learn_textLABSCO SUMMARY
Nothing leaves the machine it runs on.
Your documents, the index and the model that answers from them all sit locally, which is a different trade from any hosted retrieval connector — and the reason to pick this one. You pay for it up front, in an Ollama install and a model download before the first question returns anything.
What it is
A local retrieval store an assistant can both add to and read from. Documents are parsed with Unstructured so titles, lists and tables survive instead of being flattened into a wall of text, with fallback strategies underneath so an awkward file still gets in. Generation runs through a model you serve locally with Ollama and embeddings are computed on your machine, so once the models are pulled nothing leaves it.
What you get
- Facts, definitions and notes stored under a source name you choose, so they can be asked about sessions later
- File ingestion across PDF, Word, PowerPoint, Excel, OpenDocument, HTML, XML, Markdown, plain text, CSV, JSON, YAML, email, and images through OCR
- Answers that come back with the sources they were drawn from and how relevant each one was
- Filtered search that narrows by file type or by structure — only documents containing tables, or at least so many titles
- A report of what the knowledge base currently holds, broken down by file type, structure and how each document was processed
- A desktop application for bulk-ingesting a folder, with a preview-and-select step before anything is written to the store
- A Markdown copy of every processed document, kept on disk for checking what was actually indexed
Requirements
Python 3.10 or newer, and Ollama installed and running with a language model pulled before the first question will work — that is the step the system genuinely depends on, not an optional extra. Tesseract is needed only for reading text out of images. The project is built around Windows: installation, launch and diagnostics are .bat scripts and the documented client entry points at one of them, so on macOS or Linux you are running the Python underneath by hand. Its documentation is in Spanish. The vector store and the converted document copies live in folders inside the project.
Setup effort
Build from source — get the source, then follow the project's own run instructions
USE CASES
01
Giving an assistant memory that survives the session
Hand it a fact, a definition or a decision from a conversation under a source name, and it is there to be asked about in a week's time.
02
Asking questions of a folder of documents
Point it at a report, a contract or a scanned page and it is parsed with structure preserved, then answered from with the source attributed back to you.
03
Searching only the documents that hold the numbers
Filter a query by file type or by structure — only PDFs, or only documents containing at least one table — when a plain similarity search keeps returning the prose instead of the data.
04
Checking what is actually in the knowledge base
Before trusting an answer, see how many documents are stored, what types they are, and how many tables and titles came through the ingest.
5 tools
Listed in project docs. Your client may show a different list.
learn_documentask_ragask_rag_filteredget_knowledge_base_statsBEFORE YOU INSTALL
What to know first
Tools you get
5 tools named in the project's documentation.
Requires
- Python 3.10+
- Ollama installed and running, with a model pulled — this server has no cloud fallback
- Tesseract, for the document formats that need OCR
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
start.batMCP Clients
Cursor
CURSOR · JSON
{
"mcpServers": {
"rag": {
"command": "D:\\ruta\\completa\\a\\tu\\proyecto\\MCP_RAG\\mcp_server_organized\\run_server_organized.bat",
"args": [],
"workingDirectory": "D:\\ruta\\completa\\a\\tu\\proyecto\\MCP_RAG"
}
}
}
