MCPInstall

dify-knowledge-base-upload

by tiangong-aiAI & Agents

Upload local files to a Dify pipeline knowledge base through the published pipeline datasource flow and optionally apply existing metadata fields. Use when the target dataset is a published ragpipeline/localfile knowledge base or ordinary Dify document create APIs return completed with 0 chunks.

Installs
42
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/tiangong-ai/agent-skills --skill dify-knowledge-base-upload
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads dify-knowledge-base-upload automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Dify Knowledge Base Upload

Use this skill when

  • The target Dify knowledge base is backed by a published pipeline datasource.
  • UI uploads succeed but document/create-by-file or create-by-text yields completed with 0 chunks.
  • You need to upload one local file and optionally write existing metadata fields afterward.

Prepare caller-side inputs

  • Provide a local file path to upload.
  • For pure text, save it as .txt or .md first and upload that file.
  • Set caller env values:
    • DIFY_API_BASE_URL
    • DIFY_DATASET_ID
    • DIFY_API_KEY
  • Optionally provide pipeline inputs JSON if the published pipeline exposes user input variables.
  • Optionally provide metadata JSON:
    • a flat object mapping existing Dify metadata field names to values, or
    • a list of { "name": ..., "value": ... } / { "id": ..., "value": ... } items.
    • The skill does not hardcode your metadata schema. Pass the current field names or ids in the JSON you provide at runtime.
  • Read references/env.md only if you need env or debug details.

Run workflow

  • Use scripts/upload_to_dataset.py to:
    • discover the published datasource plugin from ${DIFY_API_BASE_URL}/datasets/${DIFY_DATASET_ID}/pipeline/datasource-plugins?is_published=true
    • upload the file to ${DIFY_API_BASE_URL}/datasets/pipeline/file-upload
    • run the published pipeline through ${DIFY_API_BASE_URL}/datasets/${DIFY_DATASET_ID}/pipeline/run
    • poll ${DIFY_API_BASE_URL}/datasets/${DIFY_DATASET_ID}/documents/{batch}/indexing-status
    • fetch ${DIFY_API_BASE_URL}/datasets/${DIFY_DATASET_ID}/documents/{document_id}?metadata=without
    • optionally resolve metadata field names through ${DIFY_API_BASE_URL}/datasets/${DIFY_DATASET_ID}/metadata
    • optionally update metadata through ${DIFY_API_BASE_URL}/datasets/${DIFY_DATASET_ID}/documents/metadata
  • Upload without metadata:
python3 scripts/upload_to_dataset.py \
  --file /path/to/document.pdf
  • Upload with pipeline inputs:
python3 scripts/upload_to_dataset.py \
  --file /path/to/document.pdf \
  --inputs-json assets/example-pipeline-inputs.json
  • Upload and then apply metadata:
python3 scripts/upload_to_dataset.py \
  --file /path/to/document.pdf \
  --metadata-json assets/example-metadata.json

Interpret response

  • Success prints JSON with batch, document_id, file_upload_response, pipeline_run_response, indexing_status_response, document_response, optional metadata_response, and validation.
  • validation.ok is only true when:
    • indexing_status = "completed"
    • total_segments > 0
    • segment_count > 0
  • If tokens is returned by the document detail API, it should also be greater than 0. Some pipeline deployments leave tokens = null; the script reports that as a warning instead of a hard failure.
  • The script exits non-zero if the required checks fail.
  • If --metadata-json is omitted, the script uploads the file only and skips metadata API calls.
  • Metadata keys must already exist in the target dataset. Unknown names fail fast before the metadata write request.
  • assets/example-metadata.json is only a template. Replace its keys with your own existing Dify metadata field names before live use.
  • Use --dry-run to validate local files and request shape without calling Dify.

Troubleshoot quickly

  • If auth fails, verify DIFY_API_KEY and Authorization header format.
  • If datasource discovery fails, verify the dataset has a published pipeline datasource and the key belongs to that dataset.
  • If the pipeline run fails with missing input errors, inspect user_input_variables from discovery_response and pass the missing keys in --inputs-json.
  • If the published datasource is not local_file, this skill is not the right uploader.
  • If metadata resolution fails, rename keys in the metadata JSON to the exact field names defined in Dify.
  • If you only have raw text, save it to .txt or .md and upload that file.
  • In the current tested deployment, .md uploaded successfully while .txt hit a Dify-side indexing 400. If plain text fails as .txt, retry as .md.

References

  • references/env.md
  • references/request-response.md
  • references/testing.md

Assets

  • assets/example-pipeline-inputs.json
  • assets/example-metadata.json

FAQ

What does the dify-knowledge-base-upload skill do?

Upload local files to a Dify pipeline knowledge base through the published pipeline datasource flow and optionally apply existing metadata fields. Use when the target dataset is a published ragpipeline/localfile knowledge base or ordinary Dify document create APIs return completed with 0 chunks.

How do I install dify-knowledge-base-upload?

Run npx skills add https://github.com/tiangong-ai/agent-skills --skill dify-knowledge-base-upload in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/dify-knowledge-base-upload/ (personal) or .claude/skills/dify-knowledge-base-upload/ (project).

Which AI agents can use dify-knowledge-base-upload?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is dify-knowledge-base-upload safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains dify-knowledge-base-upload?

It is published by tiangong-ai in tiangong-ai/agent-skills. It has 42 recorded installs.

More from tiangong-ai/agent-skills

View all →

email-smtp-send

tiangong-ai/agent-skills

Send emails through SMTP with optional local attachments and optional IMAP APPEND sync to Sent mailbox. Use when tasks need reliable outbound email delivery, attachment sending, SMTP connectivity checks, or cross-client sent-mail visibility (for example appending to "Sent Items" after SMTP send).

Productivity & Automation6.8K installs

email-imap-fetch

tiangong-ai/agent-skills

Listen for one or more IMAP inboxes with the IDLE command, fetch unread email metadata plus text previews, and forward each message to OpenClaw webhooks. Use when tasks need near-real-time mailbox monitoring, multi-account inbox ingestion via environment variables, and automatic trigger delivery into OpenClaw automation.

Productivity & Automation372 installs

ai-tech-rss-fetch

tiangong-ai/agent-skills

Subscribe to AI and tech RSS feeds and persist normalized metadata into SQLite using mature Python tooling (feedparser + sqlite3). Use when adding feed URLs/OPML sources, running incremental sync with deduplication, and storing entry metadata without full-text extraction or summarization.

AI & Agents235 installs

dify-knowledge-base-search

tiangong-ai/agent-skills

Open the skill to read its SKILL.md instructions.

AI & Agents111 installs

document-granular-decompose

tiangong-ai/agent-skills

Open the skill to read its SKILL.md instructions.

AI & Agents102 installs

email-imap-full-fetch

tiangong-ai/agent-skills

Open the skill to read its SKILL.md instructions.

Productivity & Automation91 installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs