Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -29,65 +29,7 @@ directory_path = "ohw_proj_chorma_db"
|
|
29 |
file_path = "ohw_proj_chorma_db.pcl"
|
30 |
# Function to update your retriever
|
31 |
# Function to update your retriever
|
32 |
-
def update_retriever():
|
33 |
-
# Define the directory and file paths
|
34 |
-
directory_path = "ohw_proj_chorma_db"
|
35 |
-
file_path = "ohw_proj_chorma_db.pcl"
|
36 |
|
37 |
-
# Remove the directory and its contents if it exists
|
38 |
-
if os.path.exists(directory_path):
|
39 |
-
shutil.rmtree(directory_path)
|
40 |
-
st.write(f"Directory '{directory_path}' and its contents were removed successfully.")
|
41 |
-
|
42 |
-
# Remove the file if it exists
|
43 |
-
if os.path.exists(file_path):
|
44 |
-
os.remove(file_path)
|
45 |
-
st.write(f"File '{file_path}' was removed successfully.")
|
46 |
-
|
47 |
-
# Run the first Python script
|
48 |
-
try:
|
49 |
-
subprocess.run(["python", "scrape_github.py"], check=True)
|
50 |
-
st.write("GitHub repos downloaded")
|
51 |
-
except subprocess.CalledProcessError as e:
|
52 |
-
st.error(f"Error running scrape_github.py: {e}")
|
53 |
-
|
54 |
-
# Run the second Python script
|
55 |
-
try:
|
56 |
-
subprocess.run(["python", "create_retriever.py"], check=True)
|
57 |
-
st.write("Retriever updated")
|
58 |
-
except subprocess.CalledProcessError as e:
|
59 |
-
st.error(f"Error running create_retriever.py: {e}")
|
60 |
-
|
61 |
-
# Additional logic to update your retriever after running the scripts
|
62 |
-
st.write("Retriever updated!")
|
63 |
-
|
64 |
-
# Function to run the scheduler
|
65 |
-
def run_scheduler():
|
66 |
-
while True:
|
67 |
-
schedule.run_pending()
|
68 |
-
time.sleep(1) # Check every second
|
69 |
-
|
70 |
-
# Schedule the retriever update every 24 hours
|
71 |
-
schedule.every(24).hours.do(update_retriever)
|
72 |
-
|
73 |
-
# Run the scheduler in a separate thread to not block the main thread
|
74 |
-
scheduler_thread = threading.Thread(target=run_scheduler)
|
75 |
-
scheduler_thread.start()
|
76 |
-
if os.path.exists(directory_path):
|
77 |
-
st.write('retriever loaded')
|
78 |
-
else:
|
79 |
-
# try:
|
80 |
-
subprocess.run(["python", "scrape_github.py"], check=True)
|
81 |
-
st.write("GitHub repos downloaded")
|
82 |
-
# except subprocess.CalledProcessError as e:
|
83 |
-
# st.error(f"Error running scrape_github.py: {e}")
|
84 |
-
|
85 |
-
# Run the second Python script
|
86 |
-
# try:
|
87 |
-
subprocess.run(["python", "create_retriever.py"], check=True)
|
88 |
-
st.write("Retriever updated")
|
89 |
-
# except subprocess.CalledProcessError as e:
|
90 |
-
# st.error(f"Error running create_retriever.py: {e}")
|
91 |
def load_from_pickle(filename):
|
92 |
with open(filename, "rb") as file:
|
93 |
return pickle.load(file)
|
|
|
29 |
file_path = "ohw_proj_chorma_db.pcl"
|
30 |
# Function to update your retriever
|
31 |
# Function to update your retriever
|
|
|
|
|
|
|
|
|
32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
def load_from_pickle(filename):
|
34 |
with open(filename, "rb") as file:
|
35 |
return pickle.load(file)
|