bytelyst/learning_ai_common_plat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
276 Commits 2 Branches 3 Tags 60 MiB
5deb5efdcf
Commit Graph

15 Commits

Author SHA1 Message Date
saravanakumardb1
5deb5efdcf docs(local-llms): add comprehensive model comparison table and deepseek-r1:32b details 
- Add Comprehensive Model Comparison Table: 11 models (local + cloud) with
  Disk, Params, Quant, RAM, Tok/s, JSON quality, Reasoning, Code, Instruction
  Following, Context window, <think> flag, and install status columns
- Add Gap Analysis table: llama3.1:8b (~55%), qwen2.5-coder:32b (~85%),
  deepseek-r1:32b (~75-80%) vs llama3.3:70b across 5 capability dimensions
- Update Tier 4 Reasoning table: add Parameters, Quant columns; add <think>
  warning note with link to eval doc transform pattern
- Update By Use Case table: add brain signal routing row, update extraction
  evals fallback to qwen2.5-coder:32b
 2026-02-19 16:06:02 -08:00
saravanakumardb1
cfc1194079 docs(local-llms): add latency/cost comparison and deepseek-r1 transform pattern to evals doc 
- Add Latency & Cost Comparison table: llama3.1:8b (~1m27s), qwen2.5-coder:32b
  (~5-8m est.), deepseek-r1:32b (~5-8m est.) vs gemini-2.5-flash (~15-25s, $0.003)
  and gpt-4o (~20-40s, $0.05-0.15) — all measured at 19 cases, concurrency=4
- Fix assertion pattern docs: single expressions required, not const/return blocks
- Add deepseek-r1 <think> strip transform pattern for promptfoo provider config
- Expand recommended models table with Disk, Reasoning, Pass Rate, and Notes columns
 2026-02-19 16:05:52 -08:00
saravanakumardb1
71a7623553 docs(local-llms): expand installed models table with parameters and quantization 
- Add Parameters, Quantization, and Status columns to models table
- qwen2.5-coder:32b: 32.8B params, Q4_K_M, 18.5 GB disk
- llama3.1:8b: 8B params, Q4_K_M, 4.9 GB disk (confirmed via ollama API)
 2026-02-19 16:05:42 -08:00
saravanakumardb1
984630eb45 docs(local-llm): mark ALL 39 items complete in DASHBOARD_REVIEW.md 
All bugs (11), code quality (6), features (16), performance (5), and
security (3) items are now checked off. Added Sprint 6 (ed93a6f) and
Sprint 7 (8bdd5ee) to commit log. Updated summary to reflect 100%
completion across 7 sprints.
 2026-02-19 15:45:46 -08:00
saravanakumardb1
2936b9f047 docs(local-llm): mark Sprint 5 P1-P3 complete in DASHBOARD_REVIEW.md 
Check off 3 items (P1, P2, P3) in performance section and sprint
tracker. Add commit b1fda3a to commit log.
 2026-02-19 15:28:59 -08:00
saravanakumardb1
9892fe7145 docs(local-llm): mark Sprint 4 items complete in DASHBOARD_REVIEW.md 
Check off 4 items (F2, F3, F9, F11) in features list and sprint
tracker. F4 (chat mode) deferred. Add commit 9c2f5f3 to commit log.
 2026-02-19 15:26:37 -08:00
saravanakumardb1
40c40756ed docs(local-llm): mark Sprint 3 items complete in DASHBOARD_REVIEW.md 
Check off 5 items (CQ1, CQ3, CQ4, S1, S2) in code quality, security,
and sprint tracker. CQ2 (inline styles) deferred. Add commit 75a3cd0
to commit log.
 2026-02-19 15:22:11 -08:00
saravanakumardb1
7a82db4876 docs(local-llm): mark Sprint 2 items complete in DASHBOARD_REVIEW.md 
Check off 5 items (B2, B7, B8, F1, F6) in bug list, features list,
and sprint tracker. Add commit 2d9475b to commit log.
 2026-02-19 15:17:16 -08:00
saravanakumardb1
9a807f64cf docs(local-llm): mark Sprint 1 items complete in DASHBOARD_REVIEW.md 
Check off 9 items (B1, B3, B4, B5, B6, B9, B10, B11, P4) in both
the bug list and sprint tracker. Add commit 2da67c2 to commit log.
 2026-02-19 15:13:43 -08:00
saravanakumardb1
554a5137ec docs(local-llm): improve dashboard review — add checkboxes, commit log, new findings 
Rewrite DASHBOARD_REVIEW.md with progress-tracking improvements:
- Add GitHub-style checkboxes to all 41 actionable items
- Add file inventory table with line counts and purposes
- Add commit log section for tracking implementation progress
- Add sprint tracker tables with effort estimates and commit columns
- New finding B11: prompt text not cleared on Escape close
- New finding CQ6: no Zod validation on API responses
- Consolidate priority matrix into sprint tables (less redundancy)
- Add deferred items section with dependency notes
- Improve item descriptions with more precise file:line references
- Add stack summary and total effort estimate (14–17 hrs)
 2026-02-19 15:11:19 -08:00
saravanakumardb1
093682eace docs(local-llm): add systematic dashboard bug & improvement review 
DASHBOARD_REVIEW.md — comprehensive code review of all 6 dashboard files
(1,395 lines). Organized into 7 sections:

- 10 bugs (B1–B10): hardcoded header, blocking pull, escape during stream,
  auto-refresh during streaming, no abort controller, vm_stat page size, etc.
- 5 code quality issues (CQ1–CQ5): monolithic component, inline styles,
  duplicated constants, no error boundary, no loading skeleton
- 16 feature ideas (F1–F16): pull progress, chat mode, prompt history,
  token/s metrics, model search, whisper test, extraction integration, etc.
- 5 performance items (P1–P5): request deduplication, cache TTL, du latency
- 3 security notes (S1–S3): input validation, shell injection pattern, CORS
- Priority matrix and 5-sprint implementation roadmap
 2026-02-19 14:36:51 -08:00
saravanakumardb1
b77afce9ae docs(local-llm): add Mission Control dashboard documentation 
- docs/05-mission-control-dashboard.md: complete dashboard reference with
  architecture diagram, API route docs (request/response examples),
  UI feature descriptions, design tokens table, v1/v2 changelog,
  and future improvements roadmap
 2026-02-19 13:03:30 -08:00
saravanakumardb1
3561deee52 docs(local-llm): add multimodal stack, model recommendations, and troubleshooting 
- docs/04-multimodal-local-stack.md: vision models (llava, qwen2.5vl, moondream2),
  audio pipeline architecture, video understanding status, Kimi alternatives,
  complete local AI stack diagram
- docs/07-model-recommendations.md: 6-tier model guide (coding, fast, general,
  reasoning, vision, embeddings), recommended 10-model stack for M4 Pro 48GB,
  use-case quick reference, hardware scaling guide
- docs/08-troubleshooting.md: corporate Forcepoint proxy workarounds, MLX warning,
  JSON parse errors, slow inference, whisper-cli vs whisper-cpp naming, audio
  format conversion, proxy-corrupted downloads detection
 2026-02-19 13:01:22 -08:00
saravanakumardb1
80f794dee7 docs(local-llm): add Ollama setup, extraction evals, and env vars reference 
- docs/02-ollama-setup-and-models.md: installation, server config, memory management,
  idle timeout, manual load/unload, OpenAI-compatible API, native API reference,
  performance tuning flags (flash attention, KV cache)
- docs/06-extraction-service-evals.md: promptfoo eval suite against Ollama, 19 cases
  across 5 tasks, assertion patterns for JSON string output, Python sidecar config
- docs/09-environment-variables.md: comprehensive var reference for Ollama server,
  evals, Python sidecar, dashboard, whisper CLI flags, proxy/network settings
 2026-02-19 13:01:05 -08:00
saravanakumardb1
464ffb92ec docs(local-llm): add docs index, hardware specs, and whisper-cpp setup 
- docs/README.md: documentation index with quick start, file structure, status table
- docs/01-hardware-and-prerequisites.md: M4 Pro 48GB specs, toolchain inventory,
  disk budget, network environment (Forcepoint proxy details)
- docs/03-whisper-cpp-setup.md: whisper-cpp installation, GGML model guide,
  ffmpeg audio conversion, CLI usage, real-time streaming, LysnrAI integration
 2026-02-19 13:00:48 -08:00