all changes

app.py

@@ -9,9 +9,46 @@ from langchain.schema import StrOutputParser
 from langchain.schema.prompt_template import format_document
 from langchain.schema.runnable import RunnablePassthrough
 from langchain.vectorstores import Chroma
+import google.generativeai as genai
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+from langchain_google_genai import ChatGoogleGenerativeAI
 
+GOOGLE_API_KEY=os.environ['GOOGLE_API_KEY']
+
+genai.configure(api_key=GOOGLE_API_KEY)
 
 
 loader = WebBaseLoader("https://blog.google/technology/ai/google-gemini-ai/")
 docs = loader.load()
+st.write(len(docs))
+
+
+model = genai.GenerativeModel('gemini-pro')
+
+prompt = st.text_input("Enter Prompt","What is the meaning of life?")
+response = model.generate_content(prompt)
+
+st.write(response.text)
+# If there is no environment variable set for the API key, you can pass the API
+# key to the parameter `google_api_key` of the `ChatGoogleGenerativeAI` function:
+# `google_api_key="key"`.
+# llm = ChatGoogleGenerativeAI(model="gemini-pro",
+#                  temperature=0.7, top_p=0.85)
+
+
+# If there is no environment variable set for the API key, you can pass the API
+# key to the parameter `google_api_key` of the `GoogleGenerativeAIEmbeddings`
+# function: `google_api_key = "key"`.
+
+# gemini_embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+
+# # Save to disk
+# vectorstore = Chroma.from_documents(
+#                      documents=docs,                 # Data
+#                      embedding=gemini_embeddings,    # Embedding model
+#                      persist_directory="./chroma_db" # Directory to save data
+#                      )
 
+# vectorstore_disk = Chroma(
+#                         persist_directory="./chroma_db",       # Directory of db
+#                         embedding_function=gemini_embeddings   # Embedding model