🧠 OpenRAG
OpenRAG is a RAG platform that cleans and structures a business's content, indexes it on our own server, and makes it queryable in natural language by external AI systems through a single permissioned door.
Vectors are not published; ACCESS is opened.
This is a product introduction, not a list of promises. Below, the parts that work today and the parts still on the roadmap are marked separately. No dates are promised for roadmap items; as they are completed they move into the "working today" section.
The core principle
OpenRAG's entire design rests on a single sentence: vectors are not published, access is opened. What is given to the outside is not a copy of the content, but the right to ask questions of it.
A vector is an engine, not a product
A vector is specific to the model that produced it; another AI cannot consume it as-is. It also inflates the text many times over. That is why vectors are never handed out.
What is opened is query access
A question comes in; an answer and the source passages it rests on go back out. The full content is never copied, distributed or downloaded.
Permission belongs to the business
The business decides which content becomes externally queryable; participation is opt-in. The permission and consent layer is on the roadmap.
How it works — target architecture
The cleaning, structuring, indexing and search links of this flow work today. Self-hosted embedding with reranking, and the single door to the outside world, are still on the roadmap; each step below states which is which.
Sources are collected
xloji sites, uploaded documents and crawled web pages are the content sources. (A WordPress plugin and a public ingestion API are on the roadmap.)
It is cleaned and structured
Messy content is cleaned, split into meaningful chunks and brought into a form RAG can use. This step works today.
It is indexed and searched
Chunks are turned into vectors and written to pgvector; they are found via an HNSW index and hybrid search (keyword + vector). This step works today; adding the reranking link is on the roadmap.
It is reached through a single door
External AI systems ask in natural language through a single permissioned door; answers and source passages come back, not the vectors themselves. This door does not exist yet; it is on the roadmap.
Parts that work todayLive
The following are running on the platform today and are already used by the AI tools on xloji.com.
pgvector + HNSW index
Content chunks are stored as vectors in the database and searched with an HNSW index over cosine similarity.
Hybrid search
Keyword search and vector search run together; the two result lists are fused into a single ranking. This finds both exact term matches and semantically close passages.
Multi-tenant isolation
Every business, site and author has its own RAG. A query runs only against its own tenant's index; data never mixes across tenants.
Document cleaning and RAG structuring
Uploaded documents are cleaned, chunked and structured for RAG. The Data Structuring tool on the platform is the user-facing face of this pipeline.
Web crawling
A site's pages are crawled, their content is extracted and passed through the same cleaning and indexing pipeline.
Public RAG feed in custom AI tools
A custom AI tool you create can be fed from a public RAG source; the tool grounds its answers in that knowledge base.
File and media storage
Files and media live in object storage — not in the vector store. The RAG record points back to the original file.
Qodka iyo dib u kala soocidda oo lagu sameynayo server-yadeena
Qodka iyo dib u kala soocidda hadda waxay ka dhacayaan server-yadeena gaar ah oo adeeg gaar ah. Qoraalka waxaa loo beddelaa vectors iyada oo aan ka bixin serverka, natiijooyinka u badanina waxay daraan dib u kala soocidda maxaliga ah si loo wanaajiyo saxnaanta.
Dib u qoridda su'aasha
Su'aasha muran ama dhammaystiran lahayn waxaa la hagaajiyaa ka hor inta aan raadinta la fulin. Isticmaalayaasha kama rabin inay weydiiyaan su'aasha "saxda ah"; nidaamku wuxuu ka dhigayaa su'aasha mid diyaar u ah raadinta.
Qoraalka ka yimid sawirrada, codadka iyo fiidiyowga
Soo-bixinta qoraalka ka yimid sawirrada iyo qoraalka codadka iyo fiidiyowga waxaa lagu fuliyaa qalab maxali ah oo ku yaal serverka, qoraalka natiijada ahna wuxuu galaa nadiifinta iyo marin-abuurka isku midka ah. Xogta kama baxo serverka.
What is on the roadmapPlanned
The following do not exist yet. They are planned and designed items; this page does not present them as if they were already built.
The single door: MCP / API gateway
A single gateway that external AI systems can query in natural language. An AI that connects once reaches every participating business through the same door.
Layerka oggolaanshaha iyo raali gelinta
Businesses join by their own choice; authentication, key management, rate limiting and abuse protection all live in this layer.
Layerka aragtida AI
Making content machine-discoverable via llms.txt, /.well-known/ and schema.org markup, plus registration in MCP registries. There is no magical auto-discovery; visibility is built this way.
WordPress plugin
A plugin that lets a WordPress site send its content to OpenRAG and get back an endpoint that AI systems can query.
We do not give dates for these items. When an item is finished it moves up into the "parts that work today" list, and this page is updated accordingly.
🔒 Data does not leave the server
OpenRAG's goal is to run every step of the RAG pipeline on our own server with local, free tools: embedding, reranking, text extraction from images and audio transcription. No media entering RAG is sent to an external service — this is a non-negotiable design rule.
The honest status: some of these steps are still performed by external services today. Moving them in-house is the first item on the roadmap.
How growth is planned
Vector search gets more expensive as content grows. OpenRAG's design limits that cost from the start in three ways.
There is no single giant index
Each business has its own small index and a query runs only against that index. Even as total content grows, the area a single query scans stays small; search cost scales with that one business's size, not with the platform's total.
Vector size and precision are adjustable
Using shorter vector dimensions and more compact number formats, the same content takes up markedly less space. These choices are built into the design from the start so that no expensive migration is needed later.
Cold tier
The index of a business that has not been queried for a long time is moved to cheap persistent storage and pulled back when a query arrives for it. That way only currently active content stays in fast memory. This tier is on the roadmap.
Frequently Asked Questions
What exactly is OpenRAG?
It is a RAG platform that cleans and structures a business's content, indexes it on our own server, and makes it queryable in natural language by external AI systems through a single permissioned door. It is not a chat tool; it is the knowledge layer that runs underneath such tools.
Do you hand my vectors or my content to anyone else?
No. The core principle is: vectors are not published, access is opened. What goes outside is not a copy of the content but the right to ask it questions; only the supporting passages come back with the answer. On top of that, the business decides which content becomes externally queryable.
What can actually be used today?
Database-ka vector iyo index, raadinta hibridka ah, ka go'aaminta dad badan, nadiifinta dukumentiyada iyo habaynta RAG, webka ka baaraandheega, quudinta RAG-ga dadweynaha ee qalabka AI-ga gaarka ah, iyo kaydinta faylalka/warbaahinta ayaa dhammaantood maanta shaqeeya. Qabow-qabow-qabow, dib u habaynta, dib u qoridda weydiinta, albaabka dibadda, lakabka oggolaanshaha, lakabka aragtida iyo plugin-ka WordPress weli ma jiro.
Ma ka bixi doonaa xogtay serverka?
Yoolka waa inuu dhammaan tillaabaha RAG pipeline-ka ay ku shaqeeyaan qalabka maxalliga ah ee serverka, iyada oo aan warbaahinta RAG-ga gelin mar walba loo dirin adeeg dibadda ah. Xaqiiqada dhabta ah: qaar ka mid ah tillaabahan weli waxaa maamula adeegyada dibadda maanta, iyo in la soo celiyo guri ayaa ah shayga ugu horeeya ee khariidadda waddada.
Goorma ayay dhammaystiri doonaan astaamaha khariidadda waddada?
Ma ballanqaadayno taariikhda. Taasina waa ujeedka saxda ah ee boggan: in si gaar ah loo muujiyo waxa maanta shaqeeya iyo waxa la qorsheeyay. Marka shay la dhammeeyo, wuxuu u guuraa liiska "qeybaha shaqeeya maanta".
Ma isticmaalaa ama ma iibiyaa maamulkayga tababar AI?
Maya. Ma jiro isticmaal noocaas ah maanta. Fikradda corpus-ka qoraalka oggolaanshaha waa shayga ugu fog, ee ugu culus sharciga ee khariidadda waddada; xitaa haddii ay dhacdo, wax qoraal ah lama isticmaali doono iyada oo aan oggolaansho cad ka helin ganacsiga.
Ku laabo portal AI ee qalabka AI-ga kale.
Su'aalo Badan La Weydiiyo
OpenRAG waa maxay?
OpenRAG waa nidaam RAG (Retrieval-Augmented Generation) oo shaqeeya server-ka gaarka ah ee xloji.com, iyo sidoo kale meel uun oo AI ah. Marka su'aal la weydiiyo, marka hore waxay raadisaa nuxurka khuseeya, ka dibna waxay abuureysaa jawaab iyada oo ku saleysan nuxurkaas. Iyada oo la joogo in ay sidoo kale u adeegto meel dhexe oo ay qalabka AI ee ka baxsan xloji.com kaga gaari karaan macluumaadka xloji.com iyada oo hal meel ah.
RAG macnaha sidee buu leeyahay, OpenRAGna sidee buu u fuliyaa?
RAG wuxuu ka soo gaabiyay 'Retrieval-Augmented Generation', taasi macnaheedu waa soo-celin iyo abuurid la xoojiyay; AI-gu wuxuu raadiyaa macluumaad ka mid ah ilaha khuseeya ka hor inta uusan jawaab soo saarin, ka dibna wuxuu u sameeyaa jawaabta iyada oo ku saleysan macluumaadkaas. OpenRAG wuxuu labadan tallaabo, raadinta iyo abuuridda, ku fuliyaa server-ka gaarka ah ee uu leeyahay. Sidaas darteed, jawaabaha OpenRAG bixiyo ma aha kuwo isku xiran, laakiin waxay ku saleysan yihiin nuxurka dhabta ah ee xloji.com.
'Meel uun oo AI ah' macnaheedu sidee buu u yahay?
Meel uun oo AI ah waxay ka dhigan tahay in dalabka AI iyo isku xirka kala duwan ay damaanad qaadaan hal meel dhexe halkii ay ka damaanad qaadi lahaayeen nidaamyada kala duwan. OpenRAG wuxuu qabtaa doorkan: labadaba astaamaha 'Weydii Su'aal' ee xloji.com iyo qalabka AI ee ka yimaada dibadda, waxay u adeegaan iyaga oo marayaa isla qaabka OpenRAG. Dhismahaan dhexe wuxuu suurtogelinayaa in taraafikada AI la maamulo iyada oo hal meel ah.
Waa maxay faa'iidada ka imaanaysa in OpenRAG shaqeeyo server-kaaga?
OpenRAG wuxuu shaqeeyaa server-ka gaarka ah ee xloji.com iyada oo aan ku tiirsaneyn adeeg daruur ah oo qof kale. Taas macnaheedu waa in xogta la raadiyo iyo xogta la shaqeeyo ay ku jiraan gacanta xloji.com. Iyada oo ah qaab shaqeeya server-kaaga, OpenRAG wuxuu fuliyaa raadinta iyo abuuridda jawaabta iyada oo aan xogta u dirin nidaamyada dibadda.
Yaa isticmaala OpenRAG?
OpenRAG waxaa isticmaala saddex koox oo kala duwan: isticmaalayaasha ugu dambaynta ee booqda xloji.com oo qora 'Su'aal Weydii' sanduuqa, nidaamyada weydiinaayaa kaabayaasha RAG ee xloji.com, iyo qalabka caqliga samaawiga ah ee dibadda ee helaya macluumaadka xloji.com iyada oo loo marayo OpenRAG. Isticmaalayaasha ugu dambaynta, OpenRAG wuxuu ku soo celinayaa jawaab ku salaysan nuxurka xloji.com. Qalabka dibadda, OpenRAG waa albaab aan macno lahayn oo loo isticmaalo xog ka soo qaadashada xloji.com.
Sidee sanduuqa 'Su'aal Weydii' ee xloji.com ula shaqeeyaa OpenRAG?
Su'aal qoran sanduuqa 'Su'aal Weydii' ee xloji.com waxaa dhisa OpenRAG. OpenRAG marka hore wuxuu raadiyaa nuxurka ku saabsan su'aasha xogta xloji.com, ka dibna wuxuu abuuraa jawaab ku salaysan nuxurkaas. Sidaas, jawaabta la siiyo isticmaalaha waxaa taageeraya nuxur dhab ah oo xloji.com ah.
Sidee qalabka caqliga samaawiga ah ee dibadda u helaa macluumaadka iyada oo loo marayo OpenRAG?
OpenRAG wuxuu u shaqeeyaa sidii albaab keliya oo ah oo u oggolaanaya qalabka caqliga samaawiga ah ee xloji.com ka baxsan in ay helaan macluumaadka xloji.com. Qalabkan ayaa ku xirmi kara OpenRAG si ay u helaan jawaabo madax bannaan oo la fahmi karo oo ka yimid nuxurka xloji.com. Sidaas darteed, macluumaadka la siiyo iyada oo loo marayo OpenRAG waxaa loo qorsheeyay inuu macno leeyahay iskiis ahaan, iyada oo aan loo baahnayn macno gaar ah.
Waa maxay xuduudaha OpenRAG?
Jawaabaha OpenRAG bixiyo waxaa lagu xaddidaa nuxurka la siiyay; OpenRAG ma soo saari karo jawaab sax ah oo ku saabsan macluumaad aan jirin ama aan lagu darin nidaamka. OpenRAG wuxuu beegsan yahay inuu ku xaddidaado nuxurka gacantiisa ku jira, halkii uu u abuuri lahaa macluumaad aan jirin. Sidaas darteed, waa in la xasuusnaadaa in jawaabta laga helo OpenRAG ay ku xaddidan tahay nuxurka xloji.com ay hadda haysato.
OpenRAG ma bot sheekhaysiin baa?
OpenRAG, maaha chatbot madaxbanaan si caadiga ah; waa RAG iyo kaabashada isku xirka ka shaqeysa ee 'Weydii Su'aal' ee xloji.com iyo helitaanka macluumaadka ee qalabka dibadda. Shaqada aasaasiga ah ee OpenRAG waa inay hesho nuxurka su'aasha ku habboon oo ay ku abuurto jawaab iyada oo ku saleysan nuxurkaas. Sidaas darteed, OpenRAG waxa ay u shaqeysaa sidii lakabka ka dambeeya jawaabaha, halkii ay ka ahayn interface si toos ah ula sheekeysta isticmaalayaasha.
Waa maxay ujeedka OpenRAG ee xloji.com?
Ujeedka OpenRAG waa inuu suurogeliyo in isticmaalayaasha dhamaadka iyo qalabka AI ee dibadda ay helaan macluumaadka xloji.com iyada oo loo marayo kaabasho la isku hallaynto oo ay maamulaan. Shaqeynta server-kaaga, waxay xaqiijineysaa in helitaankan uu dhaco iyada oo aan loo tiirsaneyn nidaamyada saddexaad. Iyada oo la adeegsanayo qaabka isku xirka hal albaab, OpenRAG waxay ku midoobisaa meelaha kala duwan ee helitaanka nidaam hal dhexe.
Macluumaad faahfaahsan oo ku saabsan OpenRAG
OpenRAG, xloji.com serverkeeda shaqeeya nidaam RAG (Retrieval-Augmented Generation) ah ahna, sidoo kale waa albaabka AI oo u mariya codsanada la xidhiidha AI hal meel. Magaceeda ku jirta 'Open' waxay tilmaameysaa in nidaamku yahay mid furan oo la heli karo, 'RAG'na waxay tilmaameysaa habka ay u shaqeyso, oo ah in marka hore la helo xogta khuseysa markii jawaab la soo saarayo, ka dibna jawaabta la abuuro iyadoo la saleynayo xogtan. Su'aal lagu qoro sanduuqa 'Su'aal Weydii' ee xloji.com marka hore waxaa OpenRAG ka raadiyaa waxyaabaha khuseeya, ka dibna jawaab ayaa la soo saaraa iyadoo la saleynayo waxyaabaha la helay. Isku midkaani wuxuu sidoo kale u oggol yahay qalabka AI ee ka baxsan xloji.com inuu helo xogta xloji.com iyada oo maraya OpenRAG, isla markaana uu isticmaalo xogtan jawaabtiisa. Dhismahaan wuxuu suurtogelinayaa in xloji.com bixiyo adeeg iyada oo hal nidaam dhexe ah u adeegaysa, halkii ay ka sameyn lahayd xulufada AI gaar ah oo kala duwan oo loogu talagalay alaabadeeda kala duwan.
Fikrada aasaasiga ah ee qaabka RAG waa in nidaamka AI aanu ku tiirsanayn oo kaliya xogta guud ee hore loo tababaray, laakiin marka hore wuxuu ka soo qaadaa xogta cusub ee saxda ah ee la xidhiidha su'aasha ilaha, ka dibna wuxuu ku jawaabaa xogtan. OpenRAG wuxuu shaqeeyaa iyada oo isku dari doonaa labadan tallaabo, oo ah helidda (retrieval) iyo soo saaridda (generation), serverkeeda. Habkaan waxaa loola jeedaa in la yareeyo miyirka qaabka AI ee soo saarista xog aan jirin; sababtoo ah jawaabtu ma ka timid xusuusta qaabka, laakiin waxay ka timid waxyaabaha dhabta ah ee la helay. Sidaas darteed, jawaabaha OpenRAG bixiyo ma aha kuwo random ah ama xog ku dhacay, laakiin waxay ku salaysan yihiin xogta xloji.com. Sidaas darteed, ilaha jawaabta uu soo saaro OpenRAG ayaa weli la raaco iyada oo ah xogta xloji.com. Xaqiiqada ah in serverku leeyahay xloji.com waxay ka dhigan tahay in xogta la raadiyo iyo la shaqeeyo lagu hayo gacanta xloji.com iyada oo aan ku tiirsaneyn adeeg daruur ah oo saddexaad.
Dhanka 'albaabka AI-ga hal-dhigga' ee OpenRAG, waxay ka dhigan tahay in codsanada AI iyo isku xirka kala duwan loo qoondeeyo hal meel dhexe halkii ay ka marayaan nidaamyada kala duwan. Sidaas darteed, labadaba muuqaalka 'Su'aal Weydii' ee xloji.com iyo qalabka dibadda oo ku xidhan OpenRAG waxay isticmaalaan isku midkaani nidaam iyo isla fikrada aasaasiga ah. Iyada oo ah dhismay albaab ah, OpenRAG wuxuu hubiyaa in dhammaan isku xidhka AI u maro hal meel; taasna waxay kor u qaadaa isku midnimada jawaabaha iyo xakameynta xogta iyada oo ah nidaam ka shaqeeya serverkeeda. Habkaan hal-meel ah wuxuu sidoo kale suurtogelinayaa in dayactirka iyo cusbooneysiinta lagu sameeyo hal meel halkii ay ka kala jaraan nidaamyada kala duwan. Dhankaas, OpenRAG maaha kaliya qalab su'aal-jawaab, laakiin waa lakab nidaam ah oo isku xidha dhammaan meelaha xloji.com ay ku heli karto AI.
OpenRAG waxaa si toos ah ama si dadban u isticmaala saddex koox oo isticmaale ah: isticmaalayaasha dhamaadka ee booqda xloji.com oo qora su'aalaha sanduuqa 'Su'aal Weydii', nidaamyada ka raadiya nidaamka RAG ee xloji.com, iyo qalabka AI dibadda ah ee helaya xogta xloji.com iyada oo maraya OpenRAG. Saddexdan kooxood oo isticmaale ah waxay ka helaan jawaabo ka yimid isla nidaamka OpenRAG, isla xogta. Sidaas darteed, haddii la weydiiyo xog ku saabsan xloji.com meel kasta, waxaad heli doontaa ilo isku mid ah. Jawaabaha OpenRAG bixiyo waxay xaddidan yihiin xogta la siiyay; taasi waa, ha ka filan jawaab sax ah OpenRAG haddii xogta aanay jirin nidaamka ama aan lagu darin serverkeeda. Xaddidaaddani waxay sidoo kale tahay aasaaska kalsoonida OpenRAG: waxay ku dadaashaa soo saarista jawaabo xaddidan oo ku salaysan xogta ay haysato, halkii ay ka sameyn lahayd xog aan jirin.