Build Pinecone

KINDAreplaces $20/mosaves $240/yrback to the verdict

0%0 of 16 items done

Saved on this device only. Tick prerequisites first, then work the phases in order · do not start one until the checks above it pass.

Semantic search over your own documents with pgvector in the Postgres you already run: chunked documents with embeddings, cosine search with an HNSW index, hybrid ranking with full-text so exact identifiers still win, a localhost search page, and backups that are just pg_dump.

estimated effort one sittingthe files for this build are in the project pack

DatabasePostgres 16 with pgvectorEmbeddingsA provider behind an interfaceRuntimeNode 22

Before step 1

Everything below is assumed from the first step. Tick each one when you actually have it, not when you plan to.

installfree
Why Everything in this build runs on it: the server, the scripts, the tests.
Get it Download the LTS installer from nodejs.org, or install with your package manager (brew install node, or nvm install 22). Restart the terminal afterwards. open ↗
Verify node --version prints v22 or higher
installfree
Why Every step below is a command you type or a file you edit.
Get it VS Code (code.visualstudio.com), Cursor or Zed. Open a folder for the project and use the editor's built-in terminal. open ↗
Verify You can open a folder and run a command in its terminal
installfree
Why History for your code, and the way most hosts deploy.
Get it Install from git-scm.com or with your package manager, then run git init in the project folder once it exists. open ↗
Verify git --version prints a version
installfree
Why The whole store.
Get it Docker: docker run -d -e POSTGRES_PASSWORD=pw -p 5432:5432 pgvector/pgvector:pg16. Or install pgvector on an existing Postgres. open ↗
Verify CREATE EXTENSION vector; succeeds
API keypay per use, or free locally
Why Phase 1 embeds chunks.
Get it OpenAI: platform.openai.com/api-keys. Local: install Ollama and ollama pull nomic-embed-text. open ↗
have readyfree
Why Markdown, PDFs converted to text, or a folder of notes.
Get it A folder of files.

Data model

Create these before the first phase that stores anything. Changing a table later is the expensive kind of change.

- documents: id, source, title, url, updated_at
- chunks: id, document_id, position, text, embedding vector(N), token_count
Chunks, not documents, carry the vectors: a 40-page PDF as one vector matches nothing well.

Environment variables

These go in a .env file the app reads at startup. The pack's .env.example is this table as a file · copy it, never commit the filled-in version.

Variable	Needed	Example	Where the value comes from
`DATABASE_URL`secret	required	`postgres://postgres:pw@localhost:5432/search`	Your Postgres.
`EMBED_PROVIDER`	required	`openai`	openai or ollama.
`OPENAI_API_KEY`secret	optional	`sk-...`	For the openai provider.
`EMBED_MODEL`	required	`text-embedding-3-small`	Model name; dimension must match the column.
`DOCS_DIR`	required	`./docs`	Where the ingester reads.

The build, in order

1
Store and embed
Chunks with vectors, idempotent on document hash, provider swappable.
1. documents (id, source, title, url, updated_at, hash), chunks (id, document_id, position, text, embedding vector(N), token_count). N matches EMBED_MODEL's dimension.
  Files schema.sql
  terminal
  mkdir semantic && cd semantic && git init && npm init -y && npm pkg set type=module && npm install pg@8 mkdir -p docs && cp .env.example .env
done when · tick each as it passes
next phase
2
Search
Top-k by cosine with an HNSW index actually used.
1. terminal
  CREATE INDEX ON chunks USING hnsw (embedding vector_cosine_ops);
2. terminal
  EXPLAIN ANALYZE SELECT ... ORDER BY embedding <=> $1 LIMIT 10;
done when · tick each as it passes
next phase
3
Hybrid
Exact identifiers win: fuse vector and full-text ranks.
done when · tick each as it passes
next phase
4
A page
Localhost search with highlighted passages and source links.
done when · tick each as it passes
next phase
5
Operate
Migrations, pg_dump, reindex.
2. Files README.md
done when · tick each as it passes
next phase
6
Serve it to othersproduct builder
Auth, rate limits, and cost visibility.
done when · tick each as it passes

what this build does not replace

Billions of vectors and serverless scale; under a few million this is a column.
serverless scaling to billions of vectors
zero-ops managed indexes
hybrid and sparse search features
the SLA

after v1, if you want it

Re-ranking with a cross-encoder
Per-user document permissions

Need the files? The project pack on the verdict page hands your agent the whole brief · more databases.