Is your feature request related to a problem? Please describe.
When we try to use Gemini LLM we only have option to pass it as an API KEY, what if we have a json file through which we want to connect to our LLM Project?
Describe the solution you'd like
In gemini_chat.py inside the else part, we can have a solution of passing the path to the json file through which we will be connecting to the Gemini LLM project
The code for connection can look something like this
`
if "api_key" in config or os.getenv("GOOGLE_API_KEY"):
import google.generativeai as genai
genai.configure(api_key=config["api_key"])
self.chat_model = genai.GenerativeModel(model_name)
else:
# Authenticate using VertexAI
import google.auth
import vertexai
from vertexai.generative_models import GenerativeModel, Part
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = PATH
credentials, _ = google.auth.default()
vertexai.init()
self.chat_model = GenerativeModel("gemini-pro")
Is your feature request related to a problem? Please describe. When we try to use Gemini LLM we only have option to pass it as an
API KEY, what if we have a json file through which we want to connect to our LLM Project?Describe the solution you'd like In
gemini_chat.pyinside the else part, we can have a solution of passing the path to the json file through which we will be connecting to the Gemini LLM projectThe code for connection can look something like this
` if "api_key" in config or os.getenv("GOOGLE_API_KEY"): import google.generativeai as genai
`