Index of every page on this site: llms.txt
All skills
tencent avatar

/weknora-rag-search

@1b3a1fe
by tencenttencent/weknora38k stars
5,278
Run it yourself

Use when retrieving from or asking questions against a WeKnora knowledge base via the `weknora` CLI — and especially when unsure whether to use `chat`, `session ask`, or `search chunks` for a given goal.

Use this Skill: https://skilld.dev/gh/tencent/weknora/weknora-rag-search

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈56 tokens for metadata: the name and description. ≈961 when used: this file. ≈1.2k more on demand in 2 files.

Description uses 2.8% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈224 characters, or 2.8%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

WeKnora — retrieval & RAG queries

REQUIRED BACKGROUND: read the weknora-shared skill first (auth, --kb resolution, the JSON envelope, exit codes, streaming/NDJSON output).

WeKnora gives you several ways to "ask about a knowledge base." Picking the wrong one wastes turns or returns the wrong shape. Use the decision table.

Pick the command by your goal

Your goal Command LLM synthesis? Returns
Natural-language answer grounded in a KB chat "<q>" --kb <kb> yes bounded answer events; --reference adds citations; --verbose adds execution detail
Answer via a custom agent (its own KB scope, tools, web search) session ask --agent <id> "<q>" yes (+ tools) bounded answer events; --reference adds citations; --verbose adds execution detail
Raw context chunks to reason over yourself (no answer) search chunks "<q>" --kb <kb> no ranked chunk list
Which documents match a keyword (title/filename) search docs "<q>" --kb <kb> no document list
Find a knowledge base by name search kb "<q>" no KB list
Find a past session by title search sessions "<q>" no session list

The three decisions that matter

  1. Answer vs raw context. Want a written answer → chat / session ask. Want chunks to feed into your own reasoning (e.g. you'll synthesize across sources) → search chunks. Don't call chat just to read source text.
  2. chat vs session ask. chat = plain KB RAG Q&A. session ask --agent <id> = invoke a configured custom agent (it may scope its own KBs, call tools, do web search). If the user set up an agent for this, prefer it (weknora agent list to find ids); otherwise chat.
  3. One-shot vs multi-turn. Both chat and session ask return a data.session_id in default JSON output. Pass --session <id> on the next call to continue the conversation. In NDJSON mode, read it from init.

Safety / Gotchas

  • chat, search chunks, search docs need a KB: pass --kb <id-or-name>, or set WEKNORA_KB_ID, or weknora link the directory (resolved in that order). If none resolves it's exit 1 (local.kb_id_required); a bad name is exit 1 (local.kb_not_found). Resolve names with weknora kb list / search kb. (search kb / search sessions are tenant-wide and take no --kb.)
  • chat / session ask return one buffered JSON envelope with answer events by default. Add --reference for indexed citations and --verbose for execution detail; use --format ndjson for raw events or --format text for the live human-readable projection.
  • A stalled stream is not stopped by Ctrl-C (that just drops your local connection; the server keeps generating + billing). Stop it server-side: weknora session stop <session-id> --message <message-id> (session_id from data.session_id, or from init under --format ndjson). Re-attach to a stream with weknora session resume <session-id> --message <message-id>.
  • search chunks --limit defaults to 8 (tuned for an LLM context window); the search docs/kb/sessions lists default to 30. Tune retrieval with --vector-threshold / --keyword-threshold, or --no-vector/--no-keyword to disable a channel. Details: references/search-chunks.md.

Quick examples

# raw retrieval to reason over
weknora search chunks "retry backoff policy" --kb engineering --limit 12

# grounded answer (human transcript)
weknora chat "How do we handle retries?" --kb engineering --format text

# continue the conversation (session id from data.session_id above)
weknora chat "And the max attempts?" --kb engineering --session sess_abc

# answer via a custom agent
weknora session ask --agent ag_123 "Summarize this quarter's incidents"

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts21d3 checks · Risk SAFE
  • Gen Agent Trust Hub21d

    This skill consists entirely of documentation and guidance for using the WeKnora CLI tool for retrieval and RAG tasks. It contains no executable code, network operations, or security risks.

  • Socket21d

    No alerts

  • Snyk21d

    Risk: LOW · No issues

Signed by skilld at 1b3a1fe. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 5 months ago
metadata
{
  "tested_against": "v0.10"
}

README badge

README badge for tencent/weknora/weknora-rag-search