feat: add HPC-AI model provider support

[lioZ129]

Two related pr:

• docs: add HPC-AI chat generator docs haystack#11048
• docs: add HPC-AI integration page haystack-integrations#438

Proposed Changes:

• Add a new hpc-ai-haystack integration under integrations/hpc_ai
• Introduce HPCAIChatGenerator, built on top of Haystack's OpenAIChatGenerator, to support HPC-AI's OpenAI-compatible API
• Default the integration to:
  • HPC_AI_API_KEY for authentication
  • HPC_AI_BASE_URL as an optional override
  • https://api.hpc-ai.com/inference/v1 as the default base URL
• Register the officially supported models via SUPPORTED_MODELS:
  • minimax/minimax-m2.5
  • moonshotai/kimi-k2.5
• Add integration-specific tests, examples, README, and pydoc config
• Wire the new integration into the repo-level inventory and CI configuration:
  • root README.md
  • .github/workflows/hpc_ai.yml
  • .github/labeler.yml
  • .github/workflows/CI_coverage_comment.yml

How did you test it?

• Ran hatch run fmt-check
• Ran hatch run test:types
• Ran hatch run test:unit
• Ran hatch run test:integration
• Performed additional local sanity checks on serialization, async tests, examples, and generated package structure

Notes for the reviewer

• This integration intentionally reuses the existing OpenAI-compatible chat generator flow rather than introducing a new transport layer
• The scope of this PR is limited to the core integration package and repo wiring
• Companion documentation changes are prepared separately in the haystack and haystack-integrations repositories

Checklist

• I have read the contributors guidelines and the code of conduct
• I have updated the related issue with new insights and changes
• I added unit tests and updated the docstrings
• I've used one of the conventional commit types for my PR title: fix:, feat:, build:, chore:, ci:, docs:, style:, refactor:, perf:, test:.

[CLAassistant]

All committers have signed the CLA.

[Copilot]

Pull request overview

Adds a new HPC-AI integration package to this repository, providing an OpenAI-compatible chat generator component and wiring it into the repo’s CI and inventory.

Changes:

• Introduces hpc-ai-haystack integration with HPCAIChatGenerator (OpenAI-compatible) plus examples and packaging metadata.
• Adds unit/integration tests for sync + async usage (including tools + streaming).
• Wires the integration into repo-level README, labeler, and coverage/CI workflows.

Reviewed changes

Copilot reviewed 17 out of 19 changed files in this pull request and generated 5 comments.

Show a summary per file

File	Description
README.md	Adds hpc-ai-haystack to the integrations inventory table.
integrations/hpc_ai/src/haystack_integrations/components/generators/hpc_ai/chat/chat_generator.py	Implements HPCAIChatGenerator with HPC-AI defaults and OpenAI-compatible request shaping.
integrations/hpc_ai/src/haystack_integrations/components/generators/hpc_ai/init.py	Exposes HPCAIChatGenerator from the integration package.
integrations/hpc_ai/tests/test_hpc_ai_chat_generator.py	Adds sync tests for init/serde/run/tool-calls/streaming conversion.
integrations/hpc_ai/tests/test_hpc_ai_chat_generator_async.py	Adds async tests for init/run/streaming/tool calling.
integrations/hpc_ai/tests/test_hpc_ai_stub_async.py	Adds a trivial async test (currently redundant).
integrations/hpc_ai/pyproject.toml	Defines packaging, lint/type/test tooling, and coverage config for the integration.
integrations/hpc_ai/README.md	Documents env vars and pointers for contributing/testing.
integrations/hpc_ai/examples/*	Adds basic + tool-calling examples for the new generator.
integrations/hpc_ai/pydoc/config_docusaurus.yml	Registers module for pydoc generation.
.github/workflows/hpc_ai.yml	Adds CI workflow for the integration (lint/types/tests/coverage).
.github/workflows/CI_coverage_comment.yml	Adds the new workflow name to coverage-comment triggering.
.github/labeler.yml	Adds label rules for changes under integrations/hpc_ai.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[lioZ129]

@bogdankostic could you please review these PRs?

[bogdankostic]

Thanks for the PR, @lioZ129!
We ask that all new integrations begin as a "New Integration Proposal" issue so we can assess whether they are a fit for our core integrations. I'm closing this PR for the time being, but we look forward to seeing the proposal.

Alternatively, you can always release this as an external integration (for example with the help of our custom component template repo).

[lioZ129]

@bogdankostic Thanks for the clarification! Understood on the process for new integrations. I’ve opened a dedicated “New Integration Proposal” issue here: #3122

I’ll wait for feedback there first and if the proposal is accepted I can resubmit the implementation as a new PR aligned with the approved scope.