mirror of https://github.com/bendtherules/ask262.git synced 2026-08-18 13:21:55 +00:00

T

bendtherules 3b6e9a9d8f refactor(ingest): restructure section document creation logic and add warnings for oversized documents

- Move full‑section Document creation into an `else` block so it only occurs when no sub‑documents were created.
- Remove premature return that skipped adding the full section.
- Add post‑processing loop to log a warning for any final document exceeding `LARGE_DOC_THRESHOLD`.

2026-03-31 13:54:07 +05:30

.opencode/plans

docs(plans): add migration plan for LlamaIndex → LangChain.js + LanceDB

2026-03-31 12:21:06 +05:30

engine262

build: migrate to Typescript + biome

2026-03-27 17:33:58 +05:30

setup

refactor(ingest): restructure section document creation logic and add warnings for oversized documents

2026-03-31 13:54:07 +05:30

spec-built

build: Internal method linking - plan and basic script

2026-03-30 12:43:40 +05:30

.gitignore

spec - Remove all style tags

2026-03-27 18:36:24 +05:30

agent.ts

Migrate to langchain

2026-03-31 13:06:59 +05:30

AGENTS.md

docs: add AGENTS.md

2026-03-31 12:20:58 +05:30

biome.json

chore: Lint fixes

2026-03-27 17:47:12 +05:30

bun.lock

ingest.ts - handle empty db, add loader

2026-03-31 13:46:19 +05:30

constants.ts

refactor(constants): move SPEC_DIR and CODE_DIR to constants

2026-03-27 17:53:16 +05:30

package.json

ingest.ts - handle empty db, add loader

2026-03-31 13:46:19 +05:30

Readme.md

build: basic setup (gemini-3-flash)

2026-03-26 19:04:48 +05:30

tsconfig.json

chore: Type-check fixes

2026-03-27 17:48:02 +05:30

Readme.md

RAG Pipeline for Language Specification Exploration

This project implements a RAG-based AI chat agent to explore the ECMAScript specification and its implementation in engine262.

Prerequisites

Node.js: Version 18+
Ollama: Installed locally with an embedding model (e.g., nomic-embed-text)
OpenAI-compatible Endpoint: A hosted or local LLM service

Setup

Install dependencies:
```
npm install
```

Prepare environment:

export OPENAI_API_BASE="your_endpoint_base_url"
export OPENAI_API_KEY="your_api_key"

Clone specification: (Ensure ./spec-built/multipage contains the HTML files)
Ingest data:
```
node ingest.mjs
```
Note: This will take significant time as it generates local embeddings via Ollama for both the spec and the implementation.
Build graph:
```
node build_graph.mjs
```

Usage

Ask the agent questions about how code relates to the specification:

node agent.mjs "Explain how the 'if' statement works and show its implementation."

The agent will use tools to search the specification, explore the implementation code, and navigate the relationships between them using the graph.