download_transcripts.py

@@ -1,7 +1,6 @@
 import requests
 import os
 from bs4 import BeautifulSoup
-import json
 
 folder_path = "transcripts"
 
@@ -9,22 +8,21 @@ if not os.path.exists(folder_path):
     os.makedirs(folder_path)
 
 for i in range(1, 139):
-    try:
-        url = f"https://darknetdiaries.com/transcript/{i}"
-        r = requests.get(url)
-        soup = BeautifulSoup(r.text, 'html.parser')
+    url = f"https://darknetdiaries.com/transcript/{i}"
+    r = requests.get(url)
+    soup = BeautifulSoup(r.text, 'html.parser')
 
-        transcript = soup.find('pre').get_text()
+    transcript = soup.find('pre').get_text()
+    title_section = soup.find('h1').get_text()
 
-        url = f"https://api.darknetdiaries.com/{i}.json"
-        r = requests.get(url)
-        parsed_json = json.loads(r.text)
-        title = parsed_json["episode_name"]
-        number = parsed_json["episode_number"]
-        downloads = parsed_json["total_downloads"]
+    url = f"https://darknetdiaries.com/episode/{i}"
+    r = requests.get(url)
+    soup = BeautifulSoup(r.text, 'html.parser')
+    downloads = soup.find(id='downloads').get_text()
 
-        with open(f"{folder_path}/episode_{number}.txt", "w") as f:
-            f.write(f"{title}\n{downloads}\n{transcript}")
-        print(f"{number} {title}")
-    except Exception:
-        print(f"Failed scraping episode {i}")
+    ep, title = title_section.split(":", 1)
+    ep = ep.strip()
+    title = title.strip()
+    with open(f"{folder_path}/episode_{i}.txt", "w") as f:
+        f.write(f"{title}\n{downloads}\n{transcript}")
+    print(f"{ep} {title}")

main.py

@@ -4,13 +4,9 @@ from llama_index.node_parser import SimpleNodeParser
 from llama_index import VectorStoreIndex
 from llama_index.llms import OpenAI, ChatMessage, MessageRole
 from llama_index.prompts import ChatPromptTemplate
-from llama_index import set_global_handler
-from llama_index.chat_engine.types import ChatMode
 import os
 import re
 
-#set_global_handler("simple")
-
 llm = OpenAI(model="gpt-4", temperature=0, max_tokens=256)
 service_context = ServiceContext.from_defaults(llm=llm)
 set_global_service_context(service_context)
@@ -94,13 +90,16 @@ refine_template = ChatPromptTemplate(chat_refine_msgs)
 
 chat_engine = index.as_chat_engine(
     text_qa_template=text_qa_template,
-    refine_template=refine_template,
-    chat_mode=ChatMode.OPENAI
+    refine_template=refine_template
 )
 
 while True:
     try:
-        chat_engine.chat_repl()
+        user_prompt = input("Prompt: ")
+        streaming_response = chat_engine.stream_chat(user_prompt)
+        for token in streaming_response.response_gen:
+            print(token, end="")
+        print("\n")
     except KeyboardInterrupt:
         break