Add Real-World Project: Search and Summarize Your Own Journal - #283
Open
abderrahim-lectures wants to merge 1 commit into
Open
Add Real-World Project: Search and Summarize Your Own Journal#283abderrahim-lectures wants to merge 1 commit into
abderrahim-lectures wants to merge 1 commit into
Conversation
Add a Real-World Project that indexes a folder of dated markdown journal entries with local embeddings (sentence-transformers + numpy), searches them semantically, and summarizes a date range with a free-tier LLM that cites the [YYYY-MM-DD] source behind every claim. Includes a committed 12-entry sample journal, sample queries with ground truth, a runnable CLI, and a Colab/Kaggle/Binder notebook; teaches that embeddings + a small LLM beat grep and reading everything for an unstructured personal corpus, with the same no-invented-facts audit discipline as the changelog work. Closes #282 Co-authored-by: deepseek-v4-flash-free <noreply@opencode.ai>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What's included
docs/projects/journal-search-summarize/index.md— 5 steps (corpus → local embedding → semantic search → free-tier dated summary with citation audit → end-to-end on sample queries), each with a StepChecklist and Socratic questions; 6-provider table; opencode blurb; Colab/Kaggle/Binder badges;_category_.jsonat position 26.examples/journal-search-summarize/main.py— CLI:index,search '<query>',summarize START END,--interactive.data/journal/— 12 committed dated sample entries;data/sample_queries.json— 6 queries with ground-truth notes.notebook.ipynb(12 cells, journal embedded inline, getpass + 6-provider selection),pyproject.toml,uv.lock,.env.example,.gitignore,.python-version,README.md.src/data/projects.ts,docs/projects/index.mdx,src/pages/index.tsx(idjournal-search-summarize, tagsAI Agents,Retrieval-Augmented Generation).Verification
npm run typecheck— passes.npm run build— passes for all 4 locales (en/ar/es/fr); the only broken-anchor warnings remaining are pre-existingdocs-qa-bot→rag-noteslinks that exist on main and are untouched here.uv run:main.py --help,index(built a real 12×384 index),search(all 6 sample queries return the expected ground-truth entries), summarize validation paths, and--interactive. Live LLM call not exercised (no API key on the build machine), matching the other LLM examples.Closes #282