Update app.py

app.py

@@ -1,31 +1,37 @@
-from langchain.agents import initialize_agent
-from langchain.llms import OpenAI
-from gradio_tools.tools import (
-    StableDiffusionTool,
-    ImageCaptioningTool,
-    StableDiffusionPromptGeneratorTool,
-    TextToVideoTool,
-)
+import gradio as gr
+from langchain.document_loaders.base import Document
+from langchain.indexes import VectorstoreIndexCreator
+from apify_client import ApifyClient
+import os
 
-from langchain.memory import ConversationBufferMemory
+# Update with your OpenAI API key
+os.environ["OPENAI_API_KEY"] = "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"
 
-llm = OpenAI(temperature=0)
-memory = ConversationBufferMemory(memory_key="chat_history")
-tools = [
-    StableDiffusionTool().langchain,
-    ImageCaptioningTool().langchain,
-    StableDiffusionPromptGeneratorTool().langchain,
-    TextToVideoTool().langchain,
-]
+# Function to fetch website content using the updated actor
+def fetch_website_content(website_url):
+    apify_client = ApifyClient("apify_api_uz0y556N4IG2aLcESj67kmnGSUpHF12XAkLp")
+    run_input = {"startUrls": [{"url": website_url}]}
+    run = apify_client.actor("moJRLRc85AitArpNN").call(run_input=run_input)
+    items = list(apify_client.dataset(run["defaultDatasetId"]).iterate_items())
+    return items if items else None
 
+# Fetch and index website content
+content = fetch_website_content("https://python.langchain.com/en/latest/")
+documents = [Document(page_content=item["text"] or "", metadata={"source": item["url"]}) for item in content]
+index = VectorstoreIndexCreator().from_loaders([documents])
 
-agent = initialize_agent(
-    tools, llm, memory=memory, agent="conversational-react-description", verbose=True
-)
-output = agent.run(
-    input=(
-        "Please create a photo of a dog riding a skateboard "
-        "but improve my prompt prior to using an image generator."
-        "Please caption the generated image and create a video for it using the improved prompt."
-    )
-)
+# Function for the Gradio UI
+def ask_langchain(question):
+    result = index.query_with_sources(question)
+    answer = result["answer"]
+    sources = ", ".join(result["sources"])
+    return f"{answer}\n\nSources: {sources}"
+
+# Gradio interface
+iface = gr.Interface(fn=ask_langchain, 
+                     inputs="text", 
+                     outputs="text",
+                     live=True,
+                     title="LangChain Query",
+                     description="Ask a question about LangChain based on the indexed content.")
+iface.launch()