Skip to content

Latest commit

 

History

History
79 lines (59 loc) · 2.5 KB

.env.md

File metadata and controls

79 lines (59 loc) · 2.5 KB
Raw

The .env file is used to store environment variables for the backend server. it contains two sections: Text Processing Configuration and Image Processing Configuration:

Text Processing Configuration

These variables are used for document (text) processing:

  • TEXT_API_END_POINT: Specifies the API endpoint for text processing.
  • TEXT_MODEL_NAME: Defines the model to be used for text processing.
  • TEXT_API_KEYS: A list containing the API key(s) required for authentication when making requests to the text API endpoint. Using multiple keys will help in avoiding rate limits.

Image Processing Configuration

These variables are used for image processing:

  • IMAGE_API_END_POINT: Specifies the API endpoint for image processing.
  • IMAGE_MODEL_NAME: Defines the model used for image processing.
  • IMAGE_API_KEYS: A list containing the API key(s) for image processing requests. Using multiple keys will help in avoiding rate limits.

Examples:

  • GROQ (Recommended for text processing)

Get your free api key from here: https://console.groq.com/keys

# API and MODEL used for documents processing
TEXT_API_END_POINT=https://api.groq.com/openai/v1
TEXT_MODEL_NAME=llama3-70b-8192
TEXT_API_KEYS=["gsk_xxx","gsk_yyy"]

# API and MODEL used for images processing
IMAGE_API_END_POINT=https://api.groq.com/openai/v1
IMAGE_MODEL_NAME=llava-v1.5-7b-4096-preview
IMAGE_API_KEYS=["gsk_xxx","gsk_yyy"]
  • OPENAI
# API and MODEL used for documents processing
TTEXT_API_END_POINT=https://api.openai.com/v1
TTEXT_MODEL_NAME=gpt-4o
TTEXT_API_KEYS=["sk-xxx","sk-yyy"]

# API and MODEL used for images processing
TIMAGE_API_END_POINT=https://api.openai.com/v1
TIMAGE_MODEL_NAME=gpt-4o
TIMAGE_API_KEYS=["sk-xxx","sk-yyy"]
  • OLLAMA
# API and MODEL used for documents processing
TEXT_API_END_POINT=http://localhost:11434/v1
TEXT_MODEL_NAME=gemma2:latest
TEXT_API_KEYS=["ollama"]

# API and MODEL used for images processing
IMAGE_API_END_POINT=http://localhost:11434/v1
IMAGE_MODEL_NAME=moondream:latest
IMAGE_API_KEYS=["ollama"]
  • HUGGING FACE

Get your free api key from here: https://huggingface.co/settings/tokens

# API and MODEL used for documents processing
TEXT_API_END_POINT=https://api-inference.huggingface.co/v1
TEXT_MODEL_NAME=microsoft/Phi-3-mini-4k-instruct
TEXT_API_KEYS=["hf_xxx","hf_yyy"]

# API and MODEL used for images processing
IMAGE_API_END_POINT=https://api-inference.huggingface.co/v1
IMAGE_MODEL_NAME=nlpconnect/vit-gpt2-image-captioning
IMAGE_API_KEYS=["hf_xxx","hf_yyy"]