Improved .env examples

env_examples/.env.huggingface.example

@@ -15,6 +15,14 @@ LLM_URL=https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-70B-
 LLM_TYPE=HF_API
 LLM_NAME=Meta-Llama-3-70B-Instruct
 
+# If you want to use any other model serving provider the configuration will be similar
+# Below is the example for Groq
+# GROQ_API_KEY=gsk_YOUR_GROQ_API_KEY
+# LLM_URL=https://api.groq.com/openai/v1
+# LLM_TYPE=GROQ_API
+# LLM_NAME=llama3-70b-8192
+
+
 # The Open AI whisper family with more models is available on HuggingFace:
 # https://huggingface.co/collections/openai/whisper-release-6501bba2cf999715fd953013
 # You can also use any other compatible STT model from HuggingFace

env_examples/.env.local.example

@@ -1,5 +1,5 @@
-# You can also run models locally or on you own server and use them instead if they are compatible with HuggingFace API
-# For local models seletct HF_API as a type because they usse HuggingFace API
+# You can run models locally or on you own server and use them instead if they are compatible with HuggingFace API
+# For local models seletct HF_API as a type because they use HuggingFace API
 
 # Most probalby you don't need a key for your local model
 # But if you have some kind of authentication compatible with HuggingFace API you can use it here
@@ -8,21 +8,35 @@ HF_API_KEY=None
 # The main usecase for the local models in locally running LLMs
 # You can serve any model using Text Generation Inference from HuggingFace
 # https://github.com/huggingface/text-generation-inference
-# This project uses Messages API that is compatible with Open AI API and allows you to just plug and play OS models
-# Don't gorget to add '/v1' to the end of the URL
+# It uses Messages API that is compatible with Open AI API and allows you to just plug and play OS models
+# Don't forget to add '/v1' to the end of the URL
 # Assuming you have Meta-Llama-3-8B-Instruct model running on your local server, your configuration will look like this
 LLM_URL=http://192.168.1.1:8080/v1
 LLM_TYPE=HF_API
 LLM_NAME=Meta-Llama-3-8B-Instruct
 
+# Another polula alternative is ollama https://ollama.com/ it supports the same API and the usage is identical
+# OLLAMA_API_KEY=ollama # you don't really need it
+# LLM_URL=http://192.168.1.128:11434/v1
+# LLM_TYPE=OLLAMA_API
+# LLM_NAME=llama3
+
 # Running STT model locally is not straightforward
-# But for example you can one of the whispers models on your laptop
+# But for example you can run one of the whispers models on your laptop
 # It requires some simple wrapper over the model to make it compatible with HuggingFace API. Maybe I will share some in the future
 # But assuming you manages to run a local whisper-server, your configuration will look like this
 STT_URL=http://127.0.0.1:5000/transcribe
 STT_TYPE=HF_API
 STT_NAME=whisper-base.en
 
+# You can also run TTS models locally without API
+# It will use transformers library to run the model
+# I would not recommend doing it on the machine without GPU, it will be too slow
+# STT_URL=None
+# STT_TYPE=HF_LOCAL
+# STT_NAME=openai/whisper-base.en
+
+
 # I don't see much value in running TTS models locally given the quality of online models
 # But if you have some kind of TTS model running on your local server you can use it here
 TTS_URL=http://127.0.0.1:5001/read

env_examples/.env.openai.example

@@ -4,11 +4,12 @@
 # Set up you key here: https://platform.openai.com/api-keys
 OPENAI_API_KEY=sk-YOUR_OPENAI_API_KEY
 
-# "gpt-3.5-turbo" - ~3 seconds delay with good quality, recommended model
-# "gpt-4-turbo","gpt-4", etc. 10+ seconds delay but higher quality of responses
+# "gpt-4o-mini" - the fastest and cheapest model
+# "gpt-4o" - good balance between speed and quality
+# "gpt-4-turbo","gpt-4", "gpt-3.5-turbo" older models with differetn pros and cons
 LLM_URL=https://api.openai.com/v1
 LLM_TYPE=OPENAI_API
-LLM_NAME=gpt-3.5-turbo
+LLM_NAME=gpt-4o-mini
 
 # "whisper-1" is the only OpenAI STT model available with OpenAI API
 STT_URL=https://api.openai.com/v1