.editorconfig

@@ -1,14 +0,0 @@
-root = true
-
-[*]
-charset = utf-8
-end_of_line = lf
-indent_size = 4
-indent_style = space
-insert_final_newline = true
-trim_trailing_whitespace = true
-max_line_length = 120
-
-[*.md]
-trim_trailing_whitespace = false
-max_line_length = 0

.gitignore

@@ -1,5 +1,3 @@
-.env
 /transcripts
 /index
-/.idea
+/.idea
-/venv

README.MD

@@ -9,15 +9,9 @@ Well, let's ask our LLM:
 
 ## How to run
 ### Install dependencies
-It is recommended to use a python version greater than or equal to ``3.10.0``.
+I have no idea what the correct way to install dependencies with python is. Somehow install these libraries and their dependencies:
-Another stuff recommended, is to create a venv or use an IDE that supports venv creation, so all dependencies are installed locally to the project and not globally. If not, you can use https://virtualenv.pypa.io/en/latest/ to artificially create isolated environments.
+- llama_index
-
+- beautifulsoup4
-Install the dependencies required to run the project by running the following command at the project root :
-
-```shell
-pip install -r requirements.txt
-```
-
 ### Execution
 Download transcripts:
 ```shell
@@ -37,7 +31,6 @@ python3 main.py
 On the first run, it will generate the index. This can take a while, but it will be cached on disk for the next runs.
 
 You can then ask it any questions about Darknet Diaries!
-
 ## Examples
 
 > What is the intro of the podcast?
@@ -76,4 +69,4 @@ You can then ask it any questions about Darknet Diaries!
 >>The episode also covers a project where Jason was tasked with hacking into a large, worldwide bank. His job was to examine the bank's mobile app for any potential security vulnerabilities that could expose customer or sensitive information. The episode provides a detailed look into the world of penetration testing, highlighting the importance of robust security measures in both physical and digital spaces.
 > 
 > How many downloads does this episode have?
->> Episode 130 of Darknet Diaries, titled "JASON'S PEN TEST", has 667,528 downloads.
+>> Episode 130 of Darknet Diaries, titled "JASON'S PEN TEST", has 667,528 downloads.

download_transcripts.py

@@ -5,30 +5,26 @@ import json
 
 folder_path = "transcripts"
 
-if __name__ == '__main__':
+if not os.path.exists(folder_path):
-    if not os.path.exists(folder_path):
+    os.makedirs(folder_path)
-        os.makedirs(folder_path)
 
-    for i in range(1, 139):
+for i in range(1, 139):
-        try:
+    try:
-            # fetch transcript
+        url = f"https://darknetdiaries.com/transcript/{i}"
-            url = f"https://darknetdiaries.com/transcript/{i}"
+        r = requests.get(url)
-            r = requests.get(url)
+        soup = BeautifulSoup(r.text, 'html.parser')
-            soup = BeautifulSoup(r.text, 'html.parser')
 
-            transcript = soup.find('pre').get_text()
+        transcript = soup.find('pre').get_text()
 
-            # fetch transcript metadata
+        url = f"https://api.darknetdiaries.com/{i}.json"
-            url = f"https://api.darknetdiaries.com/{i}.json"
+        r = requests.get(url)
-            r = requests.get(url)
+        parsed_json = json.loads(r.text)
-            parsed_json = json.loads(r.text)
+        title = parsed_json["episode_name"]
-            title = parsed_json["episode_name"]
+        number = parsed_json["episode_number"]
-            number = parsed_json["episode_number"]
+        downloads = parsed_json["total_downloads"]
-            downloads = parsed_json["total_downloads"]
 
-            # write transcript
+        with open(f"{folder_path}/episode_{number}.txt", "w") as f:
-            with open(f"{folder_path}/episode_{number}.txt", "w", encoding='utf-8') as f:
+            f.write(f"{title}\n{downloads}\n{transcript}")
-                f.write(f"{title}\n{downloads}\n{transcript}")
+        print(f"{number} {title}")
-            print(f"{number} {title}")
+    except Exception:
-        except Exception as err:
+        print(f"Failed scraping episode {i}")
-            print(f"Failed scraping episode {i} : [{err}]")

main.py

@@ -4,109 +4,103 @@ 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 import set_global_handler
 from llama_index.chat_engine.types import ChatMode
-from dotenv import load_dotenv
 import os
 import re
 
 # set_global_handler("simple")
 
-# load .env
+llm = OpenAI(model="gpt-4", temperature=0, max_tokens=256)
-load_dotenv()
-OPEN_API_KEY = os.getenv('OPEN_API_KEY')
-
-# config llm context
-llm = OpenAI(model="gpt-4", temperature=0, max_tokens=256, api_key=OPEN_API_KEY)
 service_context = ServiceContext.from_defaults(llm=llm)
 set_global_service_context(service_context)
 
-if __name__ == '__main__':
+if not os.path.exists("./index/lock"):
-    if not os.path.exists("./index/lock"):
+    documents = []
-        documents = []
+    for filename in os.listdir("./transcripts"):
-        for filename in os.listdir("./transcripts"):
+        episode_number = re.search(r'\d+', filename).group()
-            episode_number = re.search(r'\d+', filename).group()
+        with open("./transcripts/" + filename, 'r') as f:
-            with open("./transcripts/" + filename, 'r') as f:
+            title = f.readline().strip()
-                title = f.readline().strip()
+            downloads = f.readline().strip()
-                downloads = f.readline().strip()
+            content = f.read()
-                content = f.read()
+        document = Document(
-            document = Document(
+            text=content,
-                text=content,
+            doc_id=filename,
-                doc_id=filename,
+            metadata={
-                metadata={
+                "episode_number": episode_number,
-                    "episode_number": episode_number,
+                "episode_title": title,
-                    "episode_title": title,
+                "episode_downloads": downloads,
-                    "episode_downloads": downloads,
+                "episode_url": f"https://darknetdiaries.com/episode/{episode_number}/"
-                    "episode_url": f"https://darknetdiaries.com/episode/{episode_number}/"
+            }
-                }
-            )
-            documents.append(document)
-
-        parser = SimpleNodeParser.from_defaults()
-        nodes = parser.get_nodes_from_documents(documents)
-
-        index = VectorStoreIndex(nodes, show_progress=True)
-        index.storage_context.persist(persist_dir="./index")
-        open("./index/lock", 'a').close()
-    else:
-        print("Loading index...")
-        storage_context = StorageContext.from_defaults(persist_dir="./index")
-        index = load_index_from_storage(storage_context)
-
-    chat_text_qa_msgs = [
-        ChatMessage(
-            role=MessageRole.SYSTEM,
-            content=(
-                "You have been trained on the Darknet Diaries podcast transcripts with data from october 6 2023."
-                "You are an expert about it and will answer as such. You know about every episode up to number 138."
-                "Always answer the question, even if the context isn't helpful."
-                "Mention the number and title of the episodes you are referring to."
-            )
-        ),
-        ChatMessage(
-            role=MessageRole.USER,
-            content=(
-                "Context information is below.\n"
-                "---------------------\n"
-                "{context_str}\n"
-                "---------------------\n"
-                "Given the context information and not prior knowledge,"
-                "answer the question: {query_str}\n"
-            )
         )
-    ]
+        documents.append(document)
-    text_qa_template = ChatPromptTemplate(chat_text_qa_msgs)
 
-    chat_refine_msgs = [
+    parser = SimpleNodeParser.from_defaults()
-        ChatMessage(
+    nodes = parser.get_nodes_from_documents(documents)
-            role=MessageRole.SYSTEM,
-            content="Always answer the question, even if the context isn't helpful.",
-        ),
-        ChatMessage(
-            role=MessageRole.USER,
-            content=(
-                "We have the opportunity to refine the original answer "
-                "(only if needed) with some more context below.\n"
-                "------------\n"
-                "{context_msg}\n"
-                "------------\n"
-                "Given the new context, refine the original answer to better "
-                "answer the question: {query_str}. "
-                "If the context isn't useful, output the original answer again.\n"
-                "Original Answer: {existing_answer}"
-            ),
-        ),
-    ]
-    refine_template = ChatPromptTemplate(chat_refine_msgs)
 
-    chat_engine = index.as_chat_engine(
+    index = VectorStoreIndex(nodes, show_progress=True)
-        text_qa_template=text_qa_template,
+    index.storage_context.persist(persist_dir="./index")
-        refine_template=refine_template,
+    open("./index/lock", 'a').close()
-        chat_mode=ChatMode.OPENAI
+else:
+    print("Loading index...")
+    storage_context = StorageContext.from_defaults(persist_dir="./index")
+    index = load_index_from_storage(storage_context)
+
+chat_text_qa_msgs = [
+    ChatMessage(
+        role=MessageRole.SYSTEM,
+        content=(
+            "You have been trained on the Darknet Diaries podcast transcripts with data from october 6 2023."
+            "You are an expert about it and will answer as such. You know about every episode up to number 138."
+            "Always answer the question, even if the context isn't helpful."
+            "Mention the number and title of the episodes you are referring to."
+        )
+    ),
+    ChatMessage(
+        role=MessageRole.USER,
+        content=(
+            "Context information is below.\n"
+            "---------------------\n"
+            "{context_str}\n"
+            "---------------------\n"
+            "Given the context information and not prior knowledge,"
+            "answer the question: {query_str}\n"
+        )
     )
+]
+text_qa_template = ChatPromptTemplate(chat_text_qa_msgs)
+
+chat_refine_msgs = [
+    ChatMessage(
+        role=MessageRole.SYSTEM,
+        content="Always answer the question, even if the context isn't helpful.",
+    ),
+    ChatMessage(
+        role=MessageRole.USER,
+        content=(
+            "We have the opportunity to refine the original answer "
+            "(only if needed) with some more context below.\n"
+            "------------\n"
+            "{context_msg}\n"
+            "------------\n"
+            "Given the new context, refine the original answer to better "
+            "answer the question: {query_str}. "
+            "If the context isn't useful, output the original answer again.\n"
+            "Original Answer: {existing_answer}"
+        ),
+    ),
+]
+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
+)
+
+while True:
+    try:
+        chat_engine.chat_repl()
+    except KeyboardInterrupt:
+        break
 
-    while True:
-        try:
-            chat_engine.chat_repl()
-        except KeyboardInterrupt:
-            break

requirements.txt

@@ -1,16 +0,0 @@
-# =====================
-# Required dependencies
-# =====================
-# general deps
-requests~=2.31.0
-llama-index~=0.8.40
-beautifulsoup4~=4.12.2
-python-dotenv~=1.0.0
-
-# llama sub deps
-transformers~=4.34.0
-torch~=2.1.0
-
-# =====================
-# Development dependencies
-# =====================