updated app.py, initial rag demo ready. pip requirements also updated.

app.py

@@ -1,14 +1,17 @@
 import discord
 
 import os
+import json
 import requests
 import threading
 
+
 intents = discord.Intents.default()
 intents.message_content = True
 bot = discord.Bot(intents = intents)
 token = os.environ.get('TOKEN_DISCORD')
 
+
 class Like_Dislike(discord.ui.View):
     @discord.ui.button(style=discord.ButtonStyle.primary, emoji="👍")
     async def like_button(self, button, interaction):
@@ -18,44 +21,197 @@ class Like_Dislike(discord.ui.View):
     async def dislike_button(self, button, interaction):
         await interaction.response.send_message("You disliked the response")
 
+
 @bot.event
 async def on_ready():
     print(f"{bot.user} is ready and online!")
 
+
 @bot.slash_command(name="help", description="list of commands and other info.")
 async def help(ctx: discord.ApplicationContext):
     await ctx.respond("Hello! FURY Bot responds to all your messages\
                       \n1)Inside Forum channel and\
                       \n2)Those that tag the bot.")
 
+
+def llm_output(question: str, context: str) -> str:
+    """
+    Returns output from the LLM using the given user-question and retrived context
+    """
+
+    URL_LLM = 'https://robinroy03-fury-bot.hf.space'
+    # URL_LLM = 'http://localhost:11434'    # NOTE: FOR TESTING
+
+    prompt = f"""
+    You are a senior developer. Answer the users question based on the context provided.
+
+    Question: {question}
+
+    Context: {context}
+    """
+    obj = {
+            'model': 'phi3',
+            'prompt': prompt,
+            'stream': False
+        }
+
+    response = requests.post(URL_LLM + "/api/generate", json=obj)
+    response_json = json.loads(response.text)
+
+    return response_json['response']
+
+
+def embedding_output(message: str) -> list:
+    """
+    Returns embeddings for the given message
+
+    rtype: list of embeddings. Length depends on the model.
+    """
+
+    URL_EMBEDDING = 'https://robinroy03-fury-embeddings-endpoint.hf.space'
+
+    response = requests.post(URL_EMBEDDING + "/embedding", json={"text": message})
+    response_json = json.loads(response.text)
+
+    return response_json['output']
+
+
+def db_output(embedding: list) -> dict:
+    """
+    Returns the KNN results.
+
+    rtype: JSON
+    """
+
+    URL_DB = 'https://robinroy03-fury-db-endpoint.hf.space'
+    
+    response = requests.post(URL_DB + "/query", json={"embeddings": embedding})
+    response_json = json.loads(response.text)
+
+    return response_json
+
+
 @bot.event
 async def on_message(message):
-    url = 'http://127.0.0.1:8000/completion'
-    obj = {'user': message.author.id,
-           'text': message.content.replace("<@1243428204124045385>", "")}
+    """
+    Returns llm answer with the relevant context.
+    """
+
+    if (message.author == bot.user) or not(bot.user.mentioned_in(message)):
+        return
+
+    print(message.content)
+    await message.reply(content="Your message was received, it'll take around 30 seconds for FURY to process an answer.")
+
+    question = message.content.replace("<@1243428204124045385>", "")
+    embedding: list = embedding_output(question)
+    db_knn: dict = db_output(embedding)
+    llm_answer: str = llm_output(question, db_knn['matches'][0]['metadata']['text'])      # for the highest knn result (for the test only right now)  TODO: make this better
+
+    try:
+        await message.reply(content=llm_answer, view=Like_Dislike())
+        await message.reply(content=db_knn['matches'][0]['metadata']['text'])
+    except Exception as e:                                                           # TODO: make exception handling better
+        print(e)
+        await message.reply("An error occurred. Retry again.")
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+# @bot.event
+# async def on_message(message):
+#     url_llm = 'https://robinroy03-fury-bot.hf.space'
+#     url_embedding = 'https://robinroy03-fury-embeddings-endpoint.hf.space'
+#     url_db = 'https://robinroy03-fury-db-endpoint.hf.space'
+
+#     PROMPT = """
+#     You are a senior developer. Answer the users question based on the context provided.
+
+#     Question: {question}
+
+#     Context: {context}
+#     """
+
+#     user_question = message.content.replace("<@1243428204124045385>", "")
+    
+#     user_question_embedding = requests.post(url_embedding + "/embedding", json={"text": user_question})
+#     user_question_embedding = json.loads(user_question_embedding.text)['output']
+#     print(user_question_embedding)
+
+#     user_question_retrived_db_context = requests.post(url_db + "/query", json={"embeddings": user_question_embedding})
+#     user_question_retrived_db_context = json.loads(user_question_retrived_db_context.text)['matches'][0]['metadata']['text']
+#     print(user_question_retrived_db_context)
+
+#     PROMPT = PROMPT.format(question=user_question, context=user_question_retrived_db_context)
+#     print(PROMPT)
+
+#     obj = {
+#             # 'user': message.author.id,
+#             'model': 'phi3',
+#             'prompt': PROMPT,
+#             'stream': False
+#         }
+
+#     if (message.author != bot.user) and (bot.user.mentioned_in(message)):
+#         await message.reply(content="Your message was received, it'll take around 10 seconds for FURY to process an answer.")
+
+#         try:
+#             return_obj = requests.post(url_llm + "/api/generate", json=obj)
+#             return_json = json.loads(return_obj.text)
+#             await message.reply(content=return_json['response'] + "\n\n" + user_question_retrived_db_context, view=Like_Dislike())
+#         except requests.exceptions.RequestException as e:
+#             print(e)
+#             await message.reply(content="Sorry something internally went wrong. Retry again.")
+
+
+
+
+
+
+
+
+
+
 
-    if (message.author != bot.user) and (bot.user.mentioned_in(message)):
-        await message.reply(content="Your message was received, it'll take around 10 seconds for FURY to process an answer.")
 
-        try:
-            return_obj = requests.post(url, json=obj)
-            print(return_obj.text)
-            await message.reply(content=return_obj.text, view=Like_Dislike())
-        except requests.exceptions.RequestException as e:
-            print(e)
-            await message.reply(content="Sorry something internally went wrong. Retry again.")
+bot.run(token)
 
-def run_bot():
-    bot.run(token)
-threading.Thread(target=run_bot).start()
+# def run_bot():
+#     bot.run(token)
+# threading.Thread(target=run_bot).start()
 
 
 # ------------------------------------------------------------------------------------------------------------------------------
 
-import gradio as gr
+# import gradio as gr
 
-demo = gr.Blocks()
-with demo:
-    gr.HTML("The bot is working..")
+# demo = gr.Blocks()
+# with demo:
+#     gr.HTML("The bot is working..")
 
-demo.queue().launch()
+# demo.queue().launch()

requirements.txt

@@ -1,18 +1,84 @@
 aiodns==3.2.0
+aiofiles==23.2.1
 aiohttp==3.9.5
 aiosignal==1.3.1
+altair==5.3.0
+annotated-types==0.7.0
+anyio==4.4.0
 attrs==23.2.0
 Brotli==1.1.0
 certifi==2024.6.2
 cffi==1.16.0
 charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.2.1
+cycler==0.12.1
+dnspython==2.6.1
+email_validator==2.1.1
+fastapi==0.111.0
+fastapi-cli==0.0.4
+ffmpy==0.3.2
+filelock==3.14.0
+fonttools==4.53.0
 frozenlist==1.4.1
+fsspec==2024.6.0
+gradio==4.33.0
+gradio_client==0.17.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.23.3
 idna==3.7
+importlib_resources==6.4.0
+Jinja2==3.1.4
+jsonschema==4.22.0
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.0
+mdurl==0.1.2
 msgspec==0.18.6
 multidict==6.0.5
+numpy==1.26.4
+orjson==3.10.3
+packaging==24.0
+pandas==2.2.2
+pillow==10.3.0
 py-cord==2.5.0
 pycares==4.4.0
 pycparser==2.22
+pydantic==2.7.3
+pydantic_core==2.18.4
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.1
 requests==2.32.3
+rich==13.7.1
+rpds-py==0.18.1
+ruff==0.4.7
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.37.2
+tomlkit==0.12.0
+toolz==0.12.1
+tqdm==4.66.4
+typer==0.12.3
+typing_extensions==4.12.1
+tzdata==2024.1
+ujson==5.10.0
 urllib3==2.2.1
+uvicorn==0.30.1
+uvloop==0.19.0
+watchfiles==0.22.0
+websockets==11.0.3
 yarl==1.9.4