feat: Migrate from OpenAI to Google Gemini Pro

Replaces OpenAI's language models with Google's Gemini Pro for enhanced performance and capabilities. The code now utilizes `ChatGoogleGenerativeAI` and leverages environment variables for API key management.

Projects/2. Large Language Models and LangChain/few_short.py

@@ -1,7 +1,15 @@
 from langchain import PromptTemplate
 from langchain import FewShotPromptTemplate
-from langchain.chat_models import ChatOpenAI
+from langchain_google_genai import ChatGoogleGenerativeAI # Import ChatGoogleGenerativeAI
 from langchain import LLMChain
+from dotenv import load_dotenv 
+import os
+
+# Load environment variables from .env file
+load_dotenv() 
+
+# Create ChatGoogleGenerativeAI instance
+llm = ChatGoogleGenerativeAI(model="gemini-pro", google_api_key=os.getenv("GEMINI_API_KEY")) 
 
 # create our examples dictionery
 examples = [
@@ -49,7 +57,7 @@
 )
 
 # load the model
-chat = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0.9)
+chat = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.9, google_api_key=os.getenv("GEMINI_API_KEY")) # Use 'gemini-pro' instead of 'gemini'
 
 chain = LLMChain(llm=chat, prompt=few_shot_prompt_template, verbose=True)
 

Projects/3. Learning How to Prompt/chain_prompting.py

@@ -1,8 +1,20 @@
 from langchain import PromptTemplate, LLMChain
-from langchain.llms import OpenAI
+from langchain_google_genai import ChatGoogleGenerativeAI
+import os
+from dotenv import load_dotenv
+
+
+# Load environment variables from .env file
+load_dotenv()
 
 # Initialize LLM
-llm = OpenAI(model_name="text-davinci-003", temperature=0)
+api_key = os.getenv("GEMINI_API_KEY")
+llm = ChatGoogleGenerativeAI(model="gemini-pro", google_api_key=api_key)
+print(
+    llm.invoke(
+        "What are some of the pros and cons of Python as a programming language?"
+    )
+)
 
 # Prompt 1
 template_question = """What is the name of the famous scientist who developed the theory of general relativity?
@@ -36,5 +48,5 @@
 # Run the LLMChain for the second prompt
 response_fact = chain_fact.run(input_data)
 
-print("Scientist:", scientist)
-print("Fact:", response_fact)
+print("Scientist:", scientist.text)
+print("Fact:", response_fact.text)