Add OCI LLM, embeddings, and Oracle integrations

[fede-kamel]

Summary

This PR adds first-class OCI support across CrewAI’s native LLM and embedding paths, plus OCI and Oracle DB tool integrations in crewai-tools.

What’s included

crewai

• Add native OCI LLM provider support for:
  • chat completions
  • async calls
  • batch calls
  • streaming
  • structured output
  • tool calling
  • multimodal input handling
• Add OCI embedding support for:
  • text embeddings
  • image embeddings
• Add live and SDK-surface coverage for OCI provider and embedding paths
• Add a small OCI agent profiling entrypoint for repeatable local profiling

crewai-tools

• Add OCI tools for:
  • Generative AI agent invocation
  • Knowledge Base retrieval
  • Object Storage read/write
• Add Oracle DB tools for:
  • text retrieval
  • vector retrieval
  • hybrid retrieval
• Add live integration coverage for OCI tools and Oracle DB retrieval paths

Key fixes

• Preserve input ordering in OCICompletion.abatch()
• Guard shared OCI client access
• Fix OCI live test parametrization so unsupported/unconfigured live cases skip cleanly
• Fix Oracle hybrid retrieval JSON bind handling
• Fix Oracle hybrid retrieval LOB JSON parsing
• Correct the OCI image embedding live fixture to use a valid image payload
• Tighten OCI/Oracle type annotations to satisfy strict mypy

Validation

This PR was validated with targeted unit and live integration coverage against real OCI profiles and a real Oracle Autonomous Database.

Validated live paths include:

• OCI chat/basic/async/batch/stream/structured flows
• OCI tool calling, including repeated sequential asks with the same agent
• OCI multimodal image, PDF, audio, and video flows
• OCI text embeddings
• OCI image embeddings
• OCI Knowledge Base tool
• Oracle Text search
• Oracle vector search using OCI-produced embeddings
• Oracle hybrid search using an installed DB-local ONNX model

Final targeted checks:

• Ruff on touched OCI/Oracle source: clean
• Mypy on touched crewai OCI source: clean
• Mypy on touched crewai-tools OCI/Oracle source: clean

Targeted test results:

• crewai OCI slice: 5 passed, 5 skipped
• crewai-tools OCI/Oracle slice: 9 passed, 4 skipped

The remaining skips in those targeted reruns are expected live-env/model-selection skips from the integration harness, not product failures.

Notes

• Oracle hybrid vector index creation is distinct from OCI embedding model usage. The Oracle DB test fixture documents the DB-local vectorizer requirement and the prior ORA-40284 behavior.
• OCI agent profiling support is included via lib/crewai/tests/llms/oci/profile_oci_agent.py.

Commit split

1. 7cfb5f7 Add OCI LLM and embedding support to crewai
2. d6ae839 Add OCI and Oracle DB tools integrations

---

Note

High Risk
Adds a new native LLM provider (including streaming/tool-calling/structured output) and a new embeddings provider, plus new OCI/Object Storage/Oracle DB tools, touching core model routing and RAG factory code paths. Risk is mainly in provider selection/streaming/tool execution and optional-dependency handling affecting existing LLM/RAG behavior.

Overview
Adds first-class Oracle Cloud Infrastructure (OCI) support to CrewAI, including a new native oci LLM provider with streaming, async/batch helpers, tool calling, structured outputs, and multimodal message normalization, plus response metadata capture.

Extends RAG to support OCI embeddings (text + image) via a new oci embeddings provider and updates optional import handling for RAG factories.

Introduces new crewai-tools integrations for OCI agent invocation, OCI Object Storage read/write, and an OCI-backed knowledge base retriever, along with new Oracle Database retrieval tools (text, vector, and hybrid search) and associated unit/live integration tests and documentation updates (OCI setup + new tool pages).

^{Written by Cursor Bugbot for commit 9be59b9. This will update automatically on new commits. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

There are 2 total unresolved issues (including 1 from previous review).

^{Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}