Enhance file handling instructions in code interpreter and message handler; clarify usage of load_file() and print() for user-uploaded files
This commit is contained in:
@@ -12,6 +12,7 @@ You have access to a powerful code interpreter environment that allows you to:
|
|||||||
- Execute Python code in a secure, isolated environment
|
- Execute Python code in a secure, isolated environment
|
||||||
- Maximum execution time: 60 seconds
|
- Maximum execution time: 60 seconds
|
||||||
- Output limit: 100KB
|
- Output limit: 100KB
|
||||||
|
- ⚠️ **IMPORTANT: Use print() to display results!** Only printed output is captured and shown to the user.
|
||||||
|
|
||||||
## 📦 **Package Management (Auto-Install)**
|
## 📦 **Package Management (Auto-Install)**
|
||||||
The code interpreter can AUTOMATICALLY install missing packages when needed!
|
The code interpreter can AUTOMATICALLY install missing packages when needed!
|
||||||
@@ -43,18 +44,64 @@ import seaborn as sns # Will auto-install if missing
|
|||||||
import pandas as pd # Will auto-install if missing
|
import pandas as pd # Will auto-install if missing
|
||||||
|
|
||||||
df = pd.DataFrame({'x': [1,2,3], 'y': [4,5,6]})
|
df = pd.DataFrame({'x': [1,2,3], 'y': [4,5,6]})
|
||||||
|
print(df) # ⚠️ Use print() to show output!
|
||||||
sns.scatterplot(data=df, x='x', y='y')
|
sns.scatterplot(data=df, x='x', y='y')
|
||||||
plt.savefig('plot.png')
|
plt.savefig('plot.png')
|
||||||
|
print("Chart saved!") # Confirm completion
|
||||||
```
|
```
|
||||||
|
|
||||||
|
⚠️ **REMINDER: Only printed output is visible!** Always use print() for any data you want the user to see.
|
||||||
|
|
||||||
## 📁 **File Management (48-Hour Lifecycle)**
|
## 📁 **File Management (48-Hour Lifecycle)**
|
||||||
|
|
||||||
### **User-Uploaded Files**
|
### **User-Uploaded Files**
|
||||||
- Users can upload files (CSV, Excel, JSON, images, etc.)
|
- Users can upload files (CSV, Excel, JSON, images, etc.)
|
||||||
- Files are stored with unique `file_id`
|
- Files are stored with unique `file_id`
|
||||||
- Access files using: `df = load_file('file_id_here')`
|
|
||||||
- Files expire after 48 hours automatically
|
- Files expire after 48 hours automatically
|
||||||
|
|
||||||
|
### **CRITICAL: How to Load Files**
|
||||||
|
|
||||||
|
**Option 1: load_file() - Returns data directly (RECOMMENDED)**
|
||||||
|
```python
|
||||||
|
# For CSV files - returns DataFrame directly, DO NOT pass to pd.read_csv()!
|
||||||
|
# ⚠️ Use the ACTUAL file_id from the upload message, NOT this example!
|
||||||
|
df = load_file('<file_id_from_upload_message>')
|
||||||
|
print(df.head()) # Works immediately!
|
||||||
|
```
|
||||||
|
|
||||||
|
**Option 2: get_file_path() - Returns path for manual loading**
|
||||||
|
```python
|
||||||
|
# If you need the actual file path:
|
||||||
|
path = get_file_path('<file_id_from_upload_message>')
|
||||||
|
df = pd.read_csv(path)
|
||||||
|
```
|
||||||
|
|
||||||
|
### **COMMON MISTAKES TO AVOID**
|
||||||
|
```python
|
||||||
|
# ❌ WRONG - load_file() returns a DataFrame, NOT a path!
|
||||||
|
file_path = load_file('<file_id>')
|
||||||
|
df = pd.read_csv(file_path) # ERROR: Cannot read DataFrame as CSV!
|
||||||
|
|
||||||
|
# ❌ WRONG - file_id is NOT a file path!
|
||||||
|
df = pd.read_csv('<file_id>') # ERROR: File not found!
|
||||||
|
|
||||||
|
# ❌ WRONG - Using example IDs from documentation!
|
||||||
|
df = load_file('example_from_docs') # ERROR: Use REAL file_id from upload!
|
||||||
|
|
||||||
|
# ✅ CORRECT - use load_file() with the ACTUAL file_id from upload message
|
||||||
|
df = load_file('<file_id_from_upload_message>') # Copy exact ID from 📁 FILE UPLOADED
|
||||||
|
print(df.head()) # ⚠️ Use print() to show output!
|
||||||
|
print(df.describe())
|
||||||
|
|
||||||
|
# ✅ CORRECT - use get_file_path() if you need the path
|
||||||
|
path = get_file_path('<file_id_from_upload_message>')
|
||||||
|
df = pd.read_csv(path)
|
||||||
|
print(df.info()) # Always print results!
|
||||||
|
```
|
||||||
|
|
||||||
|
⚠️ CRITICAL: The file_id is shown in the conversation when a file is uploaded.
|
||||||
|
Look for: "📁 FILE UPLOADED" or "df = load_file('...')" in recent messages!
|
||||||
|
|
||||||
### **Generated Files**
|
### **Generated Files**
|
||||||
- ANY file you create is captured and saved
|
- ANY file you create is captured and saved
|
||||||
- Supported types: images, CSVs, text, JSON, HTML, PDFs, etc. (80+ formats)
|
- Supported types: images, CSVs, text, JSON, HTML, PDFs, etc. (80+ formats)
|
||||||
@@ -94,10 +141,14 @@ plt.savefig('plot.png')
|
|||||||
|
|
||||||
**Load uploaded file:**
|
**Load uploaded file:**
|
||||||
```python
|
```python
|
||||||
# User uploaded 'sales_data.csv' with file_id: 'user_123_1234567890_abc123'
|
# ⚠️ Find the ACTUAL file_id in the conversation's "📁 FILE UPLOADED" message!
|
||||||
df = load_file('user_123_1234567890_abc123')
|
# DO NOT copy this example - use the real file_id shown when the user uploaded!
|
||||||
print(df.head())
|
df = load_file('<paste_actual_file_id_here>')
|
||||||
print(f"Loaded {len(df)} rows")
|
|
||||||
|
# ⚠️ CRITICAL: Always use print() to display results!
|
||||||
|
print(df.head()) # Show first rows
|
||||||
|
print(df.describe()) # Show statistics
|
||||||
|
print(f"Loaded {len(df)} rows, {len(df.columns)} columns")
|
||||||
```
|
```
|
||||||
|
|
||||||
**Create multiple output files:**
|
**Create multiple output files:**
|
||||||
|
|||||||
@@ -195,9 +195,35 @@ NORMAL_CHAT_PROMPT = """You're ChatGPT for Discord. Be concise, helpful, safe. R
|
|||||||
TOOLS:
|
TOOLS:
|
||||||
1. google_search(query) - Web search for current info
|
1. google_search(query) - Web search for current info
|
||||||
2. scrape_webpage(url) - Extract webpage content
|
2. scrape_webpage(url) - Extract webpage content
|
||||||
3. execute_python_code(code) - Run Python, packages auto-install. Use load_file('file_id') for user files. Save outputs to files.
|
3. execute_python_code(code) - Run Python, packages auto-install. **FILE ACCESS: See critical instructions below!**
|
||||||
4. set_reminder(content, time) / get_reminders() - Manage reminders
|
4. set_reminder(content, time) / get_reminders() - Manage reminders
|
||||||
|
|
||||||
|
═══════════════════════════════════════════════════════════════
|
||||||
|
⚠️ CRITICAL: FILE ACCESS IN CODE INTERPRETER
|
||||||
|
═══════════════════════════════════════════════════════════════
|
||||||
|
|
||||||
|
When users upload files, you will see a message like:
|
||||||
|
📁 FILE UPLOADED - USE THIS FILE_ID:
|
||||||
|
Filename: data.csv
|
||||||
|
⚠️ TO ACCESS THIS FILE IN CODE, YOU MUST USE:
|
||||||
|
df = load_file('<THE_ACTUAL_FILE_ID_FROM_CONTEXT>')
|
||||||
|
|
||||||
|
**IMPORTANT: Copy the EXACT file_id from the file upload message - do NOT use examples!**
|
||||||
|
|
||||||
|
✅ CORRECT:
|
||||||
|
df = load_file('<file_id_from_upload_message>')
|
||||||
|
print(df.head()) # Use print() to show output!
|
||||||
|
|
||||||
|
⚠️ IMPORTANT: Always use print() to display results - code output is only captured via print()!
|
||||||
|
|
||||||
|
❌ WRONG - Using filename:
|
||||||
|
df = pd.read_csv('data.csv') # FAILS - file not found!
|
||||||
|
|
||||||
|
❌ WRONG - Using example file_id from prompts:
|
||||||
|
df = load_file('example_id_from_docs') # FAILS - use the REAL ID!
|
||||||
|
|
||||||
|
⚠️ CRITICAL: Look for the 📁 FILE UPLOADED message in this conversation and copy the EXACT file_id shown there!
|
||||||
|
|
||||||
═══════════════════════════════════════════════════════════════
|
═══════════════════════════════════════════════════════════════
|
||||||
IMAGE GENERATION & EDITING TOOLS
|
IMAGE GENERATION & EDITING TOOLS
|
||||||
═══════════════════════════════════════════════════════════════
|
═══════════════════════════════════════════════════════════════
|
||||||
|
|||||||
@@ -1222,11 +1222,20 @@ print("\\n=== Correlation Analysis ===")
|
|||||||
user_message = message.content.strip() if message.content else ""
|
user_message = message.content.strip() if message.content else ""
|
||||||
|
|
||||||
file_context = (
|
file_context = (
|
||||||
f"\n\n[User uploaded file: {filename}]\n"
|
f"\n\n══════════════════════════════════════════════\n"
|
||||||
f"[File ID: {file_id}]\n"
|
f"📁 FILE UPLOADED - USE THIS FILE_ID:\n"
|
||||||
f"[File Type: {file_type}]\n"
|
f"══════════════════════════════════════════════\n"
|
||||||
f"[Size: {size_str}]\n"
|
f"Filename: {filename}\n"
|
||||||
f"[Available in code_interpreter via: load_file('{file_id}')]\n"
|
f"File Type: {file_type}\n"
|
||||||
|
f"Size: {size_str}\n"
|
||||||
|
f"\n"
|
||||||
|
f"⚠️ TO ACCESS THIS FILE IN CODE, YOU MUST USE:\n"
|
||||||
|
f" df = load_file('{file_id}')\n"
|
||||||
|
f"\n"
|
||||||
|
f"❌ DO NOT use the filename directly (e.g., pd.read_csv('{filename}'))\n"
|
||||||
|
f"❌ DO NOT use file_id as a path (e.g., pd.read_csv('{file_id}'))\n"
|
||||||
|
f"✅ ONLY use: load_file('{file_id}')\n"
|
||||||
|
f"══════════════════════════════════════════════\n"
|
||||||
)
|
)
|
||||||
|
|
||||||
if user_message:
|
if user_message:
|
||||||
|
|||||||
@@ -197,7 +197,7 @@ BLOCKED_PATTERNS = [
|
|||||||
r'gc\.',
|
r'gc\.',
|
||||||
r'sys\.getsizeof',
|
r'sys\.getsizeof',
|
||||||
r'sys\.getrefcount',
|
r'sys\.getrefcount',
|
||||||
r'id\s*\(', # Block id() which can leak memory addresses
|
r'\bid\s*\(', # Block id() which can leak memory addresses (\b ensures word boundary)
|
||||||
]
|
]
|
||||||
|
|
||||||
# Additional patterns that log warnings but don't block
|
# Additional patterns that log warnings but don't block
|
||||||
@@ -1050,31 +1050,57 @@ import os
|
|||||||
|
|
||||||
FILES = {json.dumps(file_paths_map)}
|
FILES = {json.dumps(file_paths_map)}
|
||||||
|
|
||||||
|
def get_file_path(file_id):
|
||||||
|
'''
|
||||||
|
Get the actual file path for a given file ID.
|
||||||
|
Use this to get the path for pd.read_csv(), open(), etc.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
file_id: The file ID provided when the file was uploaded
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
str: The actual file path on disk
|
||||||
|
|
||||||
|
Example:
|
||||||
|
path = get_file_path('878573881449906208_1764556246_bdbaecc8')
|
||||||
|
df = pd.read_csv(path)
|
||||||
|
|
||||||
|
Available files: Use list(FILES.keys()) to see available files
|
||||||
|
'''
|
||||||
|
if file_id not in FILES:
|
||||||
|
raise ValueError(f"File '{{file_id}}' not found. Available: {{list(FILES.keys())}}")
|
||||||
|
return FILES[file_id]
|
||||||
|
|
||||||
def load_file(file_id):
|
def load_file(file_id):
|
||||||
'''
|
'''
|
||||||
Load a file automatically based on its extension.
|
Load a file automatically based on its extension and return the data directly.
|
||||||
Supports 200+ file types with smart auto-detection.
|
DO NOT pass the result to pd.read_csv() - it already returns a DataFrame!
|
||||||
|
|
||||||
Args:
|
Args:
|
||||||
file_id: The file ID provided when the file was uploaded
|
file_id: The file ID provided when the file was uploaded
|
||||||
|
|
||||||
Returns:
|
Returns:
|
||||||
Loaded file data (varies by file type):
|
Loaded file data (varies by file type):
|
||||||
- CSV/TSV: pandas DataFrame
|
- CSV/TSV: pandas DataFrame (ready to use!)
|
||||||
- Excel (.xlsx, .xls): pandas ExcelFile object
|
- Excel (.xlsx, .xls): pandas ExcelFile object
|
||||||
- JSON: pandas DataFrame or dict
|
- JSON: pandas DataFrame or dict
|
||||||
- Parquet/Feather: pandas DataFrame
|
- Parquet/Feather: pandas DataFrame
|
||||||
- Text files: string content
|
- Text files: string content
|
||||||
- Images: PIL Image object
|
- Images: PIL Image object
|
||||||
- And 200+ more formats...
|
|
||||||
|
|
||||||
Excel file usage examples:
|
CORRECT usage for CSV:
|
||||||
excel_file = load_file('file_id')
|
df = load_file('file_id') # Returns DataFrame directly
|
||||||
sheet_names = excel_file.sheet_names
|
print(df.head())
|
||||||
df = excel_file.parse('Sheet1')
|
|
||||||
df2 = pd.read_excel(excel_file, sheet_name='Sheet1')
|
|
||||||
|
|
||||||
Available files: {{', '.join(FILES.keys()) if FILES else 'None'}}
|
WRONG usage (DO NOT DO THIS):
|
||||||
|
file_path = load_file('file_id') # WRONG! This is a DataFrame, not a path
|
||||||
|
df = pd.read_csv(file_path) # This will FAIL!
|
||||||
|
|
||||||
|
If you need the file path instead, use get_file_path():
|
||||||
|
path = get_file_path('file_id')
|
||||||
|
df = pd.read_csv(path)
|
||||||
|
|
||||||
|
Available files: Use list(FILES.keys()) to see available files
|
||||||
'''
|
'''
|
||||||
if file_id not in FILES:
|
if file_id not in FILES:
|
||||||
available_files = list(FILES.keys())
|
available_files = list(FILES.keys())
|
||||||
|
|||||||
@@ -190,7 +190,7 @@ def capture_exception(
|
|||||||
"""
|
"""
|
||||||
logger.exception(f"Captured exception: {exception}")
|
logger.exception(f"Captured exception: {exception}")
|
||||||
|
|
||||||
if SENTRY_AVAILABLE and sentry_sdk.Hub.current.client:
|
if SENTRY_AVAILABLE and sentry_sdk.is_initialized():
|
||||||
with sentry_sdk.push_scope() as scope:
|
with sentry_sdk.push_scope() as scope:
|
||||||
if context:
|
if context:
|
||||||
for key, value in context.items():
|
for key, value in context.items():
|
||||||
@@ -219,7 +219,7 @@ def capture_message(
|
|||||||
log_method = getattr(logger, level, logger.info)
|
log_method = getattr(logger, level, logger.info)
|
||||||
log_method(message)
|
log_method(message)
|
||||||
|
|
||||||
if SENTRY_AVAILABLE and sentry_sdk.Hub.current.client:
|
if SENTRY_AVAILABLE and sentry_sdk.is_initialized():
|
||||||
with sentry_sdk.push_scope() as scope:
|
with sentry_sdk.push_scope() as scope:
|
||||||
if context:
|
if context:
|
||||||
for key, value in context.items():
|
for key, value in context.items():
|
||||||
@@ -242,7 +242,7 @@ def set_user_context(
|
|||||||
username: Discord username
|
username: Discord username
|
||||||
guild_id: Discord guild ID
|
guild_id: Discord guild ID
|
||||||
"""
|
"""
|
||||||
if SENTRY_AVAILABLE and sentry_sdk.Hub.current.client:
|
if SENTRY_AVAILABLE and sentry_sdk.is_initialized():
|
||||||
sentry_sdk.set_user({
|
sentry_sdk.set_user({
|
||||||
"id": str(user_id),
|
"id": str(user_id),
|
||||||
"username": username,
|
"username": username,
|
||||||
@@ -325,7 +325,7 @@ async def measure_async(name: str, **metadata):
|
|||||||
|
|
||||||
# Start Sentry transaction if available
|
# Start Sentry transaction if available
|
||||||
transaction = None
|
transaction = None
|
||||||
if SENTRY_AVAILABLE and sentry_sdk.Hub.current.client:
|
if SENTRY_AVAILABLE and sentry_sdk.is_initialized():
|
||||||
transaction = sentry_sdk.start_transaction(
|
transaction = sentry_sdk.start_transaction(
|
||||||
op="task",
|
op="task",
|
||||||
name=name
|
name=name
|
||||||
|
|||||||
Reference in New Issue
Block a user