mrmaheshrajput

import asyncio
from typing import List, Dict


class AdvancedCodeAssistant(CodeAssistant):
    """Enhanced with parallel tool execution"""
    
    async def search_codebase(self, query: str) -> List[Dict]:
        """Search entire codebase"""
        return self.retrieve_context(query, k=5)

mrmaheshrajput

import os
import anthropic
from pathlib import Path
import tiktoken
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
import faiss
import openai

mrmaheshrajput

import asyncio
import json
import sys
from typing import Optional, List
from contextlib import AsyncExitStack

from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
import ollama
from dotenv import load_dotenv

mrmaheshrajput

"""
MCP Observability Server
A Model Context Protocol server for observability and monitoring systems.
"""

import asyncio
import json
import logging
import random
import time

mrmaheshrajput

import asyncio
import json
from typing import Optional
from contextlib import AsyncExitStack

from dotenv import load_dotenv
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
import ollama

mrmaheshrajput

import datetime

from mcp.server.fastmcp import FastMCP


mcp = FastMCP("mcp-excel-server")

@mcp.tool()
def get_datetime() -> datetime.datetime:
    """Use this tool when the user wants to know today's date."""

mrmaheshrajput

"""
Source: https://github.com/modelcontextprotocol/quickstart-resources/blob/main/weather-server-python/weather.py
"""
rom typing import Any
import httpx
from mcp.server.fastmcp import FastMCP

# Initialize FastMCP server
mcp = FastMCP("weather")

mrmaheshrajput

def build_tsmixer_model(input_shape, forecast_horizon=1, hidden_dim=128, num_layers=2):
    inputs = Input(shape=input_shape)
    x = inputs
    
    # Time mixing layers
    for _ in range(num_layers):
        # Mix across time dimension
        time_mix = tf.keras.layers.Permute((2, 1))(x)  # [batch, features, time]
        time_mix = Dense(input_shape[0], activation='relu')(time_mix)  # Project each feature across time
        time_mix = tf.keras.layers.Permute((2, 1))(time_mix)  # Back to [batch, time, features]

mrmaheshrajput

def build_tft_model(static_shape, past_shape, future_shape, forecast_horizon):
    static_inputs = Input(shape=static_shape)
    past_inputs = Input(shape=past_shape)
    future_inputs = Input(shape=future_shape)  # Known future covariates
    
    static_context = Dense(64, activation='relu')(static_inputs)
    
    past_selected = Dense(past_shape[-1], activation='sigmoid')(tf.concat([past_inputs, static_context], axis=-1))
    past_weighted = past_inputs * past_selected
    

mrmaheshrajput

def create_patches(x, patch_len, stride=1):
    """Convert time series data into patches"""
    patches = []
    for i in range(0, x.shape[1] - patch_len + 1, stride):
        patches.append(x[:, i:i+patch_len, :])
    
    # Stack patches along a new dimension
    patches = tf.stack(patches, axis=1)
    
    # Reshape to [batch, num_patches, patch_len * channels]