← Back to SansadSaar

SansadSaar — User guide

A quick tour of every feature, how to set up AI, how the privacy model works, and what costs (if any) come with each option.

1. What is SansadSaar?

A single-file browser app that surfaces every report from India's 24 Departmentally Related Standing Committees (DRSCs) — 16 chaired by the Lok Sabha, 8 by the Rajya Sabha. Reports are scraped daily from sansad.in by an open-source GitHub Action and mirrored as static JSON on GitHub Pages. The app you're using runs entirely in your browser — there is no SansadSaar server, no account, no analytics.

Three things make it different from the upstream ParliamentWatch (whose Python scraper powers the data mirror):

• It runs as a single HTML file — no Python, no install, no terminal.
• AI summaries and Q&A can run on your device (Gemma / Ternary Bonsai over WebGPU) — no API key required.
• If you want a stronger model, you can plug in your own API key (Anthropic, OpenAI, Gemini, Groq, OpenRouter, Ollama, or any OpenAI-compatible endpoint).

2. The interface at a glance

Main view — top header, filters, toolbar, sortable report list.

The header runs across the top:

• Stats tell you how many reports the mirror has, how many committees, and how many have full extracted text yet.
• AI status pill tells you what AI is configured. Click it to jump to Settings.
  • AI off — nothing configured yet
  • Loading model… — local model downloading or warming up
  • Gemma 4 E2B ready — local model ready to use
  • BYOK: Anthropic — your API key configured
• Settings (⚙) — pick the AI mode, load a model, configure web search.
• Help (?) — what you're reading is the long-form version of that modal.

3. Browse, search, filter

Below the header, a row of filters narrows the list:

1. Search — substring match against titles by default. Open any report's Full text tab and that text becomes searchable too. To pre-fetch every extracted PDF and search across the entire corpus body content, enable Deep search in Settings (~25–500 MB download depending on backfill state — uses local cache after).
2. All committees — narrow to one of the 24 DRSCs.
3. All Lok Sabhas — most data is currently from LS18; older terms backfill over time.
4. All categories — auto-tagged from titles: DFG Demand for Grants · AT Action Taken · SUBJ Subject reports (BILL and ASSURE also exist).
5. Sort — newest first by default.

Each row also carries a status badge on the right:

• metadata — only metadata is published; no extracted text yet.
• text — full text has been extracted by the mirror and is searchable.
• summary — you've generated an AI summary that's cached in your browser.

4. Reading a report

Report dialog — Details tab. PDF links go straight to sansad.in.

Click any row to open a four-tab dialog:

• Details — committee, report number, dates, links to the English and Hindi PDFs on sansad.in, source attribution.
• Full text — the extracted text from the PDF (when available). Searchable, scrollable.
• AI summary — generate a plain-English briefing of the report. Cached in your browser after the first run.
• Ask — chat with the report. The model answers based on the report's text (and your cached summary, when one exists).

5. Setting up AI

Click the ⚙ Settings icon in the header (or the AI status pill). Pick one of two modes:

Settings → Local AI section.

Option A — Local AI (default, no key, free)

Runs an open-weight model entirely in your browser via Transformers.js on WebGPU. The first load downloads weights from Hugging Face; the browser caches them so subsequent visits are instant.

1. Open Settings. AI mode = Local AI.
2. Pick a model from the dropdown.
3. Click Load. First run shows a progress bar — your machine is downloading weights from Hugging Face.
4. When the status pill says "<model> ready", you can use AI summary and Ask in any report dialog.

Option B — BYOK (Bring Your Own Key)

Settings → BYOK section. Provider list mirrors upstream ParliamentWatch.

Send the request directly from your browser to the provider you choose. Your key stays in this browser's localStorage — never sent to any other server.

1. Open Settings. AI mode = BYOK.
2. Pick a provider. Get a key from the provider's website (links in the table at §12 Costs & limits).
3. Paste the key into the API key field. Optionally override the default model.
4. Click Save. The pill turns to "BYOK: <Provider>".

6. Generating an AI summary

AI summary tab — a freshly-generated 4-section briefing.

1. Make sure AI is configured (Local model loaded, or BYOK key saved).
2. Click any report row to open the dialog.
3. Switch to the AI summary tab.
4. Click Generate. The model streams a 4-section plain-English briefing (what it's about, key findings, recommendations, why it matters).
5. The summary is cached in your browser — opening that report again later shows it instantly. Click Regenerate for a fresh attempt.

7. Asking questions about a report

Ask tab — chat input scoped to the open report.

1. From the dialog, switch to the Ask tab.
2. Type a question. Press Enter or click Send.
3. The model gets the report's full text (truncated to fit the context window) plus your cached summary if one exists. It answers from the report only.
4. Each new question + answer is appended to the thread for the duration of the dialog. Closing the dialog resets the thread.

8. Web-search enrichment for Ask

Settings → Web search section.

Optional. When configured, you get a 🌐 button next to Send in the Ask tab. Clicking it does a web search first and feeds the top results into the prompt alongside the report text. Useful for "is there recent news on this?" or "has the government acted on this since the report?" style follow-ups.

1. Settings → Web search section.
2. Pick a provider. For Tavily / Brave, paste your API key. For SearXNG, paste the instance URL (e.g. https://searx.example.org).
3. Save. The 🌐 button appears in the Ask tab.

9. Exporting metadata and summaries

Two buttons live in the toolbar above the report list:

• ⬇ Metadata (CSV) — exports the currently filtered reports as CSV. 13 columns including has_text and has_summary. Useful for dropping into Excel / a notebook for analysis.
• ⬇ Summaries (MD) — exports every AI summary you've generated as a single Markdown file, with each report headed by title + committee + LS + report number.

Both downloads happen client-side — nothing leaves your machine.

10. Deep search (optional)

By default, search hits report titles. The instant you open a report's Full text tab, that body becomes searchable too — and stays cached locally forever. If you want to search across the entire corpus' body content without opening reports one-by-one, enable Deep search in Settings.

1. Open Settings → Search section.
2. Tick "Enable full-text search across all extracted reports". The estimate line tells you how much will download.
3. Save. The app starts fetching every extracted text in the background (4 concurrent, throttled). Status appears above the report list as "Indexing N/M…".
4. Once done, search now hits body content for the entire corpus. Cached locally — return visits use zero new bandwidth.

11. Privacy & what's cached locally

SansadSaar has no server. Everything you generate stays in your browser:

• API keys — localStorage, never sent except to the provider you chose.
• Generated summaries — IndexedDB store summaries. Persistent across sessions. Visible in DevTools → Application → IndexedDB → sansadlocal (legacy DB name, kept so existing data carries over).
• Extracted PDF text — IndexedDB store texts. Once fetched, it's there for life. On return visits, only newly-published reports get pulled from the mirror.
• Model weights — browser Cache Storage. ~1.5–4.9 GB depending on the model.
• Settings — localStorage key sansadlocal.settings.v1 (legacy key, preserved across the rename).

What leaves your browser:

• Fetches to sansad-files.naklitechie.com — the static data mirror, served from Cloudflare's edge. No tracking, no analytics.
• Fetches to huggingface.co — model weights, only on first load of a given model.
• BYOK requests go directly to your chosen provider. Your key isn't proxied anywhere.
• Search-enrichment requests go directly to your chosen search provider.

What never happens: no analytics, no accounts, no telemetry, no server logs (no server). The page is a static index.html served from GitHub Pages, fronted by Cloudflare for the custom domain.

12. Costs & limits — what's free, what isn't

Three layers of cost. The first is always free; the other two depend on your choice.

Layer 1 — SansadSaar infrastructure

Layer 2 — Local AI inference

Layer 3 — BYOK API providers (optional)

Layer 3b — Web-search enrichment (optional)

13. Troubleshooting

The local model won't load

• Check the AI status pill — if it says "No WebGPU", the browser doesn't support WebGPU. Use Chrome 113+, Edge 113+, Brave, or Firefox 130+.
• If it shows "Worker error", open DevTools console for the underlying message (network failure, OOM, model file corruption). The "Clear cache" button in Settings forces a re-download.

Generation is slow

• Local AI on a CPU-only machine is slow — WebGPU on a recent GPU is needed for usable speed. Check chrome://gpu in Chrome.
• Long reports get truncated to fit the model's context window (8K for Gemma 4 E2B, 32K for Bonsai 1.7B/4B, 64K for Bonsai 8B). For very long reports, the larger Bonsai models or a BYOK provider produce better summaries.

Ollama returns CORS errors

Ollama's HTTP API doesn't allow cross-origin requests by default. Set OLLAMA_ORIGINS when starting Ollama:

OLLAMA_ORIGINS="https://sansadsaar.naklitechie.com" ollama serve

If you opened the app via http://localhost:8000 for local dev, set OLLAMA_ORIGINS=http://localhost:8000 instead.

The mirror is missing data

The daily action runs at 04:30 UTC (10:00 IST). If a new report shows up on sansad.in mid-day, it'll appear in SansadSaar the next morning. Settings → Refresh from mirror force-fetches; on a fresh visit the latest data loads automatically.

Where do credits live?

Help → Credits tab. Open from the ? button in the header.

Built on top of ParliamentWatch by Pranay Kotasthane — the scraper, committee config, and original idea are his. SansadSaar repackages it with on-device AI. Full credit list in the Help → Credits tab.