File size: 2,925 Bytes
564ce0c
569a26f
564ce0c
 
 
3fec030
 
 
 
 
 
 
 
 
c077e58
 
170f624
c077e58
 
 
170f624
 
 
c077e58
 
 
 
f63dcc6
 
3fec030
170f624
c077e58
 
 
 
170f624
c077e58
170f624
c077e58
 
 
3fec030
 
 
c077e58
3fec030
170f624
bc4e0d2
170f624
 
 
 
 
 
 
d57d7e1
170f624
c077e58
170f624
d57d7e1
170f624
 
 
f66f708
c2b8ffb
309b488
569a26f
c2b8ffb
170f624
 
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
import json
import streamlit as st
from google.oauth2 import service_account
from google.cloud import language_v1

# Function to count entities with 'mid' and '/g/' in their metadata
def count_entities(entities):
    count = 0
    for entity in entities:
        metadata = entity.metadata
        if 'mid' in metadata and '/g/' in metadata['mid']:
            count += 1
    return count

# Sidebar content
st.sidebar.title("About This Tool")
st.sidebar.markdown("This tool leverages Google's NLP technology for entity analysis.")
st.sidebar.markdown("### Step-by-Step Guide")
st.sidebar.markdown("""
1. **Open the Tool**: Navigate to the URL where the tool is hosted.
2. **User Input**: Enter the text you want to analyze.
3. **Analyze**: Click the 'Analyze' button.
4. **View Results**: See the identified entities and their details.
""")

# Header and intro
st.title("Google Cloud NLP Entity Analyzer")
st.write("This tool analyzes text to identify entities such as people, locations, organizations, and events")
st.write("Entity salience scores are always relative to the analysed text. In natural language processing, a salience score is always a prediction of what a human would consider to be the most important entities in the same text. A number of textual features contribute to the salience score.")

def sample_analyze_entities(text_content):
    service_account_info = json.loads(st.secrets["google_nlp"])
    credentials = service_account.Credentials.from_service_account_info(
        service_account_info, scopes=["https://www.googleapis.com/auth/cloud-platform"]
    )
    
    client = language_v1.LanguageServiceClient(credentials=credentials)
    document = {"content": text_content, "type_": language_v1.Document.Type.PLAIN_TEXT, "language": "en"}
    encoding_type = language_v1.EncodingType.UTF8

    response = client.analyze_entities(request={"document": document, "encoding_type": encoding_type})
    
    # Count the entities with 'mid' and '/g/' in their metadata
    entity_count = count_entities(response.entities)

    st.write(f"We found {len(response.entities)} entities - {entity_count} meet your criteria")
    st.write("---")

    for i, entity in enumerate(response.entities):
        st.write(f"Entity {i+1} of {len(response.entities)}")
        st.write(f"Name: {entity.name}")
        st.write(f"Type: {language_v1.Entity.Type(entity.type_).name}")
        st.write(f"Salience Score: {entity.salience}")
        
        if entity.metadata:
            st.write("Metadata:")
            st.write(entity.metadata)

        if entity.mentions:
            st.write("Mentions:")
            st.write(', '.join([mention.text.content for mention in entity.mentions]))
        
        st.write("---")

# User input for text analysis
user_input = st.text_area("Enter text to analyze", max_chars=5000)

if st.button("Analyze"):
    if user_input:
        sample_analyze_entities(user_input)