- app.py +68 -4
- repo_explorer.py +50 -52
app.py
CHANGED
@@ -39,10 +39,37 @@ def write_repos_to_csv(repo_ids: List[str]) -> None:
|
|
39 |
except Exception as e:
|
40 |
logger.error(f"Error writing to CSV: {e}")
|
41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
def read_csv_to_dataframe() -> pd.DataFrame:
|
43 |
-
"""Reads the CSV file into a pandas DataFrame."""
|
44 |
try:
|
45 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
except FileNotFoundError:
|
47 |
return pd.DataFrame(columns=["repo id", "strength", "weaknesses", "speciality", "relevance rating"])
|
48 |
except Exception as e:
|
@@ -225,6 +252,38 @@ def create_ui() -> gr.Blocks:
|
|
225 |
background: linear-gradient(45deg, #667eea, #764ba2);
|
226 |
border-radius: 4px;
|
227 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
228 |
"""
|
229 |
|
230 |
with gr.Blocks(
|
@@ -324,7 +383,11 @@ def create_ui() -> gr.Blocks:
|
|
324 |
df_output = gr.Dataframe(
|
325 |
headers=["Repository", "Strengths", "Weaknesses", "Speciality", "Relevance"],
|
326 |
wrap=True,
|
327 |
-
interactive=False
|
|
|
|
|
|
|
|
|
328 |
)
|
329 |
|
330 |
# --- Chatbot Tab ---
|
@@ -370,7 +433,8 @@ def create_ui() -> gr.Blocks:
|
|
370 |
)
|
371 |
|
372 |
# --- Repo Explorer Tab ---
|
373 |
-
|
|
|
374 |
|
375 |
# --- Footer ---
|
376 |
gr.Markdown(
|
|
|
39 |
except Exception as e:
|
40 |
logger.error(f"Error writing to CSV: {e}")
|
41 |
|
42 |
+
def format_text_for_dataframe(text: str, max_length: int = 200) -> str:
|
43 |
+
"""Format text for better display in dataframe by truncating and cleaning."""
|
44 |
+
if not text or pd.isna(text):
|
45 |
+
return ""
|
46 |
+
|
47 |
+
# Clean the text
|
48 |
+
text = str(text).strip()
|
49 |
+
|
50 |
+
# Remove excessive whitespace and newlines
|
51 |
+
text = re.sub(r'\s+', ' ', text)
|
52 |
+
|
53 |
+
# Truncate if too long
|
54 |
+
if len(text) > max_length:
|
55 |
+
text = text[:max_length-3] + "..."
|
56 |
+
|
57 |
+
return text
|
58 |
+
|
59 |
def read_csv_to_dataframe() -> pd.DataFrame:
|
60 |
+
"""Reads the CSV file into a pandas DataFrame with formatted text for display."""
|
61 |
try:
|
62 |
+
df = pd.read_csv(CSV_FILE, dtype=str).fillna('')
|
63 |
+
|
64 |
+
# Format text columns for better display
|
65 |
+
if not df.empty:
|
66 |
+
df['strength'] = df['strength'].apply(lambda x: format_text_for_dataframe(x, 180))
|
67 |
+
df['weaknesses'] = df['weaknesses'].apply(lambda x: format_text_for_dataframe(x, 180))
|
68 |
+
df['speciality'] = df['speciality'].apply(lambda x: format_text_for_dataframe(x, 150))
|
69 |
+
df['repo id'] = df['repo id'].apply(lambda x: format_text_for_dataframe(x, 50))
|
70 |
+
# Keep relevance rating as is since it should be short
|
71 |
+
|
72 |
+
return df
|
73 |
except FileNotFoundError:
|
74 |
return pd.DataFrame(columns=["repo id", "strength", "weaknesses", "speciality", "relevance rating"])
|
75 |
except Exception as e:
|
|
|
252 |
background: linear-gradient(45deg, #667eea, #764ba2);
|
253 |
border-radius: 4px;
|
254 |
}
|
255 |
+
|
256 |
+
/* Improved dataframe styling */
|
257 |
+
.gr-dataframe {
|
258 |
+
max-height: 400px;
|
259 |
+
overflow-y: auto;
|
260 |
+
}
|
261 |
+
|
262 |
+
.gr-dataframe table {
|
263 |
+
table-layout: fixed;
|
264 |
+
width: 100%;
|
265 |
+
}
|
266 |
+
|
267 |
+
.gr-dataframe th,
|
268 |
+
.gr-dataframe td {
|
269 |
+
padding: 8px 12px;
|
270 |
+
vertical-align: top;
|
271 |
+
word-wrap: break-word;
|
272 |
+
overflow-wrap: break-word;
|
273 |
+
max-height: 100px;
|
274 |
+
overflow-y: auto;
|
275 |
+
}
|
276 |
+
|
277 |
+
.gr-dataframe th:nth-child(1),
|
278 |
+
.gr-dataframe td:nth-child(1) { width: 15%; }
|
279 |
+
.gr-dataframe th:nth-child(2),
|
280 |
+
.gr-dataframe td:nth-child(2) { width: 25%; }
|
281 |
+
.gr-dataframe th:nth-child(3),
|
282 |
+
.gr-dataframe td:nth-child(3) { width: 25%; }
|
283 |
+
.gr-dataframe th:nth-child(4),
|
284 |
+
.gr-dataframe td:nth-child(4) { width: 20%; }
|
285 |
+
.gr-dataframe th:nth-child(5),
|
286 |
+
.gr-dataframe td:nth-child(5) { width: 15%; }
|
287 |
"""
|
288 |
|
289 |
with gr.Blocks(
|
|
|
383 |
df_output = gr.Dataframe(
|
384 |
headers=["Repository", "Strengths", "Weaknesses", "Speciality", "Relevance"],
|
385 |
wrap=True,
|
386 |
+
interactive=False,
|
387 |
+
max_rows=10,
|
388 |
+
height=400,
|
389 |
+
column_widths=["15%", "25%", "25%", "20%", "15%"],
|
390 |
+
datatype=["str", "str", "str", "str", "str"]
|
391 |
)
|
392 |
|
393 |
# --- Chatbot Tab ---
|
|
|
433 |
)
|
434 |
|
435 |
# --- Repo Explorer Tab ---
|
436 |
+
with gr.TabItem("π Repo Explorer", id="repo_explorer_tab"):
|
437 |
+
repo_components, repo_states = create_repo_explorer_tab()
|
438 |
|
439 |
# --- Footer ---
|
440 |
gr.Markdown(
|
repo_explorer.py
CHANGED
@@ -120,10 +120,9 @@ Make this comprehensive but conversational - it will be used by a chatbot to ans
|
|
120 |
logger.error(f"Error creating repo context summary: {e}")
|
121 |
return f"Repository analysis unavailable: {e}"
|
122 |
|
123 |
-
def create_repo_explorer_tab() -> Tuple[
|
124 |
"""
|
125 |
-
Creates the Repo Explorer tab
|
126 |
-
component references, and state variables.
|
127 |
"""
|
128 |
|
129 |
# State variables for repo explorer
|
@@ -132,58 +131,57 @@ def create_repo_explorer_tab() -> Tuple[gr.TabItem, Dict[str, gr.components.Comp
|
|
132 |
"current_repo_id": gr.State("")
|
133 |
}
|
134 |
|
135 |
-
|
136 |
-
|
137 |
-
|
138 |
-
with gr.
|
139 |
-
|
140 |
-
|
141 |
-
|
142 |
-
|
143 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
144 |
)
|
145 |
-
|
146 |
-
load_repo_btn = gr.Button("π Load Repository", variant="primary", size="lg")
|
147 |
|
148 |
-
with gr.
|
149 |
-
|
150 |
-
label="
|
|
|
151 |
interactive=False,
|
152 |
-
|
153 |
-
info="
|
154 |
)
|
155 |
-
|
156 |
-
with gr.Row():
|
157 |
-
with gr.Column(scale=2):
|
158 |
-
repo_chatbot = gr.Chatbot(
|
159 |
-
label="π€ Repository Assistant",
|
160 |
-
height=500,
|
161 |
-
type="messages",
|
162 |
-
avatar_images=(
|
163 |
-
"https://cdn-icons-png.flaticon.com/512/149/149071.png",
|
164 |
-
"https://huggingface.co/datasets/huggingface/brand-assets/resolve/main/hf-logo.png"
|
165 |
-
),
|
166 |
-
show_copy_button=True
|
167 |
-
)
|
168 |
-
|
169 |
-
with gr.Row():
|
170 |
-
repo_msg_input = gr.Textbox(
|
171 |
-
label="π Ask about this repository",
|
172 |
-
placeholder="What does this repository do? How do I use it?",
|
173 |
-
lines=1,
|
174 |
-
scale=4,
|
175 |
-
info="Ask anything about the loaded repository"
|
176 |
-
)
|
177 |
-
repo_send_btn = gr.Button("π€ Send", variant="primary", scale=1)
|
178 |
-
|
179 |
-
with gr.Column(scale=1):
|
180 |
-
repo_content_display = gr.Textbox(
|
181 |
-
label="π Repository Content Preview",
|
182 |
-
lines=25,
|
183 |
-
interactive=False,
|
184 |
-
show_copy_button=True,
|
185 |
-
info="Preview of the repository files and content"
|
186 |
-
)
|
187 |
|
188 |
# Component references
|
189 |
components = {
|
@@ -196,7 +194,7 @@ def create_repo_explorer_tab() -> Tuple[gr.TabItem, Dict[str, gr.components.Comp
|
|
196 |
"repo_content_display": repo_content_display
|
197 |
}
|
198 |
|
199 |
-
return
|
200 |
|
201 |
def handle_load_repository(repo_id: str) -> Tuple[str, str, str]:
|
202 |
"""Load a specific repository and prepare it for exploration with chunk-based analysis."""
|
|
|
120 |
logger.error(f"Error creating repo context summary: {e}")
|
121 |
return f"Repository analysis unavailable: {e}"
|
122 |
|
123 |
+
def create_repo_explorer_tab() -> Tuple[Dict[str, gr.components.Component], Dict[str, gr.State]]:
|
124 |
"""
|
125 |
+
Creates the Repo Explorer tab content and returns the component references and state variables.
|
|
|
126 |
"""
|
127 |
|
128 |
# State variables for repo explorer
|
|
|
131 |
"current_repo_id": gr.State("")
|
132 |
}
|
133 |
|
134 |
+
gr.Markdown("### ποΈ Deep Dive into a Specific Repository")
|
135 |
+
|
136 |
+
with gr.Row():
|
137 |
+
with gr.Column(scale=2):
|
138 |
+
repo_explorer_input = gr.Textbox(
|
139 |
+
label="π Repository ID",
|
140 |
+
placeholder="microsoft/DialoGPT-medium",
|
141 |
+
info="Enter a Hugging Face repository ID to explore"
|
142 |
+
)
|
143 |
+
with gr.Column(scale=1):
|
144 |
+
load_repo_btn = gr.Button("π Load Repository", variant="primary", size="lg")
|
145 |
+
|
146 |
+
with gr.Row():
|
147 |
+
repo_status_display = gr.Textbox(
|
148 |
+
label="π Repository Status",
|
149 |
+
interactive=False,
|
150 |
+
lines=3,
|
151 |
+
info="Current repository loading status and basic info"
|
152 |
+
)
|
153 |
+
|
154 |
+
with gr.Row():
|
155 |
+
with gr.Column(scale=2):
|
156 |
+
repo_chatbot = gr.Chatbot(
|
157 |
+
label="π€ Repository Assistant",
|
158 |
+
height=500,
|
159 |
+
type="messages",
|
160 |
+
avatar_images=(
|
161 |
+
"https://cdn-icons-png.flaticon.com/512/149/149071.png",
|
162 |
+
"https://huggingface.co/datasets/huggingface/brand-assets/resolve/main/hf-logo.png"
|
163 |
+
),
|
164 |
+
show_copy_button=True
|
165 |
+
)
|
166 |
+
|
167 |
+
with gr.Row():
|
168 |
+
repo_msg_input = gr.Textbox(
|
169 |
+
label="π Ask about this repository",
|
170 |
+
placeholder="What does this repository do? How do I use it?",
|
171 |
+
lines=1,
|
172 |
+
scale=4,
|
173 |
+
info="Ask anything about the loaded repository"
|
174 |
)
|
175 |
+
repo_send_btn = gr.Button("π€ Send", variant="primary", scale=1)
|
|
|
176 |
|
177 |
+
with gr.Column(scale=1):
|
178 |
+
repo_content_display = gr.Textbox(
|
179 |
+
label="π Repository Content Preview",
|
180 |
+
lines=25,
|
181 |
interactive=False,
|
182 |
+
show_copy_button=True,
|
183 |
+
info="Preview of the repository files and content"
|
184 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
185 |
|
186 |
# Component references
|
187 |
components = {
|
|
|
194 |
"repo_content_display": repo_content_display
|
195 |
}
|
196 |
|
197 |
+
return components, states
|
198 |
|
199 |
def handle_load_repository(repo_id: str) -> Tuple[str, str, str]:
|
200 |
"""Load a specific repository and prepare it for exploration with chunk-based analysis."""
|