sarman/dgx-spark-playbooks
1
0
Fork 0
mirror of https://github.com/NVIDIA/dgx-spark-playbooks.git synced 2026-04-23 02:23:53 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
cbe92b50e7
dgx-spark-playbooks/nvidia
History
Santosh Bhavani cbe92b50e7 Increase topK default to 40 for multi-hop context 
- Update default topK from 20 to 40 in query parameters
- Support richer context with multi-hop graph traversal
- Maintain flexible topK range (1-50) via slider
- Respect user selection of query mode (don't force mode changes)

Higher topK allows more edges from multi-hop paths to be included
in the context provided to the LLM for answer generation.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-25 13:49:07 -07:00
..
comfy-ui chore: Regenerate all playbooks 2025-10-13 13:22:50 +00:00
connect-to-your-spark chore: Regenerate all playbooks 2025-10-13 01:00:24 +00:00
connect-two-sparks chore: Regenerate all playbooks 2025-10-14 01:21:39 +00:00
cuda-x-data-science chore: Regenerate all playbooks 2025-10-21 00:57:26 +00:00
dgx-dashboard chore: Regenerate all playbooks 2025-10-18 21:48:15 +00:00
flux-finetuning chore: Regenerate all playbooks 2025-10-13 17:36:51 +00:00
jax chore: Regenerate all playbooks 2025-10-14 14:11:25 +00:00
llama-factory chore: Regenerate all playbooks 2025-10-12 20:53:42 +00:00
multi-agent-chatbot chore: Regenerate all playbooks 2025-10-22 19:44:23 +00:00
multi-modal-inference chore: Regenerate all playbooks 2025-10-13 14:55:45 +00:00
nccl chore: Regenerate all playbooks 2025-10-13 16:51:50 +00:00
nemo-fine-tune chore: Regenerate all playbooks 2025-10-22 18:54:29 +00:00
nim-llm chore: Regenerate all playbooks 2025-10-12 20:53:42 +00:00
nvfp4-quantization chore: Regenerate all playbooks 2025-10-13 14:55:45 +00:00
ollama chore: Regenerate all playbooks 2025-10-12 20:13:25 +00:00
open-webui chore: Regenerate all playbooks 2025-10-13 14:55:45 +00:00
pytorch-fine-tune chore: Regenerate all playbooks 2025-10-13 17:36:51 +00:00
rag-ai-workbench chore: Regenerate all playbooks 2025-10-12 20:53:42 +00:00
speculative-decoding chore: Regenerate all playbooks 2025-10-12 20:13:25 +00:00
tailscale chore: Regenerate all playbooks 2025-10-12 20:13:25 +00:00
trt-llm chore: Regenerate all playbooks 2025-10-18 21:48:15 +00:00
txt2kg Increase topK default to 40 for multi-hop context 2025-10-25 13:49:07 -07:00
unsloth chore: Regenerate all playbooks 2025-10-13 17:36:51 +00:00
vibe-coding chore: Regenerate all playbooks 2025-10-21 13:09:58 +00:00
vllm chore: Regenerate all playbooks 2025-10-18 21:28:42 +00:00
vlm-finetuning chore: Regenerate all playbooks 2025-10-13 17:36:51 +00:00
vscode chore: Regenerate all playbooks 2025-10-13 13:22:50 +00:00
vss chore: Regenerate all playbooks 2025-10-18 21:28:42 +00:00