modify gemini dependences

app.py

@@ -2,15 +2,11 @@ import gradio
 import gradio as gr
 from langchain.chains import RetrievalQA
 from langchain.text_splitter import SpacyTextSplitter
-from langchain_community.chat_models import ChatZhipuAI, ChatGooglePalm
 from langchain_community.document_loaders import PyPDFLoader
-from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings, GooglePalmEmbeddings
+from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings
 from langchain_community.vectorstores import Chroma
 from langchain_core.prompts import PromptTemplate
-
-import spacy
-
-spacy.cli.download("en_core_web_sm")
+from langchain_google_genai import ChatGoogleGenerativeAI
 
 template = """Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer. Use three sentences maximum. Keep the answer as concise as possible. Always say "thanks for asking!" at the end of the answer.
 Tips: Make sure to cite your sources, and use the exact words from the context.
@@ -31,15 +27,11 @@ class RAGDemo(object):
             gradio.Error("Please enter model API key.")
             return
         if 'glm' in model_name:
-            self.chat_model = ChatZhipuAI(
-                temperature=0.5,
-                api_key=api_key,
-                model="glm-3-turbo",
-            )
+            gradio.Error("GLM is not supported yet.")
         elif 'gemini' in model_name:
-            self.chat_model = ChatGooglePalm(
+            self.chat_model = ChatGoogleGenerativeAI(
                 google_api_key=api_key,
-                model_name='gemini-pro'
+                model='gemini-pro'
             )
 
     def _init_embedding(self, embedding_model_name, api_key):
@@ -48,8 +40,6 @@ class RAGDemo(object):
             return
         if 'glm' in embedding_model_name:
             gradio.Error("GLM is not supported yet.")
-        elif 'gemini' in embedding_model_name:
-            self.embedding = GooglePalmEmbeddings(google_api_key=api_key, show_progress_bar=True)
         else:
             self.embedding = HuggingFaceInferenceAPIEmbeddings(
                 api_key=api_key, model_name=embedding_model_name
@@ -59,6 +49,7 @@ class RAGDemo(object):
         if not file_path:
             gradio.Error("Please enter vector database file path.")
             return
+        gr.Info("Building vector database...")
         loader = PyPDFLoader(file_path)
         pages = loader.load()
 
@@ -68,6 +59,7 @@ class RAGDemo(object):
         self.vector_db = Chroma.from_documents(
             documents=docs, embedding=self.embedding
         )
+        gr.Info("Vector database built successfully.")
 
     def _init_settings(self, model_name, api_key, embedding_model, embedding_api_key, data_file):
         self._init_chat_model(model_name, api_key)
@@ -78,7 +70,8 @@ class RAGDemo(object):
         basic_qa = RetrievalQA.from_chain_type(
             self.chat_model,
             retriever=self.vector_db.as_retriever(),
-            chain_type_kwargs={"prompt": QA_CHAIN_PROMPT}
+            chain_type_kwargs={"prompt": QA_CHAIN_PROMPT},
+            verbose=True,
         )
         return basic_qa.invoke(input_text)
 
@@ -90,13 +83,13 @@ class RAGDemo(object):
                 with gr.Row():
                     with gr.Column():
                         model_name = gr.Dropdown(
-                            choices=['glm-3-turbo', 'gemini-1.0-pro'],
+                            choices=['gemini-1.0-pro'],
                             value='glm-3-turbo',
                             label="model"
                         )
                         api_key = gr.Textbox(placeholder="your api key for LLM", label="api key")
                         embedding_model = gr.Dropdown(
-                            choices=['glm-embedding-2', 'gemini-embedding', 'sentence-transformers/all-MiniLM-L6-v2',
+                            choices=['sentence-transformers/all-MiniLM-L6-v2',
                                      'intfloat/multilingual-e5-large'],
                             value="sentence-transformers/all-MiniLM-L6-v2",
                             label="embedding model"
@@ -122,7 +115,7 @@ class RAGDemo(object):
                 inputs=input_text,
                 outputs=output,
             )
-            return demo
+        return demo
 
 
 app = RAGDemo()