Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -69,14 +69,12 @@ def download_gitlab_project_by_version():
|
|
69 |
response = requests.get(url, stream=True)
|
70 |
archive_bytes = io.BytesIO(response.content)
|
71 |
|
72 |
-
print(archive_bytes)
|
73 |
|
74 |
if response.status_code == 200:
|
75 |
# Extract filename from content-disposition header
|
76 |
content_disposition = response.headers.get("content-disposition")
|
77 |
if content_disposition and "filename=" in content_disposition:
|
78 |
filename = content_disposition.split("filename=")[-1].strip('"')
|
79 |
-
print(filename)
|
80 |
|
81 |
|
82 |
# test
|
@@ -150,9 +148,7 @@ def download_gitlab_repo():
|
|
150 |
def get_all_files_in_folder(temp_dir, folder_path):
|
151 |
|
152 |
all_files = []
|
153 |
-
print("inner method of get all files in folder")
|
154 |
target_dir = os.path.join(temp_dir, folder_path)
|
155 |
-
print(target_dir)
|
156 |
|
157 |
for root, dirs, files in os.walk(target_dir):
|
158 |
print(f"Files in current directory ({root}): {files}")
|
@@ -171,11 +167,8 @@ def process_directory(directory, folder_paths, file_paths):
|
|
171 |
all_texts = []
|
172 |
file_references = []
|
173 |
|
174 |
-
zip_filename = next((file for file in os.listdir(directory) if file.endswith('.zip')), None)
|
175 |
-
|
176 |
-
zip_file_path = os.path.join(directory, zip_filename) # zip_file_path: data/kadi-apy-master-2a244f1af1483b48f8f9c0d99ce2744a0950c834.zip
|
177 |
-
print("zip_file_path:", zip_file_path)
|
178 |
-
# zip_file_path = os.listdir(directory) if file.endswith('.zip')
|
179 |
|
180 |
with tempfile.TemporaryDirectory() as tmpdirname:
|
181 |
# Unzip the file into the temporary directory
|
@@ -183,11 +176,11 @@ def process_directory(directory, folder_paths, file_paths):
|
|
183 |
zip_ref.extractall(tmpdirname)
|
184 |
|
185 |
files = []
|
186 |
-
print("tmpdirname: " , tmpdirname)
|
187 |
unzipped_root = os.listdir(tmpdirname)
|
188 |
-
print("unzipped_root ", unzipped_root)
|
189 |
|
190 |
-
tmpsubdirpath= os.path.join(tmpdirname, unzipped_root[0])
|
191 |
print("tempsubdirpath: ", tmpsubdirpath)
|
192 |
|
193 |
if folder_paths:
|
@@ -216,7 +209,6 @@ def process_directory(directory, folder_paths, file_paths):
|
|
216 |
relative_path = os.path.relpath(file_path, tmpsubdirpath)
|
217 |
print("Relative Filepaths brother:", relative_path)
|
218 |
file_references.append(relative_path)
|
219 |
-
print("AAAAAAAAAAAAAAAAAAAAAAAAAAAAA: ", relative_path)
|
220 |
|
221 |
return all_texts, file_references
|
222 |
|
@@ -312,6 +304,7 @@ def format_kadi_apy_library_context(docs):
|
|
312 |
type_info = doc.metadata.get("type", "Unknown Type")
|
313 |
source_info = doc.metadata.get("source", "Unknown Type")
|
314 |
# Format metadata and document content
|
|
|
315 |
formatted_doc = f"# source: {source_info}\n# class: {class_info}\n# type: {type_info}\n{doc.page_content}\n\n\n"
|
316 |
doc_context.append(formatted_doc)
|
317 |
|
@@ -342,9 +335,9 @@ def rag_workflow(query):
|
|
342 |
kadi_apy_library_docs = retrieve_within_kadiApy_library (vector_store, query, k = 10)
|
343 |
|
344 |
doc_context = format_kadi_api_doc_context(kadi_apy_docs)
|
345 |
-
print(doc_context)
|
346 |
code_context = format_kadi_apy_library_context(kadi_apy_library_docs)
|
347 |
-
print("AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA:",code_context)
|
348 |
|
349 |
|
350 |
|
|
|
69 |
response = requests.get(url, stream=True)
|
70 |
archive_bytes = io.BytesIO(response.content)
|
71 |
|
|
|
72 |
|
73 |
if response.status_code == 200:
|
74 |
# Extract filename from content-disposition header
|
75 |
content_disposition = response.headers.get("content-disposition")
|
76 |
if content_disposition and "filename=" in content_disposition:
|
77 |
filename = content_disposition.split("filename=")[-1].strip('"')
|
|
|
78 |
|
79 |
|
80 |
# test
|
|
|
148 |
def get_all_files_in_folder(temp_dir, folder_path):
|
149 |
|
150 |
all_files = []
|
|
|
151 |
target_dir = os.path.join(temp_dir, folder_path)
|
|
|
152 |
|
153 |
for root, dirs, files in os.walk(target_dir):
|
154 |
print(f"Files in current directory ({root}): {files}")
|
|
|
167 |
all_texts = []
|
168 |
file_references = []
|
169 |
|
170 |
+
zip_filename = next((file for file in os.listdir(directory) if file.endswith('.zip')), None)
|
171 |
+
zip_file_path = os.path.join(directory, zip_filename)
|
|
|
|
|
|
|
172 |
|
173 |
with tempfile.TemporaryDirectory() as tmpdirname:
|
174 |
# Unzip the file into the temporary directory
|
|
|
176 |
zip_ref.extractall(tmpdirname)
|
177 |
|
178 |
files = []
|
179 |
+
print("tmpdirname: " , tmpdirname)
|
180 |
unzipped_root = os.listdir(tmpdirname)
|
181 |
+
print("unzipped_root ", unzipped_root)
|
182 |
|
183 |
+
tmpsubdirpath= os.path.join(tmpdirname, unzipped_root[0])
|
184 |
print("tempsubdirpath: ", tmpsubdirpath)
|
185 |
|
186 |
if folder_paths:
|
|
|
209 |
relative_path = os.path.relpath(file_path, tmpsubdirpath)
|
210 |
print("Relative Filepaths brother:", relative_path)
|
211 |
file_references.append(relative_path)
|
|
|
212 |
|
213 |
return all_texts, file_references
|
214 |
|
|
|
304 |
type_info = doc.metadata.get("type", "Unknown Type")
|
305 |
source_info = doc.metadata.get("source", "Unknown Type")
|
306 |
# Format metadata and document content
|
307 |
+
print("YYYYYYYEEEEEEEEEEEEEEE222222222222222222222222222222:}\n\n", doc.page_content)
|
308 |
formatted_doc = f"# source: {source_info}\n# class: {class_info}\n# type: {type_info}\n{doc.page_content}\n\n\n"
|
309 |
doc_context.append(formatted_doc)
|
310 |
|
|
|
335 |
kadi_apy_library_docs = retrieve_within_kadiApy_library (vector_store, query, k = 10)
|
336 |
|
337 |
doc_context = format_kadi_api_doc_context(kadi_apy_docs)
|
338 |
+
#print(doc_context)
|
339 |
code_context = format_kadi_apy_library_context(kadi_apy_library_docs)
|
340 |
+
#print("AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA:",code_context)
|
341 |
|
342 |
|
343 |
|