ติดตั้ง Knowledge Rag อย่างไร?

คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP

Knowledge Rag ต้องใช้ API key ไหม?

ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น

Knowledge Rag ใช้ทรานสปอร์ตแบบใด?

Knowledge Rag ทำงานแบบโลคัลผ่าน stdio

เซิร์ฟเวอร์ MCP Knowledge Rag | PlugMCP

pip install knowledge-rag   →   restart Claude Code   →   search_knowledge("your query")

Decision	What to verify
Local or remote processing	Where models run, which client receives content, and which features need network access
Retrieval quality	Expected-source queries on your corpus, including its languages and identifiers
Performance	Cold initialization, indexing, uncached queries, memory peaks and concurrent use on comparable hardware
Operations	Authentication, metrics exposure, backups, recovery and one-writer ownership
Extensibility	Supported parsers, model profiles and the public MCP contract

pip install knowledge-rag
knowledge-rag init                    # scaffolds config.yaml + documents/

search_knowledge("your query")

# config.yaml
server:
  transport: "sse"                    # or "streamable-http"
  host: "0.0.0.0"
  port: 8179
  auth:
    bearer_token: "your-secret-token"
  rate_limit:
    enabled: true
    requests_per_minute: 60
  metrics:
    enabled: true
    port: 9179
  logging:
    format: "json"                    # ELK / Loki / Datadog / CloudWatch ready

knowledge-rag --transport sse

knowledge-rag --transport streamable-http
# MCP endpoint: http://127.0.0.1:8179/mcp

Transport	Clients	Shared index / process	RAM overhead	Process management	Startup & query latency	Best fit
`stdio`	1	No	1 runtime per client; models load lazily in each process when queried	Client manages its own process; no separate server	Spawns per client; pays preflight and first-query model load	Simplest local setup (single client)
`sse`	Many	Yes	Shared server process; single shared model load across clients	Operator manages one background server	Reuses warm server; first-query model load still applies	Legacy HTTP clients
`streamable-http`	Many	Yes	Shared server process; single shared model load across clients	Operator manages one background server	Reuses warm server; first-query model load still applies	Preferred shared-server setup

docker pull ghcr.io/lyonzin/knowledge-rag:latest
docker run -v $(pwd)/documents:/app/documents -p 8179:8179 ghcr.io/lyonzin/knowledge-rag:latest

#	Skill	What it does
1	`rag-check-first`	Search the corpus before answering any technical claim
2	`rag-cite-sources`	Every claim ships with `path:line` citations
3	`rag-onboard-context`	First interaction of a session probes what is indexed
4	`rag-deep-dive`	3-step drill: `search` → `fetch` → `find similar`
5	`rag-web-fallback`	Only hit the web when local RAG comes back empty
6	`rag-troubleshoot`	Bug / error → RAG first for prior fixes
7	`rag-code-review`	Review consults ADRs / patterns before commenting
8	`rag-index-decisions`	After a decision, index it back — close the feedback loop
9	`rag-security-first`	Security tasks: MITRE / CVE / runbook first
10	`rag-evaluate-quality`	Weekly checkup — MRR@5 · Recall@5 · Precision@5

# Option 1 — Via skills.sh (needs Node — one command, zero clone)
npx skills add lyonzin/knowledge-rag

# Option 2 — Via our install.sh (no Node needed; works on Linux/macOS/WSL/Git Bash)
curl -fsSL https://raw.githubusercontent.com/lyonzin/knowledge-rag/master/skills/install.sh | bash

Tool	Purpose
`search_knowledge`	Hybrid semantic + BM25 with cross-encoder rerank
`get_document`	Retrieve full content of one document
`search_similar`	Find documents similar to a reference
`evaluate_retrieval`	Measure MRR@5 · Recall@5 · Precision@5
`add_document`	Index a new document via MCP
`update_document`	Re-index a changed document
`remove_document`	Drop a document + all its chunks
`add_from_url`	Fetch, sanitize, and index a URL
`list_documents`	Enumerate indexed documents
`list_categories`	Auto-tagged by folder path
`get_index_stats`	Corpus size, cache hit rate, embedding dim
`reindex_documents`	Smart incremental OR nuclear rebuild
`get_reindex_status`	Live progress polling (async reindex)

flowchart TB
    subgraph CLIENTS["MCP Clients (any of these)"]
        C1[Claude Code]
        C2[Claude Desktop]
        C3[Cursor]
        C4[Windsurf]
        C5[VS Code · Cline · Gemini CLI · Zed]
    end

    subgraph TRANSPORT["Transport Layer"]
        T1[stdio<br/>1 process per client]
        T2[SSE / streamable-http<br/>1 server serves N clients]
    end

    subgraph MIDDLEWARE["ASGI Middleware Chain (HTTP mode)"]
        M1[HealthMiddleware<br/>/health · /healthz]
        M2[BearerAuthMiddleware<br/>constant-time compare]
        M3[Rate Limiter<br/>sliding window]
    end

    subgraph MCP["13 MCP Tools (frozen contract)"]
        MT1[search_knowledge]
        MT2[get_document · search_similar]
        MT3[add_document · add_from_url · update · remove]
        MT4[reindex_documents · get_reindex_status]
        MT5[list_documents · list_categories · get_index_stats · evaluate_retrieval]
    end

    subgraph SEARCH["Retrieval Pipeline"]
        R[Query Router<br/>lexical vs semantic]
        F[FTS5 Fast-Path<br/>opt-in lexical retrieval]
        BM[BM25 Inverted Index<br/>keyword candidates]
        SE[Semantic Search<br/>FastEmbed ONNX lazy-loaded]
        RRF[Reciprocal Rank Fusion]
        CE[Cross-Encoder Rerank<br/>MiniLM-L-6-v2]
        QC[Query Cache<br/>LRU + 5-min TTL]
    end

    subgraph STORAGE["Storage (100% local)"]
        CH[ChromaDB<br/>vectors + metadata<br/>WAL mode]
        FT[SQLite FTS5<br/>lexical index<br/>WAL + busy-timeout]
        MD[index_metadata.json<br/>durable state]
    end

    subgraph INGEST["Document Ingestion"]
        FS[documents/ folder]
        WD[Watchdog<br/>10s debounce]
        PA[Format parsers<br/>MD · PDF · DOCX · code · IaC · IPYNB]
        CK[Chunker<br/>markdown-aware · code-aware]
        EM[FastEmbed ONNX<br/>384D bge-small-en-v1.5]
        DD[SHA256 Dedup]
        SW[Staging Rebuild<br/>rollback on handled publication failure]
    end

    subgraph OBS["Enterprise Observability (opt-in)"]
        PM[Prometheus /metrics<br/>7 canonical + histograms]
        LG[Structured JSON logs<br/>ELK · Loki · Datadog · CloudWatch]
        HC[Health payload<br/>version · uptime · cache stats]
    end

    subgraph CFG["Configuration"]
        YM[config.yaml<br/>+ 5 domain presets]
    end

    C1 & C2 & C3 & C4 & C5 -->|MCP protocol| T1
    C1 & C2 & C3 & C4 & C5 -.->|remote deploy| T2
    T1 --> MCP
    T2 --> M1 --> M2 --> M3 --> MCP

    MT1 --> QC
    QC -->|cache miss| R
    R -->|lexical| F
    R -->|semantic| SE
    R -->|hybrid| BM
    F --> CH
    F --> FT
    BM --> CH
    SE --> CH
    BM --> RRF
    SE --> RRF
    RRF --> CE
    CE --> QC

    MT2 --> CH
    MT3 --> INGEST
    MT4 --> SW
    MT5 --> CH

    FS --> WD --> PA
    PA --> CK --> EM --> DD --> CH
    SW -.->|validated publication| CH
    SW -.-> FT
    CH -.-> MD

    MCP -.->|instrumented| PM
    MCP -.->|logs| LG
    M1 --> HC

    YM -.-> SEARCH
    YM -.-> STORAGE
    YM -.-> OBS
    YM -.-> MIDDLEWARE

    classDef client fill:#3776AB,stroke:#1e5a8a,color:#fff
    classDef transport fill:#00A67E,stroke:#006e54,color:#fff
    classDef middleware fill:#6b46c1,stroke:#4c1d95,color:#fff
    classDef storage fill:#4b5563,stroke:#1f2937,color:#fff
    classDef obs fill:#dc2626,stroke:#7f1d1d,color:#fff
    classDef ingest fill:#f59e0b,stroke:#78350f,color:#fff

    class C1,C2,C3,C4,C5 client
    class T1,T2 transport
    class M1,M2,M3 middleware
    class CH,FT,MD storage
    class PM,LG,HC obs
    class FS,WD,PA,CK,EM,DD,SW ingest

#	Format	Extension	Parser	Default	Notes
1	Markdown	`.md`	Section-aware (splits at `##`)	Yes	Headers preserved as chunk boundaries
2	Plain Text	`.txt`	Fixed-size chunking	Yes	1000 chars + 200 overlap
3	PDF	`.pdf`	PyMuPDF extraction or explicit page-marked UTF-8 text	Yes	No OCR; extracted-text recognition is limited to 4 MiB
4	Word	`.docx`	python-docx	Yes	Headings preserved as markdown
5	Excel	`.xlsx`	openpyxl	Yes	Sheet-by-sheet extraction
6	PowerPoint	`.pptx`	python-pptx	Yes	Slide-by-slide extraction
7	Jupyter Notebook	`.ipynb`	Cell-aware parser	Yes	Markdown + code cells only; skips outputs/base64
8	JSON	`.json`	Structure-aware	Yes	Flattened key-value extraction
9	CSV	`.csv`	Row-based parser	Yes	Headers + rows as text
10	XML	`.xml`	XML parser	Yes	Root element + namespace metadata
11	Python	`.py`	Code-aware parser	Yes	Functions/classes as chunks
12	C Source	`.c`	Code-aware parser	Yes	Functions / structs / includes extracted
13	C/C++ Header	`.h`	Code-aware parser	Yes	Function declarations + structs extracted
14	C++ Source	`.cpp`	Code-aware parser	Yes	Classes / structs / includes extracted
15	JavaScript	`.js`	Code-aware parser	Yes	Functions / classes / imports (ESM + CJS)
16	React JSX	`.jsx`	Code-aware parser	Yes	Same as JS parser
17	TypeScript	`.ts`	Code-aware parser	Yes	Functions / classes / interfaces / enums / imports
18	React TSX	`.tsx`	Code-aware parser	Yes	Same as TS parser
19	Go	`.go`	Code-aware parser	Yes	Functions / structs / imports extracted
20	Rust	`.rs`	Code-aware parser	Yes	Functions / structs / enums / traits / `use` imports
21	Kotlin	`.kt`	Code-aware parser	Yes	Functions (incl. class members) / classes extracted
22	YAML	`.yaml`	YAML parser	Yes	Kubernetes kind / apiVersion / name extracted
23	YAML	`.yml`	YAML parser	Yes	Same as YAML parser
24	HuJSON	`.hujson`	HuJSON parser	Yes	JSON with comments + trailing commas (e.g. Tailscale ACLs)
25	CUE	`.cue`	Code-aware parser	Yes	Imports / package extracted
26	Protocol Buffers	`.proto`	Proto parser	Yes	Services / messages / RPCs extracted
27	Rego	`.rego`	Code-aware parser	Yes	OPA policies — imports / package extracted
28	SQL	`.sql`	SQL parser	Yes	Table names + statement types extracted
29	Shell	`.sh`	Shell parser	Yes	Function names extracted
30	jq	`.jq`	Shell parser	Yes	Indexed as shell-style script
31	Dockerfile	`Dockerfile`	Text parser	Yes	Matched by exact filename (no extension)
32	Makefile	`Makefile`	Text parser	Yes	Matched by exact filename (no extension)
33	Tiltfile	`Tiltfile`	Code-aware parser	Yes	Starlark — `def` functions / `load()` extracted
34	MQL4 Source	`.mq4`	Code parser	No	MetaTrader — opt-in via `documents.supported_formats`
35	MQL4 Header	`.mqh`	Code parser	No	MetaTrader — opt-in via `documents.supported_formats`

# config.yaml — everything is optional; defaults just work

paths:
  documents_dir: "./documents"
  data_dir: "./data"

models:
  embedding:
    profile: "compact"                  # "compact" | "quality" | "multilingual" | "custom"
    gpu: "auto"                         # "auto" | "true" | "false" | "directml"
    device_id: null                      # DirectML: explicit DXGI adapter index
  reranker:
    enabled: true                       # cross-encoder rerank

search:
  default_results: 5
  max_results: 100

server:                                 # optional — SSE / HTTP mode
  transport: "stdio"                    # or "sse" / "streamable-http"
  auth:
    bearer_token: ""                    # set a secret to enable auth
  rate_limit:
    enabled: false
  metrics:
    enabled: false
  logging:
    format: "text"                      # or "json"

Requirement	How knowledge-rag delivers
Data locality (LGPD / GDPR / HIPAA)	100% on-premise, zero egress network calls after initial model download
Air-gapped deployment	ONNX models pre-cached; set `HF_HUB_OFFLINE=1` to enforce zero-network
CVE monitoring	Dependabot (weekly) + pip-audit + Socket + CodeQL
Supply chain security	PyPI Trusted Publishing via OIDC (no long-lived tokens)
Vulnerability disclosure	Private security advisory via SECURITY.md
Signed release attestations	GitHub release attestations on every published version
Dependency management	Version ranges in `requirements.txt` / `pyproject.toml`; resolve and record a tested environment for reproducibility
Authenticated access	Bearer token middleware on SSE / HTTP transports (constant-time compare, RFC 6750)
Rate limiting	Sliding-window per-client RPM + burst (opt-in, zero-cost when disabled)
Audit-ready logging	Opt-in structured JSON logs → ship to your SIEM
Path traversal defenses	CWE-22 / CWE-59 guards on 6 CRUD tools
External-content mitigation	Known-token neutralization and provenance fencing on `add_from_url`; not a general prompt-injection prevention guarantee

Doc	What's inside
Installation guide	5 install methods · 8 MCP client integrations · GPU setup
API reference	Complete reference for all 13 MCP tools
Configuration reference	Every `config.yaml` field · presets · tuning
Architecture	Components · query/ingestion flow · memory/concurrency boundaries · hybrid weights
Troubleshooting	11 common issues + solutions
FTS5 fast-path guide	Opt-in lexical fast-path — when and how
Reindex operations	Zero-downtime rebuild · resume · checkpoint
GPU setup	CUDA runtime compatibility · CPU fallback · AMD/macOS GPU limitations
Migration to v4.8.0	Embedding profile · multilingual · zero-downtime
Security policy	Threat model · disclosure channel
Contributing	Development · testing · PR process
Changelog	All release notes since v1.0.0
Memory/GPU audit	Reproducible workloads · measured results · validation limits · open PR/issue review

Knowledge Rag

Q: Knowledge Rag ถูกตรวจสอบล่าสุดเมื่อใด?

ตรวจสอบล่าสุดเมื่อ 2026-11-08 Local RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder reranking on by default, 13 MCP tools, 33 file types including code, re-indexing on file changes. One Python process with embedded ChromaDB and FastEmbed ONNX: no Docker, database server or API key; offline after the first model download.

lyonzin303 ดาว

Local RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder reranking on by default, 13 MCP tools, 33 file types including code, re-indexing on file

Knowledge Memory Databases Devops

ติดตั้ง รันบน PlugMCPอ้างสิทธิ์เซิร์ฟเวอร์นี้

GitHub

รันบน PlugMCP

1# Knowledge Rag

README.mdเซิร์ฟเวอร์ MCP

ทรานสปอร์ต: stdio
สถานะ: โลคัล

เพิ่มเซิร์ฟเวอร์นี้

Host a copy with our keys and logs.

ข้อมูลเซิร์ฟเวอร์

เอกสารประกอบ

knowledge-rag

The MCP-first local RAG server for Claude Code, Cursor, and every AI agent.

⭐ Star History

🎯 Why knowledge-rag

🔒 100% local, 0% cloud

🚀 Zero-friction setup

🛡️ Production-grade OSS

💰 Zero ongoing cost

📊 How knowledge-rag compares to other RAG frameworks

The audit report records a reproducible local workload and its limitations. Results against an older implementation of this project are not speed comparisons against other RAG frameworks.

🚀 Quick Start (3 minutes, from zero to your first query)

Path 1 — Claude Code, Cursor, Windsurf, Cline, VS Code, Gemini CLI, Zed (MCP)

Path 2 — HTTP / SSE server (multi-user, air-gapped, load-balanced)

Multi-client setup (Shared Server via Streamable HTTP)

Path 3 — Docker (models pre-downloaded, air-gapped ready)

🤖 Ready-to-use skills for AI agents

🛠️ The 13 MCP tools your agent gets

🏢 Enterprise Features (built-in, zero configuration)

Security

Observability

Scale & performance

Reliability

💼 Use Cases (real corpora, real teams)

Security Teams — Red / Blue / CTF

Development Teams — Design Docs, Runbooks, Code

Research Labs — Papers, Notebooks, Datasets

Enterprise Knowledge Base — Air-gapped, Auditable

🏗️ Architecture at a glance

📄 35 File Formats — parsed natively, no plugins needed

🔌 Choose your MCP integration

⚙️ Configuration in 30 seconds

🔒 Security & Compliance

📈 Numbers that matter

The public benchmark dashboard tracks CI workloads. Mocked storage/model workloads and real-model measurements answer different questions; inspect the methodology and units before comparing them.

📚 Documentation

🤝 Community & Support

🗺️ Recent releases

📜 License

🙏 Acknowledgments

เกี่ยวกับ Knowledge Rag

เครื่องมือ

คำถาม

ติดตั้ง Knowledge Rag อย่างไร?

Knowledge Rag ต้องใช้ API key ไหม?

Knowledge Rag ใช้ทรานสปอร์ตแบบใด?

Knowledge Rag ถูกตรวจสอบล่าสุดเมื่อใด?