The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
I built IAnversic RAG, a privacy-focused knowledge retrieval system that enables organizations to search internal documents and obtain AI-generated answers grounded in verifiable sources.
The project delivers a full-stack RAG application built with FastAPI, PostgreSQL, pgvector, Ollama, and Next.js. It combines hybrid semantic and full-text search, optional reranking, source citations, and database-level permission filtering to support secure, context-aware retrieval.
Concrete results:
Implemented an end-to-end document ingestion and retrieval pipeline with source-grounded answers and citations.
Integrated PostgreSQL full-text search and vector similarity search using pgvector and HNSW indexing.
Implemented organization-level data isolation, role-based access controls, and API key management.
Enabled configurable local LLMs and embedding models, supporting self-hosted deployments and greater control over sensitive data.
Packaged the application into Docker services for the database, migrations, API, background worker, model runtime, and web interface.
The result is a modular, self-hostable RAG platform designed to help businesses make internal knowledge more accessible while maintaining control over their data and infrastructure.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Ported my own Python trading bot into an MQL5 Expert Advisor for MetaTrader 5 ⚙️
It runs two switchable strategies, BBMA and an MA crossover, and only checks signals on closed candles. It also has duplicate-order protection. Backtested on XAUUSD M15 over 12 months.
Need your trading rules turned into an EA? Send me a message.
#MQL5 #MetaTrader5 #AlgoTrading #ExpertAdvisor #Forex
Clean engineering choices here — signaling only on closed candles and adding duplicate-order protection are exactly the two things that quietly wreck live bots when people skip them.
One thing I’d be curious about: on a single 12-month XAUUSD backtest, did you model spread and...
I built TANDem Studio to make project management easier for freelancers and small teams. It brings projects, tasks, deadlines, time tracking, and client work together in one place, so everything feels more organized.
The idea came from a simple thought: we spend so much time managing work that we sometimes forget to focus on the work itself.
With TANDem Studio, I want to reduce the busywork and give people more time to create, collaborate, and build better client relationships.
TANDem Studio — More time for the work that matters.
It started with a simple request. A client told us their team was still typing invoices into a spreadsheet by hand, one by one, and asked if there was a better way.
At DZ Labs we like that kind of problem: small, real, and something people deal with every single day. So I built Invoice Register.
You give it a PDF invoice, and a few seconds later the data is sitting in a Google Sheet: supplier, dates, totals, and every line item in its own row. It works with digital invoices and with scanned ones too.
In the video you can see the whole trip: I upload a PDF, the API answers with the structured data, the rows show up in the spreadsheet, and the service is running live in the cloud.
Here is what I used to build it:
Python 3.12 and uv to manage the project and its dependencies
FastAPI and Uvicorn for the API
Pydantic to define and validate what an invoice looks like
pdfplumber to read text from digital PDFs
pdf2image, Poppler and Tesseract to read scanned invoices with OCR
LangChain and Claude to turn raw text into structured data
gspread and google-auth to write into Google Sheets
LangSmith to trace every run and see what the model did
pytest for the test suite And here is what I used to deploy it:
Docker to package the app with its system dependencies
Cloud Build and Artifact Registry to build and store the image
Google Cloud Run to run it, scaling down to zero when nobody is using it
Secret Manager to keep the API keys out of the code I will be honest: writing the code was the comfortable part. Getting it to production is where I learned the most. When the data belongs to someone else, security stops being optional. The service runs without any key files, the API is private, and every secret lives outside the code. What I enjoyed most was not the technology. It was knowing that someone will get back hours of their week. Next steps: a simple frontend for uploads, background processing, and automated deployments. If your team is still doing something by hand that a computer should be doing, I would love to hear about it.
#Python #FastAPI #LangChain #GoogleCloud #CloudRun #AI #DZLabs
Since you're tracing runs in LangSmith, I'd separate debugging metadata from invoice contents. Can you follow a failed extraction using a document ID and error details without recording supplier or line-item data in the trace?