Update app.py

app.py

@@ -15,6 +15,8 @@ import gradio as gr
 import requests
 import os
 
+from langchain_ollama import OllamaLLM
+
 
 import sys
 sys.path.append('../..')
@@ -41,6 +43,39 @@ fs_token = os.environ.get('fs_token')
 
 llm_name = "gpt-3.5-turbo-0125"
 
+
+# For Groq API
+
+from langchain_groq import ChatGroq
+
+llm = ChatGroq(
+    model="mixtral-8x7b-32768",
+    temperature=0,
+    max_tokens=None,
+    timeout=None,
+    max_retries=2,
+    # other params...
+)
+
+chat_completion = client.chat.completions.create(
+    messages=[
+        {
+            "role": "system",
+            "content": "You are a knowledgeable assistant, Provide a precise and point-wise reply based on provided context only. \
+                        Ensure that your reply addresses each aspect of the query thoroughly, and highlight the important points using text formatting in your reply..",
+        },
+        {
+            "role": "user",
+            "content": query,
+        }
+    ],
+    model="llama3-8b-8192",
+)
+
+print(chat_completion.choices[0].message.content)
+
+
+
 vectordb = initialize.initialize()
 
 chat_history_doc = []
@@ -74,9 +109,10 @@ def chat_query_doc(question, chat_history_doc):
 
 
 
-    llm = ChatOpenAI(model = llm_name, temperature = 0.1, api_key = OPENAI_API_KEY)
+    #llm = ChatOpenAI(model = llm_name, temperature = 0.1, api_key = OPENAI_API_KEY)
     #llm = GoogleGenerativeAI(model = "gemini-pro", google_api_key = GEMINI_API_KEY)                                   ###
     #llm = ChatGoogleGenerativeAI(model = "gemini-1.0-pro", google_api_key = GEMINI_API_KEY, temperature = 0)
+    llm = OllamaLLM(model="unsloth/Llama-3.2-3B")
 
     # Conversation Retrival Chain with Memory
     #memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
@@ -103,8 +139,9 @@ def chat_query_doc(question, chat_history_doc):
 
 def chat_query_IS(question, chat_history_IS):
     
-    llm = ChatOpenAI(model = llm_name, temperature = 0.1, api_key = OPENAI_API_KEY)
+    #llm = ChatOpenAI(model = llm_name, temperature = 0.1, api_key = OPENAI_API_KEY)
     #llm = ChatGoogleGenerativeAI(model="gemini-pro", google_api_key=GEMINI_API_KEY)                                   ###
+    llm = OllamaLLM(model="unsloth/Llama-3.2-3B")
 
     system_old = f""" Provide an elaborate, detailed and pointwise reply about the Topic, as per relevant IS/IEEE/BIS Standard.
               Also, at the end of your reply, quote the Relevant Standard Referred. Topic : {question}