Automating Movie Q&A on X with Hybrid RAG + Fine-Tuned LLMs
Built a production-ready X (Twitter) bot that answers movie
"Shipped a modular X bot that reliably replies to mentions with"
Backend
AI Models
Infrastructure
$4,500/mo avoided
Avoided real-time streaming API costs
Chose periodic mention polling + queueing instead of X Streaming API
15k
Monthly X API usage ceiling validated
Client reported dashboard usage (e.g., 168/15k), used to tune polling
3 AI modes
Inference strategies available without rewrites
AI_ENV_TYPE routes between localRAG (Ollama), hosted RAG (HF/Qdrant),
1 repo integration
Reduced handoff friction
Integrated working bot + AI modules into client’s FastAPI repo
The Challenge
Problem Statement
The client needed a bot similar to interactive reply bots (e.g.,
The Solution
Our Approach
Engineered a Python/FastAPI-based bot + AI services architecture with
AI Implementation
Hybrid AI Runtime (RAG + Fine-Tuned + Web Search toggle)
Technical Details
Implemented retrieval-augmented generation using Qdrant
Business Value
Enabled the client to demo and iterate quickly with multiple AI
Technical Deep Dives
Challenges We Solved
X API permissions, rate limits, and non-streaming architecture
The bot needed to respond to mentions, but streaming access was
Implemented periodic mention polling with robust rate-limit handling,
X APIPythonFastAPI
RAG ingestion reliability with change management
Client required vector DB reset/reinsert behavior and later asked for
Built a dedicated ingestion script and ingestion API endpoint
QdrantDockerPythonFastAPI
Modular refactor into production FastAPI framework
Initial implementation needed to be merged into a pre-existing FastAPI
Refactored codebase to move AI services out of twitter_bot into a
FastAPIAPIRouterPythonGitHub
Fine-tune deployment to Hugging Face + endpoint publishing
Client required a fine-tuned model that could be served via URL; access
Delivered a working Colab fine-tuning notebook, published fine-tuned
Google ColabHugging Face HubHugging Face Inference EndpointsTransformers
Process
Project Timeline
1
Discovery
Aligned on a bot that monitors X mentions and replies with movie
2
Build
Delivered RAG API and ingestion pipeline (CSV → embeddings → Qdrant).
3
Launch
Integrated the bot into the client’s production repo, validated
Project Gallery
Screenshots & Visuals
service
Preview
solution
Ready to Build Something Similar?
Let's discuss how we can help transform your business with AI.
Start Your Project
