jvelezmagic

# The goal of this file is to provide a FastAPI application for handling
# chat requests amd generation AI-powered responses using conversation chains.
# The application uses the LangChaing library, which includes a chatOpenAI model
# for natural language processing.

# The `StreamingConversationChain` class is responsible for creating and storing
# conversation memories and generating responses. It utilizes the `ChatOpenAI` model
# and a callback handler to stream responses as they're generated.

# The application defines a `ChatRequest` model for handling chat requests,

ninely

"""This is an example of how to use async langchain with fastapi and return a streaming response.
The latest version of Langchain has improved its compatibility with asynchronous FastAPI,
making it easier to implement streaming functionality in your applications.
"""
import asyncio
import os
from typing import AsyncIterable, Awaitable

import uvicorn
from dotenv import load_dotenv

wesleybliss

version: '2'
services:
    myapp:
        build: .
        container_name: "myapp"
        image: debian/latest
        environment:
            - NODE_ENV=development
            - FOO=bar
        volumes:

jlewi

import contrail.AvroHelper
import contrail.spark.SerializableGraphNodeData

val contigFile = contrail.AvroHelper.readAvro(sc,"hdfs://hadoop-nn//tmp/contrail.stages.CompressAndCorrect/part-*.avro")
val datums = contigFile.map(r => new SerializableGraphNodeData(r._1.datum))
val keyedById = datums.map(r => (r.node_id.toString, r))
keyedById.cache()
 
keyedById.lookup(“4fw3YAOX8-lvVjIWgNPGYR3gc5CvsxI”)

viktorklang

// © 2012 Viktor Klang

import akka.dispatch.ExecutionContext
import javax.swing.SwingUtilities
import java.util.concurrent.Executor

//
object SwingExecutionContext {
  implicit val swingExecutionContext: ExecutionContext = ExecutionContext.fromExecutor(new Executor {
    def execute(command: Runnable): Unit = SwingUtilities invokeLater command