hwchase17

from langchain.chains.openai_functions import create_structured_output_runnable
from langchain.chat_models import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langchain.pydantic_v1 import BaseModel, Field
 
class Insight(BaseModel):
    insight: str = Field(description="""insight""")

chat_model = ChatOpenAI(model_name="gpt-4-1106-preview")

mberman84

1. # create new .py file with code found below
2. # install ollama
3. # install model you want “ollama run mistral”
4. conda create -n autogen python=3.11
5. conda activate autogen
6. which python
7. python -m pip install pyautogen
7. ollama run mistral
8. ollama run codellama
9. # open new terminal

hwchase17

from langchain.chat_models import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langchain.schema.output_parser import StrOutputParser
import requests
from bs4 import BeautifulSoup
from langchain.schema.runnable import RunnablePassthrough, RunnableLambda
from langchain.utilities import DuckDuckGoSearchAPIWrapper
import json

RESULTS_PER_QUESTION = 3

Cdaprod

Modified Python Script for Text and Data Processing with Minio and Transformers

This Python script is designed to perform several operations related to text and data processing using Minio for object storage and the Transformers library for text tokenization. The script is organized into various functions, each responsible for a specific task.

Functions:

1. init_logger(log_level: str): Initializes the logging mechanism with a given log level.

2. check_env(): Checks for the existence of required environment variables for Minio client setup.

Cdaprod

import os
import ast
from pydantic import BaseModel, Field
from typing import List

# Pydantic model for function code blocks
class FunctionCodeBlock(BaseModel):
    code: str = Field(..., description="The Python code block")

    class Config:

Cdaprod

Cdaprod

hwchase17

System: Respond to the human as helpfully and accurately as possible. You have access to the following tools:

click_element: Click on an element with the given CSS selector, args: {{'selector': {{'title': 'Selector', 'description': 'CSS selector for the element to click', 'type': 'string'}}}}
navigate_browser: Navigate a browser to the specified URL, args: {{'url': {{'title': 'Url', 'description': 'url to navigate to', 'type': 'string'}}}}
previous_webpage: Navigate back to the previous page in the browser history, args: {{}}
extract_text: Extract all the text on the current webpage, args: {{}}
extract_hyperlinks: Extract all hyperlinks on the current webpage, args: {{'absolute_urls': {{'title': 'Absolute Urls', 'description': 'Return absolute URLs instead of relative URLs', 'default': False, 'type': 'boolean'}}}}
get_elements: Retrieve elements in the current web page matching the given CSS selector, args: {{'selector': {{'title': 'Selector', 'description': "CSS selector, such as '*', 'div', 'p', 'a', #id, 

hwchase17

# STEP 1: Load

# Load documents using LangChain's DocumentLoaders
# This is from https://langchain.readthedocs.io/en/latest/modules/document_loaders/examples/csv.html

from langchain.document_loaders.csv_loader import CSVLoader
loader = CSVLoader(file_path='./example_data/mlb_teams_2012.csv')
data = loader.load()

hwchase17

from langchain.llms.base import LLM
from typing import Optional, List, Mapping, Any
import requests
from langchain.llms.utils import enforce_stop_tokens

class CustomLLM(LLM):

    def __init__(self, url: str):
        self.url = url