janduplessis883

# Healthcare Feedback Dataset for SetFit
# 90 examples (15 per class) - suitable for few-shot learning

# Optimized label names for ML
LABEL_MAPPING = {
    0: "access_availability",
    1: "information_provision", 
    2: "privacy_confidentiality",
    3: "continuity_care",
    4: "clinical_communication",

janduplessis883

import spacy
from spacy.matcher import Matcher
import math
import pandas as pd

# ============================================================================
# Installation Requirements:
# 1. pip install spacy
# 2. python -m spacy download en_core_web_sm
# ============================================================================

janduplessis883

import math
import os
import re
from nltk import pos_tag, word_tokenize
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import pairwise_distances
import warnings
warnings.filterwarnings("ignore")

import matplotlib.pyplot as plt

janduplessis883

import toml
from crewai_tools import BaseTool
from typing import ClassVar, Union, Dict, Any, List
import requests

# Load the TOML file
with open("notioncrew/config_secrets.toml", "r") as f:
    config_secrets = toml.load(f)

# Load environment variables from streamlit secrets

janduplessis883

janduplessis883

import spacy
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from langchain.tools import BaseTool
from typing import Optional, Union, List
from langchain.callbacks.manager import CallbackManagerForToolRun, AsyncCallbackManagerForToolRun

class DataPreprocessingTool(BaseTool):
    name = "DataPreprocessingTool"
    description = "A tool for preprocessing and structuring unstructured data."

janduplessis883

In this walkthrough we will see how to use Pinecone for semantic search.

janduplessis883

import pandas as pd
from langchain.schema import Document
from langchain_community.embeddings import OllamaEmbeddings
from langchain_community.vectorstores import Chroma
from tqdm import tqdm

janduplessis883

janduplessis883