chore: move timescale docs import into repo

Signed-off-by: Matthew Peveler <mpeveler@timescale.com>

Author: MasterOdin

.env.sample

@@ -3,4 +3,5 @@ PGHOST=postgres
 PGDATABASE=tsdb
 PGPORT=5432
 PGUSER=readonly_mcp_user
-PGPASSWORD=todo
+PGPASSWORD=todo
+DB_SCHEMA=docs

import/pyproject.toml

@@ -0,0 +1,15 @@
+[project]
+name = "docs-importer"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.13"
+dependencies = [
+    "bs4>=0.0.2",
+    "langchain-text-splitters>=0.3.9",
+    "markdownify>=1.1.0",
+    "openai>=1.97.1",
+    "psycopg[binary,pool]>=3.2.9",
+    "python-dotenv[cli]>=1.1.1",
+    "scrapy>=2.13.3",
+]

import/timescale_docs.py

@@ -0,0 +1,23 @@
+# Configuration for domain-specific element removal
+# Add CSS selectors to ignore for each domain
+
+[domain_selectors]
+docs_tigerdata_com = [
+  "script",
+  "style",
+  "nav",
+  "footer",
+  "#plan-availability",
+  ".sr-only",
+  ".code-block-copy-button"
+]
+# Add more domains as needed
+
+# Default selectors applied to all domains
+[default_selectors]
+selectors = [
+  "script",
+  "style",
+  "nav",
+  "footer"
+]

import/timescale_docs_config.toml

@@ -0,0 +1,74 @@
+import 'dotenv/config';
+import { Client } from 'pg';
+
+const schema = process.env.DB_SCHEMA;
+if (!schema) {
+  throw new Error('DB_SCHEMA is not defined');
+}
+
+export const description = 'Create schema and memory table';
+
+export async function up() {
+  const client = new Client();
+
+  try {
+    await client.connect();
+    await client.query('BEGIN');
+    await client.query(/* sql */ `
+      CREATE EXTENSION IF NOT EXISTS vector;
+
+      CREATE TABLE IF NOT EXISTS ${schema}.postgres(
+        id int8 NOT NULL PRIMARY KEY generated by default as identity
+        , version int2 NOT NULL
+        , header text NOT NULL
+        , header_path text[] NOT NULL
+        , header_depth int4 NOT NULL
+        , content text NOT NULL
+        , token_count int8 NOT NULL
+        , embedding vector(1536)
+      );
+
+      CREATE TABLE ${schema}.timescale_pages (
+        id int4 PRIMARY KEY generated by default as identity
+        , url TEXT UNIQUE NOT NULL
+        , domain TEXT NOT NULL
+        , filename TEXT NOT NULL
+        , content_length INTEGER
+        , scraped_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+        , chunking_method TEXT DEFAULT 'header'
+        , chunks_count INTEGER DEFAULT 0
+      );
+
+      CREATE TABLE IF NOT EXISTS ${schema}.timescale_chunks (
+        id int4 PRIMARY KEY generated by default as identity
+        , page_id INTEGER REFERENCES ${schema}.timescale_pages(id) ON DELETE CASCADE
+        , chunk_index INTEGER NOT NULL
+        , sub_chunk_index INTEGER NOT NULL DEFAULT 0
+        , content TEXT NOT NULL
+        , metadata JSONB
+        , embedding vector(1536)
+        , created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+      );
+    `);
+    await client.query('COMMIT');
+  } catch (e) {
+    await client.query('ROLLBACK');
+    throw e;
+  } finally {
+    await client.end();
+  }
+}
+
+export async function down() {
+  const client = new Client();
+
+  try {
+    await client.connect();
+    await client.query(/* sql */ `
+      DROP INDEX IF EXISTS ${schema}.idx_memory_key;
+      DROP TABLE IF EXISTS ${schema}.memory
+      `);
+  } finally {
+    await client.end();
+  }
+}