Spaces:
Running
on
Zero
Running
on
Zero
Update app.py
Browse files
app.py
CHANGED
@@ -166,8 +166,9 @@ def extract_data_from_pdfs(
|
|
166 |
all_text += extract_only_text(reader) + "\n\n"
|
167 |
|
168 |
if include_images == "Include Images":
|
169 |
-
|
170 |
-
|
|
|
171 |
|
172 |
progress(
|
173 |
0.6, "Generating image descriptions and inserting everything into vectorDB"
|
@@ -269,12 +270,6 @@ def check_validity_and_llm(session_states):
|
|
269 |
raise gr.Error("Please extract data first")
|
270 |
|
271 |
|
272 |
-
def get_stats(vectordb):
|
273 |
-
eles = vectordb.get()
|
274 |
-
# words =
|
275 |
-
text_data = [f"Chunks: {len(eles)}", "HIII"]
|
276 |
-
return "\n".join(text_data), "", ""
|
277 |
-
|
278 |
|
279 |
with gr.Blocks(css=CSS, theme=gr.themes.Soft(text_size=sizes.text_md)) as demo:
|
280 |
vectordb = gr.State()
|
|
|
166 |
all_text += extract_only_text(reader) + "\n\n"
|
167 |
|
168 |
if include_images == "Include Images":
|
169 |
+
imgs = extract_images([doc])
|
170 |
+
images.extend(imgs)
|
171 |
+
img_docs.extend([doc.split("/")[-1] for _ in range(len(imgs))])
|
172 |
|
173 |
progress(
|
174 |
0.6, "Generating image descriptions and inserting everything into vectorDB"
|
|
|
270 |
raise gr.Error("Please extract data first")
|
271 |
|
272 |
|
|
|
|
|
|
|
|
|
|
|
|
|
273 |
|
274 |
with gr.Blocks(css=CSS, theme=gr.themes.Soft(text_size=sizes.text_md)) as demo:
|
275 |
vectordb = gr.State()
|