758 collectifs
TT Collective
A propos
Accompagnement sur-mesure de vos projets SEO & Social Ads
Copilots
A propos
Une équipe de copilotes qui donne vie à vos idées d’app mobile.
Infra Crew
A propos
Clean & functional clouds.
Jane
A propos
Votre SaaS clé en main, de l'idée au go-to-market
Nine-Nine
A propos
Enquêtez pour innover, comprenez pour exceller
Product, Design & Impact
A propos
Ex-Shine, Indy, Betagouv, HelloWork et Spacefill, nous créons des solutions modernes à vos problématiques.
FMCG & cie
A propos
Nous construisons des stratégies marketing & commerciales adaptées aux problématiques et structure de l'industrie FMCG
socraft
A propos
Communauté d'artisans alliant technologie et méthodologie pour soutenir vos initiatives !
Undefined
A propos
Spécialiste de la création de sites sur mesure.
DONOMA
A propos
Agence éthique & créative
Julia Creative Studio
A propos
Sublimez votre marque avec impact
Agence Dentifrice
A propos
Dynamiser et rafraîchir votre présence en ligne
SASWAVE
A propos
Transform ideas in products
Les experts CTO / CPO
A propos
complémentarité technique et produit, et développement
Inexplo
A propos
L’expertise d’un cabinet d’innovation numérique externalisée et responsable 🤝
Kadabra Studio
A propos
Kadabra Studio est un collectif d’experts Figma, Bubble et Webflow. Nous concevons et développons vos solutions digitales en intégrant l’IA 🪄
FineStack.io
A propos
Empowering Your Vision with Passionate Innovation. finestack.io
Sypher
A propos
Turn your data into actions to activate x2 qualified leads
![LOT Systems logo](https://cdn.collective.work/clrp6vq560b315ci476rl9ao7.png)
LOT Systems
•Mode & Textile•Cosmétique•Santé, Pharmaceutique & Biotech•Petite entreprise
LLM RAG on GCP for a product subscription service
Development & deployment of LLM RAG system
Issue: The client is operating an interface for a physical product subscription service, with a user base distributed around the globe. They wanted to implement a journaling feature to the interface, which based on the users answers creates a digital clone in the backend.
Solution: The system was build with python, LangChain, chroma (vector db) and the openai API. It was deployed on multi-regional Cloud Functions and Cloud Run services on Google Cloud Platform (GCP). A dedicated service API was designed and used to integrate with legacy backend services as well as their Vue.js frontend. We also developed the Vue.js integration of the API.
The functionality of the service consisted of features such as:
user journal upload and vectorisation
user behavioural model creation
integration of ambient data like location, time, temperature, weather, etc
inference based on user model, journal entry, ambient data, for user interaction design (in the form of question asked to the users with the goal to build more precise user models related to their product preferences and subscriptions)
Duration: Two months.
Impact: The client was able to launch a cutting edge LLM RAG system with custom functionality and roll-out to their users.
Membres
Expertises
De
Oct. 2023 à Nov. 2023