Wikipedia Chat implemented

.gitignore

@@ -0,0 +1 @@
+wikichat

app.py

@@ -1,61 +1,23 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from interaction import LLMResource
+
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+# client = InferenceClient(
+#     "HuggingFaceH4/zephyr-7b-beta",
+#     token=os.environ["API_KEY"]
+#     )
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+demo = gr.Interface(
+    LLMResource.invoke,
+    title="Vicky - Wikipedia Chatbot",
+    inputs=[gr.Textbox(label="Input Prompt", value="When was Oppenheimer released?")],
+    outputs=[gr.Textbox(label="Output")]
 )
 
 

interaction.py

@@ -0,0 +1,39 @@
+import os
+from langchain import hub
+from langchain.agents import load_tools, initialize_agent, AgentType
+from langchain_core.messages import HumanMessage, SystemMessage, AIMessage
+from langchain_huggingface import HuggingFaceEndpoint
+from langchain_huggingface import ChatHuggingFace
+
+
+class LLMResource:
+    llm = HuggingFaceEndpoint(
+        repo_id="mistralai/Mistral-7B-Instruct-v0.2",
+        task="text-generation",
+        huggingfacehub_api_token=os.environ["API_KEY"],
+        streaming=True,
+        temperature=0.5
+    )
+    chat_model = ChatHuggingFace(
+        llm = llm,
+    )
+    tools = load_tools(["wikipedia"], llm=llm)
+    agent = initialize_agent(
+        tools,
+        llm,
+        agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION,
+        handle_parsing_errors=True,
+    )
+
+    @staticmethod
+    def invoke(message:str):
+        response = LLMResource.agent.invoke(message)
+        print(response)
+        return response["output"][:-4]
+
+    @staticmethod
+    def test():
+        print(LLMResource.agent.invoke("When was the movie \'Oppenheimer\' released?"))
+
+if __name__ == "__main__":
+    LLMResource.test()

requirements.txt

@@ -1 +1,6 @@
-huggingface_hub==0.22.2
+langchain
+langchain-huggingface
+langchain-community
+huggingface-hub
+gradio
+wikipedia