Spaces:
Runtime error
Runtime error
File size: 3,905 Bytes
d82e76f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 |
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
import chromadb
chroma_client = chromadb.Client()
collection = chroma_client.create_collection(name="emails")
df.loc[4, 'text']
for i in df.index:
collection.add(
documents = df.loc[i, 'text'],
metadatas = [{"sender": df.loc[i, 'sender'],
"recipient1": df.loc[i, 'recipient1'],
"recipient2": df.loc[i, 'recipient2'],
"recipient3": df.loc[i, 'recipient3'],
"subject": df.loc[i, 'Subject'],
"folder": df.loc[i, 'folder'],
"date": str(df.loc[i, 'date'])
}],
ids = str(i)
)
collection.get(
ids=["140"]
)
results = collection.query(
query_texts = ["this is a document"],
n_results = 2,
include = ['distances', 'metadatas', 'documents']
)
results
from chromadb.utils import embedding_functions
sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name="paraphrase-MiniLM-L3-v2")
collection_minilm = chroma_client.create_collection(name="emails_minilm", embedding_function=sentence_transformer_ef)
for i in df.index:
print(i)
collection_minilm.add(
documents = df.loc[i, 'text'],
metadatas = [{"sender": df.loc[i, 'sender'],
"recipient1": df.loc[i, 'recipient1'],
"recipient2": df.loc[i, 'recipient2'],
"recipient3": df.loc[i, 'recipient3'],
"subject": df.loc[i, 'Subject'],
"folder": df.loc[i, 'folder'],
"date": str(df.loc[i, 'date'])
}],
ids = str(i)
)
results = collection_minilm.query(
query_texts = ["this is a document"],
n_results = 2,
include = ['distances', 'metadatas', 'documents']
)
results
import gradio as gr
def query_chromadb(question,numberOfResults):
results = collection_minilm.query(
n_results = numberOfResults,
)
return results['documents'][0]
iface = gr.Interface(
fn=query_chromadb,
inputs=["text","number"],
outputs="text",
title="Email Dataset Interface",
description="Insert the question or the key word to find the topic correlated in the dataset"
)
iface.launch(share=True)
import ast
def create_output(dictionary, number):
dictionary_ids = str(dictionary['ids'])
dictionary_ids_clean = dictionary_ids.strip("[]")
dictionary_ids_clean = dictionary_ids_clean.replace("'", "")
dictionary_ids_list = dictionary_ids_clean.split(", ")
string_results = "";
for n in range(number):
t = collection_minilm.get(
ids=[dictionary_ids_list[n]]
)
id = str(t["ids"])
doc = str(t["documents"])
metadata = str(t["metadatas"])
dictionary_metadata = ast.literal_eval(metadata.strip("[]"))
string_results_old = string_results
string_temp = """---------------
SUBJECT: """ + dictionary_metadata['subject'] + """"
MESSAGE: """ + "\n" + doc + """
---------------"""
string_results = string_results_old + string_temp
return string_results
def query_chromadb_advanced(question,numberOfResults):
results = collection_minilm.query(
query_texts = question,
n_results = numberOfResults,
)
return create_output(results, numberOfResults)
result_advance = query_chromadb_advanced("bank", 4)
print(result_advance)
iface = gr.Interface(
fn=query_chromadb_advanced,
inputs=["text","number"],
outputs="text",
title="Email Dataset Interface",
description="Insert the question or the key word to find the topic correlated in the dataset"
)
iface.launch(share=True) |