Update README.md

README.md

@@ -18,8 +18,9 @@ fine-tuned using **Unsloth** on an expanded dataset of financial questions and a
 quantized and augmented with a 4bit QLoRa. \
 \
 Prompt analysis and model registry is handled by **Comet LLM**, and finance news is streamed via **Bytewax** using an \
-**Alpaca API**, and then sent as a vector embedding to **Qdrant**'s serverless vector store. **LangChain** chains the prompt and \
-most relevant news article with real-time finance information, **contextualizing the output**. \
+**Alpaca API**, then parsed, cleaned, and chunked with **unstructured**, and finally sent as a vector embedding to \
+**Qdrant**'s serverless vector store. **LangChain** chains the prompt and most relevant news article with real-time \
+finance information, **contextualizing the output**. \
 \
 **#TODO:** Add citations to output to show end-user which article has been used to generate the output.