[x] RAG with a Postgres Vector Store and Open-Source Models
[x] similarity-based approach with embeddings
[x] based on machine learning models.
[x] Similarity search with verctor db
[x] PostgresML with Django and embedding search
User Experience
[ ] Brief assessment
[ ] Personalized match with a licensed therapist
[ ] Start messaging your therapist
Built a RAG pipeline
get data into an LLM, and a component of more sophisticated agentic systems.
Loading & Ingestion
Indexing and Embedding
Storing in a specialized database known as a Vector Store
Querying: Every indexing strategy has a corresponding querying strategy, LLM improve the relevance, speed and accuracy of what you retrieve before returning it to you.
Turning it into structured responses such as an API.
User Experience
Built a RAG pipeline
Loading & Ingestion
Indexing and Embedding
Storing in a specialized database known as a Vector Store
Querying: Every indexing strategy has a corresponding querying strategy, LLM improve the relevance, speed and accuracy of what you retrieve before returning it to you.
Turning it into structured responses such as an API.