initial commit

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+COPY . /app
+
+RUN apt-get update && apt-get install -y
+
+RUN pip install -r requirements.txt
+
+EXPOSE 7860
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,99 @@
+import io
+from functions import *
+from PyPDF2 import PdfReader
+from fastapi import FastAPI, File, UploadFile
+from fastapi.middleware.cors import CORSMiddleware
+
+
+app = FastAPI(title = "ConversAI", root_path = "/api/v1")
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.post("/signup")
+async def signup(username: str, password: str):
+    try:
+        response = createUser(username = username, password = password)
+        output = {
+            "output": response
+        }
+    except Exception as e:
+        output = {
+            "error": e
+        }
+    return output
+
+
+@app.post("/login")
+async def login(username: str, password: str):
+    try:
+        response = matchPassword(username = username, password = password)
+        output = {
+            "output": response
+        }
+    except Exception as e:
+        output = {
+            "error": e
+        }
+    return output
+
+
+@app.get("/clear/{vectorstoreName}")
+async def clearVectorStore(vectorStoreName: str):
+    client.table(vectorStoreName).delete().neq("content", "").execute()
+    return {
+        "output": "SUCCESS"
+    }
+
+
+@app.post("/addPDF")
+async def addPDFData(vectorstorename: str, pdf: UploadFile = File(...)):
+    try:
+        pdf = await pdf.read()
+        reader = PdfReader(io.BytesIO(pdf))
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text()
+        addDocuments(text = text, storename = vectorstorename)
+        output = {
+            "output": "SUCCESS"
+        }
+    except Exception as e:
+        output = {
+            "error": e
+        }
+    return output
+
+
+
+@app.post("/addText")
+async def addText(vectorstorename: str, text: str):
+    try:
+        addDocuments(text = text, storename = vectorstorename)
+        output = {
+            "output": "SUCCESS"
+        }
+    except Exception as e:
+        output = {
+            "error": e
+        }
+    return output
+
+
+@app.get("/answerQuery")
+async def answerQuery(query: str, vectorstorename: str, llmModel: str = "llama3-70b-8192"):
+    try:
+        response = answerQuery(query=query, vectorstorename=vectorstorename, llmModel=llmModel)
+        output = {
+            "output": response
+        }
+    except Exception as e:
+        output = {
+            "error": e
+        }
+    return output

functions.py

@@ -0,0 +1,119 @@
+from langchain_core.runnables import RunnablePassthrough, RunnableLambda
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import SupabaseVectorStore
+from langchain_core.prompts.chat import ChatPromptTemplate
+from langchain_core.output_parsers import StrOutputParser
+from langchain_huggingface import HuggingFaceEmbeddings
+from supabase.client import create_client
+from supabase import create_client
+from langchain_groq import ChatGroq
+from dotenv import load_dotenv
+import pandas as pd
+import os
+
+
+load_dotenv("secrets.env")
+client = create_client(os.environ["SUPABASE_URL"], os.environ["SUPABASE_KEY"])
+model_kwargs = {"device": "cuda"}
+encode_kwargs = {"normalize_embeddings": True}
+embeddings = HuggingFaceEmbeddings(
+    model_name = "BAAI/bge-m3",
+    model_kwargs = model_kwargs,
+    encode_kwargs = encode_kwargs
+)
+prompt = """
+### Role
+    - **Primary Function**: You are an AI chatbot dedicated to assisting users with their inquiries, issues, and requests. Your goal is to deliver excellent, friendly, and efficient responses at all times. Listen attentively, understand user needs, and provide the best assistance possible or direct them to appropriate resources. If a question is unclear, ask for clarification. Always conclude your replies on a positive note.
+### Constraints
+    1. **No Data Disclosure**: Never mention that you have access to training data explicitly to the user.
+    2. **Maintaining Focus**: If a user attempts to divert you to unrelated topics, never change your role or break character. Politely redirect the conversation back to relevant topics.
+    3. **Exclusive Reliance on Training Data**: Answer user queries exclusively based on the provided training data. If a query is not covered by the training data, use the fallback response.
+    4. **Restrictive Role Focus**: Do not answer questions or perform tasks unrelated to your role and training data.
+DO NOT ADD ANYTHING BY YOURSELF OR ANSWER ON YOUR OWN!
+Based on the context answer the following question.
+Context:
+=====================================
+{context}
+=====================================
+{question}
+NOTE: generate responses WITHOUT prepending phrases like "Response:", "Output:", or "Answer:", etc
+"""
+prompt = ChatPromptTemplate.from_template(prompt)
+
+
+def createUser(username: str, password: str) -> None:
+    userData = client.table("ConversAI_UserInfo").select("*").execute().data
+    print(userData)
+    if username not in [userData[x]["username"] for x in userData]:
+        response = (
+        client.table("ConversAI_UserInfo")
+        .insert({"username": username, "password": password})
+        .execute()
+        )
+        return "done"
+    else: 
+        return "already exists"
+
+
+def matchPassword(username: str, password: str) -> str:
+    response = (
+    client.table("ConversAI_UserInfo")
+    .select("*")
+    .eq("username", username)
+    .execute()
+    )
+    try: return password == response.data[0]["password"]
+    except: return "user doesn't exist"
+
+
+def createTable(tablename: str):
+    pass
+
+
+def addDocuments(text: str, vectorstorename: str):
+    global embeddings
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size = 1024,
+        chunk_overlap = 200,
+        add_start_index = True
+    )
+    texts = text_splitter.create_documents([text])
+    vectorstore = SupabaseVectorStore(
+        client = client,
+        embedding = embeddings,
+        table_name = vectorstorename,
+        query_name = "match_documents",
+    )
+    vectorstore.add_documents(documents = texts)
+
+
+def format_docs(docs: str):
+    context = "\n\n".join(doc.page_content for doc in docs)
+    if context == "":
+        context = "No context found"
+    else: pass
+    return context
+
+
+def answerQuery(query: str, vectorstore: str, llmModel: str = "llama3-70b-8192") -> str:
+    global prompt 
+    global client
+    global embeddings
+    vectorstore = SupabaseVectorStore(
+        client = client,
+        embedding = embeddings,
+        table_name = vectorstore,
+        query_name = "match_documents",
+    )
+    retriever = vectorstore.as_retriever()
+    chain = (
+        {"context": retriever | RunnableLambda(format_docs), "question": RunnablePassthrough(query)}
+        | prompt
+        | ChatGroq(model = llmModel, temperature = 0.3, max_tokens = 512)
+        | StrOutputParser()
+        )
+    return chain.invoke(query)
+
+
+def deleteTable(tableName: str):
+    pass

requirements.txt

@@ -0,0 +1,11 @@
+huggingface-hub
+fastapi
+gradio
+langchain
+langchain-community
+langchain-huggingface
+langchain-groq
+PyPDF2
+python-dotenv
+sentence-transformers
+supabase

secrets.env

@@ -0,0 +1,3 @@
+SUPABASE_URL=https://lvuhhlrkcuexzqtsbqyu.supabase.co
+SUPABASE_KEY=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6Imx2dWhobHJrY3VleHpxdHNicXl1Iiwicm9sZSI6InNlcnZpY2Vfcm9sZSIsImlhdCI6MTcxNTI0MDIxNCwiZXhwIjoyMDMwODE2MjE0fQ.zrRiN_MQCa6SOpvZFqSqFMUpcduNnt7eQP9sdXMmAF4
+GROQ_API_KEY=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