new version release

Author: torrmal

README.md

@@ -12,7 +12,7 @@ pip install flat-ai
 
 Best and fastest way, is to get your teeth to it:
 
-[Tutorial Jupyter Notebook](/tutorial.ipynb)
+[Tutorial Jupyter Notebook](https://colab.research.google.com/drive/1dK5bzsFy1BtwhQgw9cFmRtqrcJyNeSi4?usp=sharing)
 
 # Features
 
@@ -184,8 +184,7 @@ for chunk in llm.get_stream('what is the subject of the email?', email=email):
 
 ## OpenAI API based
 
-As you are just about to see, this tiny library is designed to talk to LLMs that are served through an OpenAI API compatible endpoint (as they all should). 
-But, scare yourself not when you read the words OpenAI. Because, you will still be able to play with all kinds of models and providers - OpenAI or not - using the same API ([Ollama](https://ollama.com/blog/openai-compatibility) as seen below, [Groq](https://console.groq.com/docs/openai), etc). Because, Most of them have OpenAI API compatible endpoints.
+This library uses the OpenAI API format, which means it works with OpenAI and any other model and providers like Ollama, TogetherAI, Groq, etc that support the same API format. So you can use any model from any provider that has OpenAI-compatible endpoints.
 
 ```python
 import openai

flat_ai/__about__.py

@@ -1,6 +1,6 @@
 __title__ = 'flat-ai'
 __package_name__ = 'flat_ai'
-__version__ = '0.1.0'
+__version__ = '0.2.0'
 __description__ = 'F.L.A.T. (Frameworkless LLM Agent Thing) for building AI Agents'
 __email__ = 'hello@mindsdb.com'
 __author__ = 'Yours truly Jorge Torres and an LLM'

tutorial.ipynb

@@ -46,15 +46,15 @@
     "from flat_ai import FlatAI, configure_logging\n",
     "from typing import List\n",
     "from pydantic import BaseModel\n",
-    "#configure_logging('trace.logs') -- enable this and you can to tail -f trace.logs, and see everything happening with the llm calls\n",
+    "#configure_logging('trace.logs') # -- enable this and you can to tail -f trace.logs, and see everything happening with the llm calls\n",
     "\n",
     "# Create client - we're using Together.ai, but feel free to use your favorite LLM provider\n",
     "client = openai.OpenAI(\n",
     "    api_key=<YOUR API KEY>,  \n",
     "    base_url = 'https://api.together.xyz/v1' # you can comment this if you are using OpenAI directly\n",
     ")\n",
     "\n",
-    "# we will be using a llama3.1 model here\n",
+    "# we will be using a llama3.1 model here, \n",
     "llm = FlatAI(client=client, model='meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo')\n",
     "\n",
     "\n",