update AgentQnA

[minmin-intel]

Description

1. Update worker RAG agent search_knowledge_base tool with the latest changes in DocIndexRetriever
2. Update README: clean up, add more instructions regarding UI
3. Build DocIndexRetriever related docker images in unit test instead of pulling to reflect the latest changes

Issues

List the issue or RFC link this PR is working on. If there is no such link, please mark it as n/a.

Type of change

List the type of change like below. Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds new functionality)
• Breaking change (fix or feature that would break existing design and interface)
• Others (enhancement, documentation, validation, etc.)

Dependencies

List the newly introduced 3rd party dependency if exists.

Tests

Describe the tests that you ran to verify your changes.

[github-actions]

Dependency Review

✅ No vulnerabilities or license issues found.

Scanned Files

None

[Copilot]

Copilot reviewed 3 out of 6 changed files in this pull request and generated 1 comment.

Files not reviewed (3)

• AgentQnA/retrieval_tool/run_ingest_data.sh: Language not supported
• AgentQnA/tests/step4_launch_and_validate_agent_gaudi.sh: Language not supported
• AgentQnA/tests/test_compose_on_gaudi.sh: Language not supported

Comments suppressed due to low confidence (2)

AgentQnA/tools/worker_agent_tools.py:15

• Ensure that the change from using the 'text' key to 'messages' in the payload aligns with the updated API requirements for DocIndexRetriever to avoid any integration issues.

"messages": query,

AgentQnA/docker_compose/intel/hpu/gaudi/compose.yaml:141

• Confirm that the revised command flag '--max-seq-len-to-capture' matches the expected parameter name in the underlying system, ensuring consistency with the updated configuration.

command: --model $LLM_MODEL_ID --tensor-parallel-size 4 --host 0.0.0.0 --port 8000 --block-size 128 --max-num-seqs 256 --max-seq-len-to-capture 16384