🧹 Minor changes

README.md

@@ -4,6 +4,18 @@
 
 🤖 Megabots provides State-of-the-art, production ready bots made mega-easy, so you don't have to build them from scratch 🤯 Create a bot, now 🫵
 
+The Megabots library can be used to create bots that:
+
+- ⌚️ are production ready bots in minutes
+- 🗂️ can answer questions over documents
+- 🧑‍⚕️ can act personal assistants and use agents and tools (Coming soon)
+- 🗣️ can accept voice (Coming soon)
+- 👍 validate and correct the outputs of large language models (Coming soon)
+- 💰 semanticly cache LLM Queries and reduce your LLM API Costs by 10x (Coming soon)
+- 🏋️ are mega-easily to train (Coming soon)
+
+🤖 Megabots is backed by some of the most famous tools for productionalising AI. It uses [LangChain](https://docs.langchain.com/docs/) for managing LLM chains, [FastAPI](https://fastapi.tiangolo.com/) to create a production ready API, [Gradio](https://gradio.app/) to create a UI. At the moment it uses [OpenAI](https://openai.com/) to generate answers, but we plan to support other LLMs in the future.
+
 Note: This is a work in progress. The API might change.
 
 ```bash
@@ -52,20 +64,6 @@ from megabots import bot, create_interface
 demo = create_interface(QnABot("qna-over-docs"))
 ```
 
-### Features
-
-- [x] Create a question answering bot over your documents with one line of code using GPT
-- [x] Save / load index to reduce costs (Open AI embedings are used to create the index)
-- [x] Local data source (directory of documents) or S3 data source
-- [x] FAISS for storing vectors / index
-- [x] Expose bot over API using FastAPI
-- [x] Gradio UI
-- [ ] Integration with [guardrails](https://github.com/ShreyaR/guardrails)
-- [ ] Integration with [GPTCache](https://github.com/zilliztech/GPTCache)
-- [ ] Support for other vector databases (e.g. Weaviate, Pinecone)
-- [ ] Customise prompt
-- [ ] Support for LLaMA model
-
 ### Here's how it works
 
 Large language models (LLMs) are powerful, but they can't answer questions about documents they haven't seen. If you want to use an LLM to answer questions about documents it was not trained on, you have to give it information about those documents. To solve this, we use "retrieval augmented generation."