.HAHNN
.HAHNN
All work
Case 02 / 04·Open source · Docker Compose ready

AI Document Assistant · Go

DOCENTRA.

AI-powered document assistant with semantic search using Go, pgvector, and fastembed for intelligent retrieval across private document libraries.

AI EngineerBackendFull-Stack

Auth

JWT

Search

pgvector similarity

Formats

TXT / PDF

Runtime

Docker Compose

Interactive lens

PROBLEM → SOLUTION

Drag the handle right to reveal the solution over the problem.

← ProblemSolution →

Problem

Teams need meaning-based search over private TXT/PDF libraries without shipping documents into a third-party black box. Keyword search misses intent; managed RAG often means data leaving your boundary.

Solution

Docentra is a secure Go API for JWT-authenticated document upload, parsing, background embedding, and semantic search/query over Postgres with pgvector. A Python FastEmbed CLI produces embeddings; Docker Compose runs the full stack locally.

Drag right to reveal the solution · 12%

01Result

JWT-authenticated APIs for document management and vector search

02Result

Upload → extract → chunk → embed → store pipeline for TXT/PDF

03Result

Similarity search via pgvector without outsourcing the corpus

Execution flow

HOW IT RUNS

End-to-end flow from trigger to decision output.

  1. 01

    Step 1 of 5

    Client hits Go API (Chi + GORM)

  2. 02

    Step 2 of 5

    API stores uploads and document metadata in Postgres

  3. 03

    Step 3 of 5

    Background processing extracts text, chunks it, and calls FastEmbed CLI

  4. 04

    Step 4 of 5

    Chunk embeddings land in document_chunks via pgvector

  5. 05

    Step 5 of 5

    Output

    Search/query embeds the question and runs similarity (`<=>`)

Capabilities

WHAT IT CATCHES

Signal 01

POST /api/documents uploads a file and triggers async processing

Signal 02

Python FastEmbed CLI with model BAAI/bge-small-en-v1.5

Signal 03

POST /api/search and POST /api/query embed the query and rank chunks

Signal 04

Health endpoint and Compose-first local development

Pin a layer

STACK MATRIX

Click a layer to isolate it — Open Source · Go · pgvector · Docker

Live signal

CORE LOGIC

docentra.corestreaming…
1 

Docentra is a private-document semantic search stack: Go for auth and orchestration, FastEmbed for vectors, and Postgres/pgvector for retrieval. Built for RAG-style workflows where the library stays under your control.

[ VERIFY ]

Open the
source.

Claims should survive a read of the repo.

BRIEF0%Source