Research notes and resources

PostGres vector db:

• how to work with the database: https://zhimin-wen.medium.com/retrieval-augmented-generation-with-postgres-vector-db-and-llamaindex-8eceae9091f5
• how to install the vector db to docker: https://medium.com/@johannes.ocean/setting-up-a-postgres-database-with-the-pgvector-extension-10ab7ff212cc

Using LLama index python lib https://docs.llamaindex.ai/en/stable/examples/finetuning/embeddings/finetune_embedding/#generate-corpus from llama_index.core.node_parser import SentenceSplitter

Running llm at docker cpu https://github.com/saul-leon/llama-2-7b-q4-gguf-docker-cpu https://medium.com/@penkow/how-to-run-llama-2-locally-on-cpu-docker-image-731eae6398d1 https://medium.com/@ahmedtm/a-simple-guide-to-run-the-llama-model-in-a-docker-container-a3899032995e

Autonomus https://github.com/crewAIInc/crewAI

LangChain Document loading, https://python.langchain.com/v0.1/docs/modules/data_connection/document_loaders/file_directory/