Fix LFS tracking

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+chroma_langchain_db1/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,83 @@
+#custom
+report endpoint for flagging bit response
+.env
+*.pdf
+app copy.py
+myenv/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Environment variables
+.env
+
+# Logs
+*.log
+logs/
+
+# Virtual environment
+venv/
+env/
+*.venv
+*.env/
+
+# Dependency directories
+pip-wheel-metadata/
+*.egg-info/
+.dist-info/
+.Python
+node_modules/
+
+# Operating system files
+.DS_Store
+Thumbs.db
+
+# Database files
+# *.sqlite3
+*.db
+
+# ChromaDB files
+chroma/
+*.chroma
+# chroma.sqlite3
+
+# Hugging Face Spaces large files
+.git-lfs*
+
+# Temporary files
+*.bak
+*.swp
+*.tmp
+
+# IDE and editor settings
+.idea/
+.vscode/
+*.code-workspace
+
+# Jupyter Notebook checkpoints
+.ipynb_checkpoints/
+
+# Build artifacts
+build/
+dist/
+*.egg
+*.whl
+
+# Coverage reports
+htmlcov/
+.coverage
+.tox/
+.cache/
+
+# Deployment files
+*.pid
+*.lock
+*.sock
+
+# Ignore any large files not tracked by Git LFS
+!*.lfs

Dockerfile

@@ -0,0 +1,16 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9-slim
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,10 +1,11 @@
 ---
-title: Email Ai
-emoji: 🐠
-colorFrom: purple
-colorTo: gray
+title: Email AI
+emoji: 🌍
+colorFrom: red
+colorTo: pink
 sdk: docker
 pinned: false
+short_description: testing fastapi server
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,129 @@
+from fastapi import FastAPI, Depends, HTTPException, Header, File, UploadFile
+from pydantic import BaseModel
+from typing import List, Dict, Optional
+from email_ai import initialize_conversation, intro_message, get_chat_model_completions
+
+import google.generativeai as genai
+import os
+from dotenv import load_dotenv
+
+import speech_recognition as sr
+from io import BytesIO
+import wave
+
+# Load environment variables
+load_dotenv()
+# gemini_api_key = os.getenv("GEMINI_API_KEY")
+# genai.configure(api_key=gemini_api_key)
+
+# Define a secret API key (use environment variables in production)
+API_KEY = os.getenv("API_KEY")
+
+app = FastAPI()
+
+# Initialize speech recognizer
+recognizer = sr.Recognizer()
+
+# Pydantic models for request/response validation
+class Message(BaseModel):
+    role: str
+    content: str
+
+class ChatRequest(BaseModel):
+    message: str
+
+class ChatResponse(BaseModel):
+    response: str
+    conversation: List[Message]
+
+class Report(BaseModel):
+    response: str
+    message: str
+    timestamp: str
+
+# Dependency to check the API key
+async def verify_api_key(x_api_key: str = Header(...)):
+    if x_api_key != API_KEY:
+        raise HTTPException(status_code=403, detail="Unauthorized")
+    
+@app.get("/init", response_model=ChatResponse, dependencies=[Depends(verify_api_key)])
+async def get_conversation():
+    global llm, chroma_retriever, conversation_bot
+
+    conversation_bot = [Message(role="bot", content=intro_message)]
+    llm, chroma_retriever = initialize_conversation()
+
+    return ChatResponse(
+        response=intro_message,
+        conversation=conversation_bot
+    )
+
+@app.post("/chat", response_model=ChatResponse, dependencies=[Depends(verify_api_key)])
+async def send_message(request: ChatRequest):
+    global conversation_bot
+    
+    conversation_bot.append(Message(role="user", content=request.message))
+    response_assistant = get_chat_model_completions(llm, chroma_retriever, request.message)
+    conversation_bot.append(Message(role="bot", content=response_assistant.content))
+    
+    return ChatResponse(
+        response=response_assistant.content,
+        conversation=conversation_bot
+    )
+
+# Voice processing endpoint
+@app.post("/process-voice")
+async def process_voice(audio_file: UploadFile = File(...), dependencies=[Depends(verify_api_key)]):
+# async def process_voice(name: str):
+
+    global conversation_bot
+
+    try:
+        # Read the audio file
+        contents = await audio_file.read()
+        audio_data = BytesIO(contents)
+
+        # Convert audio to wav format for speech recognition
+        with sr.AudioFile(audio_data) as source:
+            audio = recognizer.record(source)
+       
+        # Perform speech recognition
+        text = recognizer.recognize_google(audio)
+        print(text)
+        
+        conversation_bot.append(Message(role="user", content=text))
+        response_assistant = get_chat_model_completions(llm, chroma_retriever, text)
+        conversation_bot.append(Message(role="bot", content=response_assistant.content))
+        # print('response_assistant.content')
+        return {
+            "transcribed_text": text,
+            "response": response_assistant.content
+        }
+    
+    except Exception as e:
+        return {"error": f"Error processing voice input: {str(e)}"}
+
+@app.post("/report")
+async def handle_feedback(
+    request: Report,
+    dependencies=[Depends(verify_api_key)]
+    ):
+    # if x_api_key != VALID_API_KEY:
+    #     raise HTTPException(status_code=403, detail="Invalid API key")
+        
+    # Here you can store the feedback in your database
+    # For example:
+    # await db.store_feedback(message, is_positive)
+    
+    return {"status": "success"}
+
+@app.post("/reset")
+async def reset_conversation():
+    global conversation_bot, llm, chroma_retriever
+    conversation_bot = [{'bot': intro_message}]
+    llm, chroma_retriever = initialize_conversation()
+    return {"status": "conversation reset"}
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

chroma_langchain_db1/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1523f0becd11cbf3a849961b447e745e0c7bde5c7cd9b6faa8e30271974655a
+size 1716224

email_ai.py

@@ -0,0 +1,75 @@
+# -*- coding: utf-8 -*-
+# Import all the required Libraries
+
+import os
+from pathlib import Path
+import pandas as pd
+from langchain_google_genai.chat_models import ChatGoogleGenerativeAI
+from langchain_core.messages import HumanMessage, SystemMessage
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_huggingface import HuggingFaceEmbeddings
+
+from langchain.vectorstores import Chroma
+from langchain.schema.runnable import RunnablePassthrough
+
+# from langchain_openai import ChatOpenAI
+from langchain.prompts import ChatPromptTemplate
+
+import google.generativeai as genai
+import os
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+gemini_api_key = os.getenv("GEMINI_API_KEY")
+
+## load the GROQ And OpenAI API KEY 
+# gemini_api_key = open("gemini_api_key.txt", "r").read().strip()
+
+def initialize_conversation():   
+    
+    llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash-latest", api_key=gemini_api_key)
+    embeddings_model = HuggingFaceEmbeddings()
+    db = Chroma(persist_directory="/Users/daddy/aimlprojects/email_ai/chroma_langchain_db1", embedding_function=embeddings_model)
+    chroma_retriever = db.as_retriever(search_kwargs={"k":50})
+
+    return llm, chroma_retriever
+# initialize_conversation()
+
+# def get_template_prompt(query):
+#     return docs, prompt
+
+intro_message = 'Hello! 😊 How can I assist you today?'
+
+#"""You are a email assistant answering queries on a knowledgebase fo email threads provided in the context:
+template = """Answer the question based only on the following context:
+    {context}
+    provide citations consisting of date of email and from whom the email was sent.
+    If you don't know the answer, just say that you don't know, don't try to make up an answer.
+
+    Question: {question}
+    """
+
+def get_chat_model_completions(llm, chroma_retriever, query):
+
+    # docs = chroma_retriever.get_relevant_documents(query) #, search_kwargs={"k": 3}) 'k' does not work here
+    prompt = ChatPromptTemplate.from_template(template)
+    
+    chain = (
+        {"context": chroma_retriever, "question": RunnablePassthrough()}
+        | prompt
+        | llm
+        #| StrOutputParser()
+    )
+
+    # response = chain.invoke("Generate report on ideas for maintaining Enron's edge?")
+    # response = chain.invoke("what is disccussed in the emails?")
+    response = chain.invoke(query)
+    # response = chain.invoke("What are issues with the email system?")
+    # response = chain.invoke("What were the solutions proposed for email system issues?")
+    # response = chain.invoke("Was the issue with the emal system resolved and when?")
+
+    # print(response.content)
+    return response
+# response=get_chat_model_completions(initialize_conversation(), query)
+# print(response.response)

requirements.txt

@@ -0,0 +1,13 @@
+pandas
+langchain
+langchain-community
+# langchain-openai
+langchain-core
+langchain-google-genai
+langchain-huggingface
+chromadb
+SpeechRecognition
+python-dotenv
+fastapi
+uvicorn[standard]
+python-multipart