nlweb-retrieval-backends

nlweb-retrieval-backends is a skill for Claude Code from OrcaQubits/agentic-commerce-skills-plugins. It costs 120 tokens per session (2,013 once invoked), scanned A, original, MIT.

A guide to choosing and configuring the search systems NLWeb uses to find relevant content. It covers systems such as Qdrant, Azure AI Search, Elasticsearch, PostgreSQL with pgvector, Snowflake, Cloudflare AutoRAG, and web search.

In plain words
What is it for?
Use it to select a search backend, configure its endpoint and environment variables, load data into it, and set up combined searches across multiple sources.
Why use it?
It helps avoid mismatched settings between the search system and the model that creates search vectors, and explains how reading from several systems differs from writing to one.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the nlweb-protocol plugin — 13 skills, 1 agent shipped together

Good fit Use it to select a search backend, configure its endpoint and environment variables, load data into it, and set up combined searches across multiple sources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-retrieval-backends
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add OrcaQubits/agentic-commerce-skills-plugins --skill nlweb-retrieval-backends
Clone the repo
git clone --depth 1 https://github.com/OrcaQubits/agentic-commerce-skills-plugins

Made for: Claude Code.

Or install nlweb-protocol, the plugin that ships this one along with the rest of its 13 skills, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for nlweb-retrieval-backends

README.md
[![agentmods](https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-retrieval-backends/github.svg)](https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-retrieval-backends)
Your own site
<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-retrieval-backends"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-retrieval-backends/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nlweb-retrieval-backends

Your own site · 80×15
<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-retrieval-backends"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-retrieval-backends.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,013 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00120 $0.02013
Opus 5 $0.00060 $0.01007
Sonnet 5 $0.00024 $0.00403
Haiku 4.5 $0.00012 $0.00201

Measured 2d ago against content hash e54eba249f25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-16, from the pricing page.

Security

Grade A, and why

nlweb-retrieval-backends scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. `curl http://localhost:8000/sites` — site is registered?
nlweb-protocol/skills/nlweb-retrieval-backends/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NLWeb Retrieval Backends

Before writing code

Fetch live docs:

  1. Fetch https://github.com/nlweb-ai/NLWeb/blob/main/docs/nlweb-retrieval.md for the architectural overview.
  2. Fetch https://github.com/nlweb-ai/NLWeb/blob/main/config/config_retrieval.yaml for the canonical list of endpoint names and their defaults — config keys move release to release.
  3. Pick the per-backend setup page from docs/setup-*.md (Qdrant, Azure AI Search, Elasticsearch, OpenSearch, Postgres, Snowflake, Cloudflare AutoRAG).
  4. Inspect AskAgent/python/retrieval_providers/<backend>.py for the exact client signature and required env vars.
  5. Verify the embedding dimension and metric (cosine/dot/L2) the backend expects — must match the embedding provider.

Conceptual Architecture

The Read-Fanout, Single-Write Pattern

NLWeb does something unusual: it reads from every enabled retrieval endpoint in parallel and deduplicates by URL, but writes go to exactly one write_endpoint. This means:

  • You can run a hybrid index (e.g., local Qdrant for site content + Bing for fresh news) without code changes
  • You migrate between backends by re-running db_load against the new write_endpoint
  • "Result quality" is the union of all enabled stores — a noisy backend pollutes the top-k

All Supported Backends

Endpoint key (config_retrieval.yaml) Backend Notes
qdrant_local Qdrant file-backed Default-enabled; data in ../data/db
qdrant_url Qdrant remote Set URL + API key in env
nlweb_west Azure AI Search Default-enabled MS-hosted demo instance — usually disable
azure_ai_search Azure AI Search (your own) Bring your own index name
milvus Milvus Flagged "under development" in YAML
elasticsearch Elasticsearch dense_vector + int8_hnsw
opensearch_knn OpenSearch + k-NN plugin The recommended OpenSearch path
opensearch_script OpenSearch no plugin script_score fallback, slower
postgres Postgres + pgvector Good if you already run Postgres
snowflake_cortex_search_1 Snowflake Cortex Search Data lives in Snowflake tables
cloudflare_autorag Cloudflare AutoRAG Indexing managed by CF; ingest via R2
shopify_mcp Shopify's MCP endpoint Default-enabled; live proxy, no ingest
bing_search Bing Web Search API Live web fallback; not a vector store

Read the full file on GitHub · 161 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 161 lines · 120 tokens per session scan A e54eba249f25

Subscribe to this mod's changes

nlweb-retrieval-backends is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 2d ago), licensed MIT. It adds 120 tokens to every session and 2,013 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-15.

Related

Other skills, from other repositories

pgvector-semantic-search

Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…

timescale/pg-aiguide · 190 tokens

postgres-hybrid-text-search

Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…

timescale/pg-aiguide · 162 tokens

ai-vector-brain

Builds vector-brain implementations for repos, docs hubs, and compliance corpora. Use when creating pgvector retrieval brains with scripts, SQL, manifests, and evals.

vasilyu1983/AI-Agents-public · 40 tokens

vector-db-rag-expert

Expert guide for high-performance Vector Databases, Deep RAG architectures, pgvector 0.8+ HNSW, Reciprocal Rank Fusion (RRF), Cross-Encoder Re-ranking, and Late Chunking / Panduan ahli Vector DB, arsitektur Deep RAG, pgvector HNSW, RRF, dan Re-ranking.

roedyrustam/vibes-plug · 77 tokens

postgres-semantic-search

PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector indexing, hybrid FTS/BM25 + RRF, ParadeDB, reranking, halfvec, multilingual search, query translation, and domain evals.…

laguagu/claude-code-nextjs-skills · 228 tokens

laravel-vector-search

Use when implementing semantic/vector search in Laravel 13 with PostgreSQL + pgvector.

fusengine/agents · 22 tokens