udpated67

Author: Drago-03

.env

@@ -6,6 +6,7 @@ BLOOMBERG_API_KEY=your_bloomberg_key
 COURTLISTENER_API_KEY=your_courtlistener_key
 EDUCATION_API_KEY=your_nlp_api_key
 GEMINI_API_KEY=AIzaSyCtRbYSCI3RRqXJV3xRRUCmCrZpYfXMsKQ
+OPENAI_API_KEY=your_openai_api_key_here
 DEEPCHEM_API_KEY=your_deepchem_key
 SUPPORT_API_KEY=your_support_key
 Pinecone_API_KEY=pcsk_3rGYF6_2Gbi7QfoUxxHXD5Wps3PifJFrEUecs2FuUQtthGGbYaWWiyoxhxGrJHcYHrUP2m

.gitignore

@@ -38,3 +38,10 @@ backend/venv/
 backend/.venv/
 **/torch/lib/
 **/site-packages/torch/lib/
+
+dotenv.local
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+

CODE_OF_CONDUCT.md

@@ -41,21 +41,25 @@ Instances of abusive, harassing, or otherwise unacceptable behavior may be repor
 Project maintainers will follow these Community Impact Guidelines in determining the consequences for any action they deem in violation of this Code of Conduct:
 
 ### 1. Correction
+
 **Impact**: Use of inappropriate language or other behavior deemed unprofessional.
 **Consequence**: A private, written warning, providing clarity around the nature of the violation.
 
 ### 2. Warning
+
 **Impact**: A violation through a single incident or series of actions.
 **Consequence**: A warning with consequences for continued behavior.
 
 ### 3. Temporary Ban
+
 **Impact**: A serious violation of community standards.
 **Consequence**: A temporary ban from any sort of interaction or public communication with the community.
 
 ### 4. Permanent Ban
+
 **Impact**: Demonstrating a pattern of violation of community standards.
 **Consequence**: A permanent ban from any sort of public interaction within the community.
 
 ## Attribution
 
-This Code of Conduct is adapted from the [Contributor Covenant](https://www.contributor-covenant.org/), version 2.1, available at [https://www.contributor-covenant.org/version/2/1/code_of_conduct.html](https://www.contributor-covenant.org/version/2/1/code_of_conduct.html). 
+This Code of Conduct is adapted from the [Contributor Covenant](https://www.contributor-covenant.org/), version 2.1, available at [https://www.contributor-covenant.org/version/2/1/code_of_conduct.html](https://www.contributor-covenant.org/version/2/1/code_of_conduct.html).

Dockerfile

@@ -4,20 +4,32 @@ FROM python:3.11-slim
 # Set working directory
 WORKDIR /app
 
-# Install system dependencies
+# Install system dependencies and Bloomberg API requirements
 RUN apt-get update && apt-get install -y \
     build-essential \
+    libxml2-dev \
+    libxslt-dev \
+    python3-dev \
     && rm -rf /var/lib/apt/lists/*
 
 # Copy requirements file
 COPY requirements.txt .
 
-# Install Python dependencies
-RUN pip install --no-cache-dir -r requirements.txt
+# Install Python dependencies including Bloomberg API
+RUN pip install --no-cache-dir -r requirements.txt && \
+    pip install --no-cache-dir --index-url=https://blpapi.bloomberg.com/repository/releases/python/simple/ blpapi
 
 # Copy source code
 COPY . .
 
+# Set Bloomberg environment variables
+ENV BLPAPI_ROOT=/app/bloomberg
+ENV PATH="${PATH}:${BLPAPI_ROOT}/bin"
+ENV LD_LIBRARY_PATH="${LD_LIBRARY_PATH}:${BLPAPI_ROOT}/lib"
+
+# Create directory for Bloomberg API logs
+RUN mkdir -p /app/bloomberg/logs
+
 # Expose port
 EXPOSE 8000
 

README.md

@@ -1,4 +1,4 @@
-# M.A.D.H.A.V.A.
+# M.A.D.H.A.V.A
 
 <div align="center">
   <img src="client/src/logo.png" alt="M.A.D.H.A.V.A. Logo" width="300" />
@@ -27,12 +27,14 @@ M.A.D.H.A.V.A. is an advanced AI-powered assistant that provides intelligent ana
 ## Getting Started
 
 1. Clone the repository
+
 ```bash
 git clone https://github.com/yourusername/M.A.D.H.A.V.A..git
 cd M.A.D.H.A.V.A.
 ```
 
 2. Install dependencies
+
 ```bash
 # Backend
 python -m venv venv
@@ -45,6 +47,7 @@ npm install
 ```
 
 3. Start the application
+
 ```bash
 # Backend
 python main.py
@@ -57,6 +60,7 @@ npm start
 ## Architecture
 
 The application follows a modern microservices architecture:
+
 - Frontend: React.js with modern UI/UX
 - Backend: FastAPI with Python
 - Database: MongoDB, Redis, Vector Store

SECURITY.md

@@ -89,4 +89,4 @@ Our project implements several security measures:
 
 ## Acknowledgments
 
-We would like to thank all security researchers and contributors who help keep our project secure. Your efforts are greatly appreciated. 
+We would like to thank all security researchers and contributors who help keep our project secure. Your efforts are greatly appreciated.

backend/Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 8000
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"] 

backend/llm.py

@@ -1,10 +1,33 @@
-import requests
+import os
 from typing import List, Dict, Any, Optional
+from dotenv import load_dotenv
+import google.generativeai as genai
+from openai import OpenAI
+import json
+
+load_dotenv()
 
 class LLM:
-    def __init__(self, model: str = "mistral"):
+    def __init__(self, model: str = "gemini"):
         self.model = model
-        self.api_url = "http://localhost:11434/api/generate"
+        self.gemini_api_key = os.getenv('GEMINI_API_KEY')
+        self.openai_api_key = os.getenv('OPENAI_API_KEY')
+        
+        # Initialize Gemini if API key is available
+        if self.gemini_api_key:
+            genai.configure(api_key=self.gemini_api_key)
+            self.gemini_model = genai.GenerativeModel('gemini-pro')
+        else:
+            self.gemini_model = None
+            
+        # Initialize OpenAI if API key is available
+        if self.openai_api_key:
+            self.openai_client = OpenAI(api_key=self.openai_api_key)
+        else:
+            self.openai_client = None
+            
+        if not self.gemini_model and not self.openai_client:
+            raise ValueError("No LLM API keys configured. Please set either GEMINI_API_KEY or OPENAI_API_KEY in your environment.")
 
     async def generate_response(self, query: str, context: List[Dict[str, Any]], domain: str = "finance") -> str:
         # Format context for the prompt
@@ -20,19 +43,10 @@ async def generate_response(self, query: str, context: List[Dict[str, Any]], dom
             "legal": "You are a legal analysis AI assistant specializing in contract analysis, regulatory compliance, and risk assessment.",
             "news": "You are a fact-checking AI assistant that cross-references claims with reliable sources and provides journalistic analysis.",
             "ecommerce": "You are an AI-powered product advisor specialized in product comparisons and personalized recommendations.",
-            "education": "You are an educational AI tutor specializing in explaining complex concepts using proven teaching methods.",
-            "code": "You are a code assistant AI specializing in providing implementation examples, debugging help, and best practices.",
-            "hr": "You are an HR automation AI specializing in candidate assessment, policy analysis, and recruitment optimization.",
-            "travel": "You are a travel planning AI specializing in creating personalized itineraries and travel recommendations.",
-            "science": "You are a scientific research AI specializing in analyzing research papers and summarizing scientific findings.",
-            "cybersecurity": "You are a cybersecurity AI specializing in threat intelligence analysis and security recommendations.",
-            "knowledge": "You are a knowledge management AI specializing in analyzing internal documents and extracting key insights.",
-            "realestate": "You are a real estate analysis AI specializing in market trends, property insights, and investment opportunities.",
-            "fitness": "You are a fitness and health coaching AI specializing in personalized exercise and nutrition recommendations.",
-            "support": "You are a customer support AI specializing in providing accurate technical assistance and troubleshooting guidance."
+            "education": "You are an educational AI tutor specializing in explaining complex concepts using proven teaching methods."
         }
 
-        prompt = f"""{domain_prompts.get(domain, domain_prompts["knowledge"])} Use the following context to answer the question. 
+        prompt = f"""{domain_prompts.get(domain, domain_prompts["finance"])} Use the following context to answer the question. 
 If you cannot answer the question based on the context, say so.
 
 Context:
@@ -42,19 +56,34 @@ async def generate_response(self, query: str, context: List[Dict[str, Any]], dom
 
 Answer:"""
 
-        response = requests.post(
-            self.api_url,
-            json={
-                "model": self.model,
-                "prompt": prompt,
-                "stream": False
-            }
-        )
+        # Try Gemini first if available
+        if self.gemini_model:
+            try:
+                response = self.gemini_model.generate_content(prompt)
+                return response.text
+            except Exception as e:
+                print(f"Gemini API error: {e}")
+                if not self.openai_client:  # If no fallback available
+                    raise e
 
-        if response.status_code != 200:
-            raise Exception("Failed to get response from LLM")
-            
-        return response.json()["response"]
+        # Fallback to OpenAI if Gemini fails or is not available
+        if self.openai_client:
+            try:
+                response = self.openai_client.chat.completions.create(
+                    model="gpt-3.5-turbo",
+                    messages=[
+                        {"role": "system", "content": domain_prompts.get(domain, domain_prompts["finance"])},
+                        {"role": "user", "content": prompt}
+                    ],
+                    temperature=0.7,
+                    max_tokens=1000
+                )
+                return response.choices[0].message.content
+            except Exception as e:
+                print(f"OpenAI API error: {e}")
+                raise e
+        
+        raise Exception("No LLM services available")
 
     async def summarize(self, text: str, instruction: str) -> str:
         """Summarize text with specific instructions."""
@@ -65,19 +94,34 @@ async def summarize(self, text: str, instruction: str) -> str:
 
 Summary:"""
 
-        response = requests.post(
-            self.api_url,
-            json={
-                "model": self.model,
-                "prompt": prompt,
-                "stream": False
-            }
-        )
+        # Try Gemini first if available
+        if self.gemini_model:
+            try:
+                response = self.gemini_model.generate_content(prompt)
+                return response.text
+            except Exception as e:
+                print(f"Gemini API error: {e}")
+                if not self.openai_client:
+                    raise e
 
-        if response.status_code != 200:
-            raise Exception("Failed to get summary from LLM")
-            
-        return response.json()["response"]
+        # Fallback to OpenAI
+        if self.openai_client:
+            try:
+                response = self.openai_client.chat.completions.create(
+                    model="gpt-3.5-turbo",
+                    messages=[
+                        {"role": "system", "content": "You are a helpful AI assistant that summarizes text based on given instructions."},
+                        {"role": "user", "content": prompt}
+                    ],
+                    temperature=0.7,
+                    max_tokens=500
+                )
+                return response.choices[0].message.content
+            except Exception as e:
+                print(f"OpenAI API error: {e}")
+                raise e
+        
+        raise Exception("No LLM services available")
 
     async def fact_check(self, claim: str, sources: List[str]) -> Dict[str, Any]:
         """Fact check a claim against provided sources."""

backend/main.py

@@ -7,19 +7,31 @@
 import uvicorn
 import json
 import os
+from dotenv import load_dotenv
 
 from embeddings import EmbeddingStore
 from llm import LLM
 from metrics_extractor import MetricsExtractor
 from alert_manager import AlertManager
 from domain_processors import DomainProcessor
 
-app = FastAPI(title="ANAND - Advanced Neural Assistance for Numerous Domain Intelligence")
+# Load environment variables
+load_dotenv()
 
-# Configure CORS
+app = FastAPI(
+    title="M.A.D.H.A.V.A.",
+    description="Multi-domain Analytical Data Harvesting & Automated Verification Assistant",
+    version="1.0.0"
+)
+
+# Configure CORS with more specific settings
 app.add_middleware(
     CORSMiddleware,
-    allow_origins=["http://localhost:5173"],
+    allow_origins=[
+        "http://localhost:5173",
+        "http://127.0.0.1:5173",
+        "http://0.0.0.0:5173"
+    ],
     allow_credentials=True,
     allow_methods=["*"],
     allow_headers=["*"],
@@ -155,19 +167,15 @@ async def process_documents():
         except Exception as e:
             print(f"Error processing documents for domain {domain}: {str(e)}")
 
-if __name__ == "__main__":
-    import asyncio
-
-    async def main():
-        for domain in embedding_stores.keys():
-            os.makedirs(f"data/{domain}", exist_ok=True)
+@app.get("/health")
+async def health_check():
+    return {"status": "healthy"}
 
-        await asyncio.gather(
-            alert_manager.start_websocket_server(),
-            process_documents()
-        )
-
-    loop = asyncio.get_event_loop()
-    loop.create_task(main())
-
-    uvicorn.run(app, host="0.0.0.0", port=8000)
+if __name__ == "__main__":
+    port = int(os.getenv('PORT', 5000))
+    uvicorn.run(
+        app,
+        host="0.0.0.0",  # Allow connections from all interfaces
+        port=port,
+        reload=True
+    )