davidmezzetti
commited on
Commit
•
e43b653
1
Parent(s):
09a5aa4
Update app.py
Browse files
app.py
CHANGED
@@ -13,7 +13,7 @@ import pandas as pd
|
|
13 |
import streamlit as st
|
14 |
|
15 |
from txtai.embeddings import Documents, Embeddings
|
16 |
-
from txtai.pipeline import Segmentation, Summary, Tabular,
|
17 |
from txtai.workflow import ServiceTask, Task, UrlTask, Workflow
|
18 |
|
19 |
|
@@ -94,11 +94,8 @@ class Application:
|
|
94 |
options["minlength"] = self.number("Min length")
|
95 |
options["maxlength"] = self.number("Max length")
|
96 |
|
97 |
-
elif component
|
98 |
-
|
99 |
-
st.sidebar.markdown("**Segment** \n*Split text into semantic units*")
|
100 |
-
else:
|
101 |
-
st.sidebar.markdown("**Textractor** \n*Extract text from documents*")
|
102 |
|
103 |
options["sentences"] = st.sidebar.checkbox("Split sentences")
|
104 |
options["lines"] = st.sidebar.checkbox("Split lines")
|
@@ -172,10 +169,6 @@ class Application:
|
|
172 |
self.pipelines[wtype] = Tabular(**self.components["tabular"])
|
173 |
tasks.append(Task(self.pipelines["tabular"]))
|
174 |
|
175 |
-
elif wtype == "textract":
|
176 |
-
self.pipelines[wtype] = Textractor(**self.components["textract"])
|
177 |
-
tasks.append(UrlTask(self.pipelines["textract"]))
|
178 |
-
|
179 |
elif wtype == "transcribe":
|
180 |
self.pipelines[wtype] = Transcription(component.pop("path"))
|
181 |
tasks.append(UrlTask(self.pipelines["transcribe"], r".\.wav$"))
|
@@ -223,10 +216,6 @@ class Application:
|
|
223 |
data["tabular"] = component
|
224 |
tasks.append({"action": "tabular"})
|
225 |
|
226 |
-
elif wtype == "textract":
|
227 |
-
data["textractor"] = component
|
228 |
-
tasks.append({"action": "textractor", "task": "url"})
|
229 |
-
|
230 |
elif wtype == "transcribe":
|
231 |
data["transcription"] = {"path": component.pop("path")}
|
232 |
tasks.append({"action": "transcription", "task": "url"})
|
@@ -341,7 +330,7 @@ class Application:
|
|
341 |
st.sidebar.markdown("# Workflow builder \n*Build and apply workflows to data* ")
|
342 |
|
343 |
# Get selected components
|
344 |
-
components = ["embeddings", "segment", "service", "summary", "tabular", "
|
345 |
selected = st.sidebar.multiselect("Select components", components)
|
346 |
|
347 |
# Get selected options
|
|
|
13 |
import streamlit as st
|
14 |
|
15 |
from txtai.embeddings import Documents, Embeddings
|
16 |
+
from txtai.pipeline import Segmentation, Summary, Tabular, Transcription, Translation
|
17 |
from txtai.workflow import ServiceTask, Task, UrlTask, Workflow
|
18 |
|
19 |
|
|
|
94 |
options["minlength"] = self.number("Min length")
|
95 |
options["maxlength"] = self.number("Max length")
|
96 |
|
97 |
+
elif component == "segment:"
|
98 |
+
st.sidebar.markdown("**Segment** \n*Split text into semantic units*")
|
|
|
|
|
|
|
99 |
|
100 |
options["sentences"] = st.sidebar.checkbox("Split sentences")
|
101 |
options["lines"] = st.sidebar.checkbox("Split lines")
|
|
|
169 |
self.pipelines[wtype] = Tabular(**self.components["tabular"])
|
170 |
tasks.append(Task(self.pipelines["tabular"]))
|
171 |
|
|
|
|
|
|
|
|
|
172 |
elif wtype == "transcribe":
|
173 |
self.pipelines[wtype] = Transcription(component.pop("path"))
|
174 |
tasks.append(UrlTask(self.pipelines["transcribe"], r".\.wav$"))
|
|
|
216 |
data["tabular"] = component
|
217 |
tasks.append({"action": "tabular"})
|
218 |
|
|
|
|
|
|
|
|
|
219 |
elif wtype == "transcribe":
|
220 |
data["transcription"] = {"path": component.pop("path")}
|
221 |
tasks.append({"action": "transcription", "task": "url"})
|
|
|
330 |
st.sidebar.markdown("# Workflow builder \n*Build and apply workflows to data* ")
|
331 |
|
332 |
# Get selected components
|
333 |
+
components = ["embeddings", "segment", "service", "summary", "tabular", "transcribe", "translate"]
|
334 |
selected = st.sidebar.multiselect("Select components", components)
|
335 |
|
336 |
# Get selected options
|