Merge pull request #11 from lpm0073/next

documentation cleanup

Author: lpm0073

README.md

@@ -1,6 +1,13 @@
-# Netec Large Language Models
+# Hybrid Search Retriever
 
-A Python [LangChain](https://www.langchain.com/) - [Pinecone](https://docs.pinecone.io/docs/python-client) proof of concept Retrieval Augmented Generation (RAG) models using sales support PDF documents.
+A Python [OpenAI](https://openai.com/) / [LangChain](https://www.langchain.com/) / [Pinecone](https://docs.pinecone.io/docs/python-client) proof of concept Retrieval Augmented Generation (RAG) model using PDF documents as the embeddings data source.
+
+Implements the following:
+
+- a command-line pdf loader program that extracts text, vectorizes, and
+  loads into a Pinecone dot product vector database that is dimensioned to match OpenAI embeddings.
+
+- a hybrid search retriever that locates relevant documents from the vector database and includes these in OpenAI prompts.
 
 See:
 

models/hybrid_search_retreiver.py

@@ -1,7 +1,16 @@
 # -*- coding: utf-8 -*-
 # pylint: disable=too-few-public-methods
 """
-Sales Support Model (SSM) for the LangChain project.
+Hybrid Search Retriever. A class that combines the following:
+    - OpenAI prompting and ChatModel
+    - PromptingWrapper
+    - Vector embedding with Pinecone
+    - Hybrid Retriever to combine vector embeddings with text search
+
+Provides a pdf loader program that extracts text, vectorizes, and
+loads into a Pinecone dot product vector database that is dimensioned
+to match OpenAI embeddings.
+
 See: https://python.langchain.com/docs/modules/model_io/llms/llm_caching
      https://python.langchain.com/docs/modules/data_connection/document_loaders/pdf
      https://python.langchain.com/docs/integrations/retrievers/pinecone_hybrid_search