that require multi-step reasoning, planning, and advanced tool use like dynamic SQL query generation. These are the most powerful (and expensive) models, essential for tasks where deep understanding and accuracy are critical. Deconstruct Complexity with a Multi-Agent Approach: A single, monolithic agent designed to do everything can become slow and unwieldy. A more advanced approach is to break down a highly complex agent into a team of smaller, specialized agents. This strategy offers two powerful benefits: It enables the use of faster, cheaper models. Each specialized agent has a narrower, more defined task, which often means you can use a less powerful (and faster) LLM for that specific job, reserving your most sophisticated model for the "manager" agent that orchestrates the others. It dramatically increases reusability. These smaller, function-specific agents and their underlying tools are modular. They can be easily repurposed and reused in the next AI Agent you build, accelerating future development cycles. Set the Stage for Success with Data: An AI Agent is only as good as the data it can access. We learned that optimizing data access is a critical first step. This involved: Implementing Dynamic Text-to-SQL: Instead of relying on rigid, pre-defined queries, we empowered the agent to build its own SQL queries dynamically from natural language. This flexibility required a deep initial investment in analyzing and understanding the critical columns and data formats our agent would need from sources like Snowflake. Generating Dedicated Database Views: To support the agent, we generated dedicated views on top of our source tables. This strategy serves two key purposes: it dramatically reduces query times by pre-joining and simplifying complex data, and it allows us to remove sensitive or unnecessary data from the source, ensuring the agent only has access to what it needs. Pre-loading the Schema for Agility: Making the database schema available to the agent is critical for accurate dynamic SQL generation. To optimize this, we pre-load the relevant schemas at startup. This simple step saves precious time on every single query the agent generates, contributing significantly to the overall responsiveness. The Engine: Tuning the Agent’s Logic and Retrieval Our Diagnostic Toolkit: Using AI to Analyze AI Before we could optimize the engine, we needed to know exactly where the friction was. Our diagnostic process followed a two-step approach: High-Level Analysis: We started in the SnapLogic Monitor, which provides a high-level, tabular view of all pipeline executions. This dashboard is the starting point for any performance investigation. As you can see below, it gives a list of all runs, their status, and their total duration. By clicking the Download table button, you can export this summary data as a CSV. This allows for a quick, high-level analysis to spot outliers and trends without immediately diving into verbose log files. AI-Powered Deep Dive: Once we identified a bottleneck from the dashboard—a pipeline that was taking longer than expected—we downloaded the detailed, verbose log files for those specific pipeline runs. We then fed these complex logs into an AI tool of our choice. This "AI analyzing AI" approach helped us instantly pinpoint key issues that would have taken hours to find manually. For example, this process uncovered an unnecessary error loop caused by duplicate JDBC driver versions, which significantly extended the execution time of our Snowflake Snaps. Fixing this single issue was a key factor in the 68% performance improvement we saw when querying our technical knowledge base. With a precise diagnosis in hand, we turned our attention to the agent's "thinking" process. This is where we saw some of our most dramatic performance gains. How We Achieved This: Crafting the Perfect Instructions (System Prompts): We transitioned from generic prompts to highly customized system prompts, optimized for both the specific task and the chosen LLM. A simpler model gets a simpler, more direct prompt, while a sophisticated model can be instructed to "think step-by-step" to improve its reasoning. A Simple Switch for Production Speed: One of the most impactful, low-effort optimizations came from how we use a key development tool: the Record Replay Snap. During the creation and testing of our agent's pipelines, this Snap is invaluable for capturing and replaying data, but it adds about 2.5 seconds of overhead to each execution. For a simple agent run involving a driver, a worker, and one tool, this adds up to 7.5 seconds of unnecessary latency in a production environment. Once our pipelines were successfully tested, we switched these Snaps to "Replay Only" mode. This simple change instantly removed the recording overhead, providing a significant speed boost across all agent interactions. Smarter, Faster Data Retrieval (RAG Optimization): For our Retrieval-Augmented Generation (RAG) tools, we focused on two key levers: Finding the Sweet Spot (k value): We tuned the k value—the number of documents retrieved for context. For our product information retrieval use case, adjusting this value was the key to our 63% speed improvement. It’s the art of getting just enough context for an accurate answer without creating unnecessary work for the LLM. Surgical Precision with Metadata: Instead of always performing a broad vector search, we enabled the agent to use metadata. If it knows a document's unique_ID, it can fetch that exact document. This is the difference between browsing a library and using a call number. It's swift and precise. Ensuring Consistency: We set the temperature to a low value during the data extraction and indexing process. This ensures that the data chunks are created consistently, leading to more reliable and repeatable search results. The Results: A Data-Driven Transformation Our optimization efforts led to significant, measurable improvements across several key use cases for the AI Agent. Use Case Before Optimization After Optimization Speed Improvement Querying Technical Knowledge Base 92 seconds 29 seconds ~68% Faster Processing Sales Order Data 32 seconds 10.7 seconds ~66% Faster RAG Retrieval 5.8 seconds 2.1 seconds ~63% Faster Production Optimization (Replay Only) 20 seconds 17.5 seconds ~12% Faster* (*This improvement came from switching development Snaps to a production-ready "Replay Only" mode, removing the latency inherent to the testing phase.) The Experience: Focusing on the User Ultimately, all the back-end optimization in the world is irrelevant if the user experience is poor. The final layer of our strategy was to focus on the front-end application. Engage, Don't Just Wait: A simple "running..." message can cause user anxiety and make any wait feel longer. Our next iteration will provide a real-time status of the agent's thinking process (e.g., "Querying product database...", "Synthesizing answer..."). This transparency keeps the user engaged and builds trust. Guide the User to Success: We learned that a blank text box can be intimidating. By providing predefined example prompts and clearly explaining the agent's capabilities, we guide the user toward successful interactions. Deliver a Clear Result: The final output must be easy to consume. We format our results cleanly, using tables, lists, and clear language to ensure the user can understand and act on the information instantly. By taking this holistic approach, we optimized the foundation, the engine, and the user experience to build an AI Agent that doesn't just feel fast. It feels intelligent, reliable, and genuinely helpful.
Bridging Legacy OPC Classic Servers(DA, AE, HDA) to SnapLogic via OPC UA Wrapper
Despite significant advances in industrial automation, many critical devices still rely on legacy OPC Classic servers (DA, AE, HDA). Integrating these aging systems with modern platforms presents challenges such as protocol incompatibility and the absence of native OPC UA support. Meanwhile, modern integration and analytics platforms increasingly depend on OPC UA for secure, scalable connectivity. This post addresses these challenges by demonstrating how the OPC UA Wrapper can seamlessly bridge OPC Classic servers to SnapLogic. Through a practical use case—detecting missing reset anomalies in saw-toothed wave signals from an OPC Simulation DA Server—you’ll discover how to enable real-time monitoring and alerting without costly infrastructure upgrades
Scalable Analytics Platform: A Data Engineering Journey
Scalable Analytics Platform: A Data Engineering Journey - Explore SnapLogic's innovative Medallion Architecture approach for handling massive data, improving analytics with S3, Trino, and Amazon Neptune. Learn about cost reduction, scalability, data governance, and enhanced insights.Industrial IoT – Turbine Lubrication Oil Level Monitoring & Alert Mechanism via OPC UA and SnapLogic
In the energy sector, turbine lubrication oil is mission-critical. A drop in oil level or pressure can silently escalate into major failures, unplanned shutdowns, and expensive maintenance windows. In this blog, we showcase a real-world implementation using SnapLogic and OPC UA, designed to: 🔧 Continuously monitor turbine lubrication oil levels 📥 Ingest real-time sensor data from industrial systems 📊 Store telemetry in data lakes for analytics and compliance 📣 Real-time Slack alerts to engineers — before failures strike This IIoT-driven solution empowers energy providers to adopt predictive maintenance practices and reduce operational risk
