Sobre este projeto
it-programming / artificial-intelligence-1
Aberto
We are looking for a Python developer with strong experience in LangChain and vector databases to build an AI Retriever Chain with contextual prompting.
🎯 Goal:
Create a modular chain using LangChain and Qdrant to retrieve relevant context from a local or remote vector store and inject it into prompt templates for downstream models (e.g., OpenAI, DeepSeek).
📌 Core Tasks:
Setup Qdrant (local or remote) in Docker
Index and persist sample documents (we will provide .txt/.md files)
Build retriever logic with filters based on metadata
Integrate with LangChain chains for RAG (Retrieval-Augmented Generation)
Use prompt templates with injected context and fallback chaining
🧪 Testing & Evaluation:
Ensure vector queries return relevant chunks
Validate prompt composition and chaining
Must support multiple llm backends (via api) – we provide details
📦 deliverables:
dockerized solution (langchain + qdrant)
clean python code with comments
github repo delivery only
readme with clear setup & usage steps
💡 bonus if you can add basic cli tool to test queries.
💵 Budget: $200–278 USD, fixed
⏱️ Payment only after full working solution is delivered and verified.
Do not apply if partial/milestone payment is expected.
We are only looking for results-driven developers who can deliver clean, testable code and respect the delivery terms.
Categoria TI e Programação
Subcategoria Inteligência Artificial
Tamanho do projeto Grande
Prazo de Entrega: Não estabelecido
Habilidades necessárias