diegoecab/oci-deal-accelerator
1
1
Fork 2
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
b30a4f0d329ccdfb0b6e7fdd92c81e39989512ba
oci-deal-accelerator/kb/diagram/assets/archcenter-refs/deploy-ai-powered-chatbot/_description.md
root b30a4f0d32 Diagram generation: ref-arch-driven procedure + spec validator + KB enrichment 
The diagram path now follows a documented standard procedure (lookup
the closest Oracle Architecture Center reference → confirm components
→ author absolute_layout → spec validator → render → visually verify)
and ships persistent guardrails so layout regressions can't recur.

Persistent procedure changes (apply to all users, all sessions):
- tools/diagram_spec_validator.py — geometry checks (CONTAINER_TOO_THIN,
  CONTAINER_PADDING_VIOLATION, LABEL_OVERFLOW_PARENT) run BEFORE either
  renderer (drawio + PPTX). Catches the subnet-collapse / label-overflow
  bugs that the post-render drawio validator missed.
- tools/oci_diagram_gen.py + tools/oci_pptx_diagram_gen.py — call the
  spec validator before emitting any output. Adds mysql / mysql_heatwave
  type aliases.
- tools/archcenter_pattern_lookup.py — scores against cached page
  descriptions (not just the 1-line summary), supports --queries for
  multi-fragment composition, and applies synonym expansion via
  kb/architecture-center/synonyms.yaml so "LB HA cross AD" matches
  "load balancer high availability availability domain".
- kb/architecture-center/synonyms.yaml — canonical synonym table
  (load balancer, autonomous database, data guard, …) used by the
  lookup scorer.

KB enrichment:
- tools/archcenter_description_fetcher.py + 121 cached _description.md
  under kb/diagram/assets/archcenter-refs/<slug>/. Removes the runtime
  dependency on docs.oracle.com when authoring specs and feeds the
  pattern-lookup scorer.
- 110+ cached .drawio / .svg / .png references for offline reuse,
  plus the OCI Toolkit v24.2 import (kb/diagram/assets/oci-toolkit-drawio).

Documentation:
- docs/skill/output-formats.md — new "Standard diagram-generation
  procedure (MANDATORY)" + geometry rules + the new validator entry.
- SKILL.md option 2 — references the mandatory procedure.
- README.md — describes the spec validator, archcenter_pattern_lookup
  and description fetcher, and updates the KB-health table.

Tooling that backs the procedure (cumulative across recent sessions):
tools/archcenter_case_runner.py, archcenter_batch_driver.py,
archcenter_zip_downloader.py, drawio_visual_validator.py,
drawio_fidelity_eval.py, harvest_drawio_icon.py, import_oci_library.py,
oci_pptx_diagram_gen.py, oci_pptx_render.py, refresh_pptx_icon_index.py.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-25 21:15:21 -03:00

5.3 KiB
Raw Blame History

Deploy an AI-powered chatbot

Summary (catalog)

AI chatbot with OCI GenAI and Functions. RAG for knowledge-grounded responses, ADB-S for conversation history and vector search. Serverless architecture with OCI Functions for cost efficiency.

Architecture (fetched from source)

Architecture

This reference architecture outlines how to configure and deploy an AI-powered chatbot on your own OCI tenancy. This chatbot can generate or summarize content, answer questions, translate languages, and more.

This AI-powered chatbot leverages Oracle Digital Assistant and OCI Generative AI large language models (LLMs). Oracle Visual Builder is used to embed the chatbot in a web application. Users can interact with OCI Generative AI through natural language questions and receive responses from the LLM by using the chatbot interface.

The following diagram illustrates this reference architecture.

Description of the illustration deploy-ai-chatbot-arch.png

deploy-ai-chatbot-arch.zip

The flow for users and developers using this architecture resembles:

  • Developers and chatbot users authenticate with OCI Identity and Access Management .

  • Users access the chatbot using the Oracle Visual Builder app where it is embedded. Developers can configure the app from the Oracle Visual Builder service home page.

  • Developers configure the chatbot using the Oracle Digital Assistant service console.

  • Developers access OCI Generative AI LLMs using APIs.

The architecture has the following components:

  • Region An Oracle Cloud Infrastructure region is a localized geographic area that contains one or more data centers, hosting availability domains. Regions are independent of other regions, and vast distances can separate them (across countries or even continents).

  • Identity and Access Management Oracle Cloud Infrastructure Identity and Access Management (IAM) provides user access control for Oracle Cloud Infrastructure (OCI) and Oracle Cloud Applications. The IAM API and the user interface enable you to manage identity domains and the resources within them. Each OCI IAM identity domain represents a standalone identity and access management solution or a different user population.

  • Oracle Visual Builder Oracle Visual Builder is an intuitive development experience on top of a development and hosting platform that empowers you to create engaging responsive applications. Focusing on ease of use and a visual development approach, it provides an easy way for you to create applications that are hosted in Oracle’s secure and scalable cloud platform.

  • Digital Assistant Oracle Digital Assistant is a platform that allows you to create and deploy digital assistants for your users. With Oracle Digital Assistant , you can create AI-driven interfaces (or chatbots) for business applications through text, chat, and voice interfaces. Each digital assistant has a collection of one or more specialized skills to help users complete a variety of tasks in natural language conversations. For example, an individual digital assistant might have skills that focus on specific types of tasks such as tracking inventory, submitting time cards, and creating expense reports.

  • Generative AI Oracle Cloud Infrastructure Generative AI is a fully-managed OCI service that provides a set of state-of-the-art, customizable, large language models (LLMs) that cover a wide range of use cases for text generation, summarization, semantic search, and more. Use the playground to try out the ready-to-use pretrained models, or create and host your own fine-tuned custom models based on your own data on dedicated AI clusters.

Considerations

When deploying this AI-powered chatbot, consider the following.

  • Region Availability Oracle hosts its OCI services in regions and availability domains. A region is a localized geographic area, and an availability domain is one or more data centers in that region. AI services are not always available in all regions. To learn more, see Regions with Generative AI in the Explore More section.

  • Document Processing The document processing feature used in this architecture is intended for smaller documents. For solutions that analyze larger documents, see the other LiveLabs in the Explore More section.

Deploy

To deploy this architecture, follow the instructions in this Live Lab:

Deploy ATOM (AI Powered) Chatbot

Explore More

Learn more about deploying an AI-powered chatbot.

Review these additional resources:

  • Deploy an ODA Chatbot powered by Generative AI Agents (LiveLab)

  • Deploy a Chatbot powered by Generative AI Agents using 23ai Vector DB (LiveLab)

  • OCI Generative AI

  • Overview of Digital Assistants and Skills

  • Regions with Generative AI

  • Well-architected framework for Oracle Cloud Infrastructure

Acknowledgments

  • Authors : Luke Farley, Abhinav Jain

  • Contributor : Kaushik Kundu

Title and Copyright Information

Deploy an AI-powered chatbot

G27457-02

August 2025

Copyright © 2025,

Oracle and/or its affiliates.

Reference in New Issue View Git Blame Copy Permalink