Responses API tool orchestration using RAG

[shikhar-cyber]

Summary

Briefly describe the changes and the goal of this PR. Make sure the PR title summarizes the changes effectively.

This provides a new guide that demonstrates how to build dynamic, multi-tool workflows using OpenAI's Responses API. It shows how to implement a Retrieval-Augmented Generation (RAG) architecture that intelligently routes user queries to either internal tools (e.g., web-search) or external services (e.g., vector databases like Pinecone). The goal is to provide developers with a clear and practical example of how to integrate third-party tools and hosted APIs into a unified conversational system.

Motivation

Many users have asked for a clear example of how to extend OpenAI's Responses API to interact with both internally hosted tools and externally hosted services, like vector databases. This guide addresses that need by providing an end-to-end walkthrough that covers:

• Routing queries dynamically based on intent and context needs.
• Using the function_calling feature of Responses API to call external vector databases.
• Integrating OpenAI-hosted tools like web-search.
• Merging retrieved data into the final response via the tool_choice mechanism.

These changes help developers build intelligent assistant-like systems that can synthesize both proprietary and public knowledge sources—improving response quality and relevance in real-world applications.

---

For new content

When contributing new content, read through our contribution guidelines, and mark the following action items as completed:

• I have added a new entry in registry.yaml (and, optionally, in authors.yaml) so that my content renders on the cookbook website.
• I have conducted a self-review of my content based on the contribution guidelines:
  • Relevance: This content is related to building with OpenAI technologies and is useful to others.
  • Uniqueness: I have searched for related examples in the OpenAI Cookbook, and verified that my content offers new insights or unique information compared to existing documentation.
  • Spelling and Grammar: I have checked for spelling or grammatical mistakes.
  • Clarity: I have done a final read-through and verified that my submission is well-organized and easy to understand.
  • Correctness: The information I include is correct and all of my code executes successfully.
  • Completeness: I have explained everything fully, including all necessary references and citations.

We will rate each of these areas on a scale from 1 to 4, and will only accept contributions that score 3 or higher on all areas. Refer to our contribution guidelines for more details.