mirror of
https://github.com/csunny/DB-GPT.git
synced 2025-09-07 03:50:42 +00:00
feat(model): Support database model registry (#1656)
This commit is contained in:
Fangyin Cheng
GitHub
@@ -23,8 +23,8 @@
|
||||
"\n",
|
||||
"nest_asyncio.apply()"
|
||||
],
|
||||
"outputs": [],
|
||||
"execution_count": 7
|
||||
"execution_count": 7,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
@@ -32,12 +32,12 @@
|
||||
"metadata": {
|
||||
"is_executing": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Set your api key and api base url\n",
|
||||
"# os.environ[\"OPENAI_API_KEY\"] = \"Your API\"\n",
|
||||
"# os.environ[\"OPENAI_API_BASE\"] = \"https://api.openai.com/v1\""
|
||||
]
|
||||
],
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
@@ -84,666 +84,8 @@
|
||||
" # message=\"find papers on LLM applications from arxiv in the last month, create a markdown table of different domains.\",\n",
|
||||
")"
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mUser\u001B[0m (to PlanManager)-[]:\n",
|
||||
"\n",
|
||||
"\"Obtain simple information about issues in the repository 'eosphoros-ai/DB-GPT' in the past three days and analyze the data. Create a Markdown table grouped by day and status.\"\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"un_stream ai response: [\n",
|
||||
" {\n",
|
||||
" \"serial_number\": \"1\",\n",
|
||||
" \"agent\": \"CodeEngineer\",\n",
|
||||
" \"content\": \"Use Github API to retrieve issues from the repository 'eosphoros-ai/DB-GPT' in the past three days.\",\n",
|
||||
" \"rely\": \"\"\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"serial_number\": \"2\",\n",
|
||||
" \"agent\": \"CodeEngineer\",\n",
|
||||
" \"content\": \"Analyze the retrieved issues data, extract the necessary information such as issue title, status, and created date.\",\n",
|
||||
" \"rely\": \"1\"\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"serial_number\": \"3\",\n",
|
||||
" \"agent\": \"CodeEngineer\",\n",
|
||||
" \"content\": \"Group the extracted data by day and status.\",\n",
|
||||
" \"rely\": \"2\"\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"serial_number\": \"4\",\n",
|
||||
" \"agent\": \"CodeEngineer\",\n",
|
||||
" \"content\": \"Create a Markdown table with the grouped data.\",\n",
|
||||
" \"rely\": \"3\"\n",
|
||||
" }\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mPlanner\u001B[0m (to PlanManager)-[gpt-4]:\n",
|
||||
"\n",
|
||||
"\"[\\n {\\n \\\"serial_number\\\": \\\"1\\\",\\n \\\"agent\\\": \\\"CodeEngineer\\\",\\n \\\"content\\\": \\\"Use Github API to retrieve issues from the repository 'eosphoros-ai/DB-GPT' in the past three days.\\\",\\n \\\"rely\\\": \\\"\\\"\\n },\\n {\\n \\\"serial_number\\\": \\\"2\\\",\\n \\\"agent\\\": \\\"CodeEngineer\\\",\\n \\\"content\\\": \\\"Analyze the retrieved issues data, extract the necessary information such as issue title, status, and created date.\\\",\\n \\\"rely\\\": \\\"1\\\"\\n },\\n {\\n \\\"serial_number\\\": \\\"3\\\",\\n \\\"agent\\\": \\\"CodeEngineer\\\",\\n \\\"content\\\": \\\"Group the extracted data by day and status.\\\",\\n \\\"rely\\\": \\\"2\\\"\\n },\\n {\\n \\\"serial_number\\\": \\\"4\\\",\\n \\\"agent\\\": \\\"CodeEngineer\\\",\\n \\\"content\\\": \\\"Create a Markdown table with the grouped data.\\\",\\n \\\"rely\\\": \\\"3\\\"\\n }\\n]\"\n",
|
||||
"\u001B[32m>>>>>>>>Planner Review info: \n",
|
||||
"Pass(None)\u001B[0m\n",
|
||||
"\u001B[34m>>>>>>>>Planner Action report: \n",
|
||||
"execution succeeded,\n",
|
||||
"[\n",
|
||||
" {\n",
|
||||
" \"serial_number\": \"1\",\n",
|
||||
" \"agent\": \"CodeEngineer\",\n",
|
||||
" \"content\": \"Use Github API to retrieve issues from the repository 'eosphoros-ai/DB-GPT' in the past three days.\",\n",
|
||||
" \"rely\": \"\"\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"serial_number\": \"2\",\n",
|
||||
" \"agent\": \"CodeEngineer\",\n",
|
||||
" \"content\": \"Analyze the retrieved issues data, extract the necessary information such as issue title, status, and created date.\",\n",
|
||||
" \"rely\": \"1\"\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"serial_number\": \"3\",\n",
|
||||
" \"agent\": \"CodeEngineer\",\n",
|
||||
" \"content\": \"Group the extracted data by day and status.\",\n",
|
||||
" \"rely\": \"2\"\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"serial_number\": \"4\",\n",
|
||||
" \"agent\": \"CodeEngineer\",\n",
|
||||
" \"content\": \"Create a Markdown table with the grouped data.\",\n",
|
||||
" \"rely\": \"3\"\n",
|
||||
" }\n",
|
||||
"]\u001B[0m\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"GroupChat select_speaker failed to resolve the next speaker's name. This is because the speaker selection OAI call returned:\n",
|
||||
"CodeEngineer\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mPlanManager\u001B[0m (to Turing)-[]:\n",
|
||||
"\n",
|
||||
"\"Use Github API to retrieve issues from the repository 'eosphoros-ai/DB-GPT' in the past three days.\"\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"un_stream ai response: To retrieve issues from the GitHub repository 'eosphoros-ai/DB-GPT' in the past three days, we can use the GitHub REST API. Here is a Python script that accomplishes this. This script uses the 'requests' library to send a GET request to the GitHub API. The script then parses the JSON response to filter out issues created in the last three days.\n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"# python\n",
|
||||
"import requests\n",
|
||||
"from datetime import datetime, timedelta\n",
|
||||
"import pytz\n",
|
||||
"\n",
|
||||
"# Get the current date and time\n",
|
||||
"now = datetime.now()\n",
|
||||
"\n",
|
||||
"# Calculate the date 3 days ago\n",
|
||||
"three_days_ago = now - timedelta(days=3)\n",
|
||||
"\n",
|
||||
"# Convert the date to ISO 8601 format\n",
|
||||
"three_days_ago_iso = three_days_ago.isoformat()\n",
|
||||
"\n",
|
||||
"# Specify the URL of the GitHub API\n",
|
||||
"url = \"https://api.github.com/repos/eosphoros-ai/DB-GPT/issues\"\n",
|
||||
"\n",
|
||||
"# Send a GET request to the GitHub API\n",
|
||||
"response = requests.get(url)\n",
|
||||
"\n",
|
||||
"# Check if the request was successful\n",
|
||||
"if response.status_code == 200:\n",
|
||||
" # Parse the JSON response\n",
|
||||
" issues = response.json()\n",
|
||||
"\n",
|
||||
" # Filter out issues created in the last three days\n",
|
||||
" recent_issues = [issue for issue in issues if issue['created_at'] > three_days_ago_iso]\n",
|
||||
"\n",
|
||||
" # Print the recent issues\n",
|
||||
" for issue in recent_issues:\n",
|
||||
" print(\"Issue ID: \", issue['id'])\n",
|
||||
" print(\"Issue Title: \", issue['title'])\n",
|
||||
" print(\"Issue URL: \", issue['html_url'])\n",
|
||||
" print(\"Issue Created At: \", issue['created_at'])\n",
|
||||
" print(\"\\n\")\n",
|
||||
"else:\n",
|
||||
" print(\"Failed to retrieve issues. HTTP Status Code: \", response.status_code)\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Please note that this script doesn't handle pagination. The GitHub API returns a maximum of 30 items per page. If there are more than 30 issues, you will need to send multiple requests to retrieve all issues. Also, the GitHub API has a rate limit. For unauthenticated requests, the rate limit is 60 requests per hour. For authenticated requests, the rate limit is 5000 requests per hour.\n",
|
||||
"\u001B[31m\n",
|
||||
">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001B[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"execute_code was called without specifying a value for use_docker. Since the python docker package is not available, code will be run natively. Note: this fallback behavior is subject to change\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"un_stream ai response: True\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mTuring\u001B[0m (to PlanManager)-[gpt-4]:\n",
|
||||
"\n",
|
||||
"\"To retrieve issues from the GitHub repository 'eosphoros-ai/DB-GPT' in the past three days, we can use the GitHub REST API. Here is a Python script that accomplishes this. This script uses the 'requests' library to send a GET request to the GitHub API. The script then parses the JSON response to filter out issues created in the last three days.\\n\\n```python\\n# python\\nimport requests\\nfrom datetime import datetime, timedelta\\nimport pytz\\n\\n# Get the current date and time\\nnow = datetime.now()\\n\\n# Calculate the date 3 days ago\\nthree_days_ago = now - timedelta(days=3)\\n\\n# Convert the date to ISO 8601 format\\nthree_days_ago_iso = three_days_ago.isoformat()\\n\\n# Specify the URL of the GitHub API\\nurl = \\\"https://api.github.com/repos/eosphoros-ai/DB-GPT/issues\\\"\\n\\n# Send a GET request to the GitHub API\\nresponse = requests.get(url)\\n\\n# Check if the request was successful\\nif response.status_code == 200:\\n # Parse the JSON response\\n issues = response.json()\\n\\n # Filter out issues created in the last three days\\n recent_issues = [issue for issue in issues if issue['created_at'] > three_days_ago_iso]\\n\\n # Print the recent issues\\n for issue in recent_issues:\\n print(\\\"Issue ID: \\\", issue['id'])\\n print(\\\"Issue Title: \\\", issue['title'])\\n print(\\\"Issue URL: \\\", issue['html_url'])\\n print(\\\"Issue Created At: \\\", issue['created_at'])\\n print(\\\"\\\\n\\\")\\nelse:\\n print(\\\"Failed to retrieve issues. HTTP Status Code: \\\", response.status_code)\\n```\\n\\nPlease note that this script doesn't handle pagination. The GitHub API returns a maximum of 30 items per page. If there are more than 30 issues, you will need to send multiple requests to retrieve all issues. Also, the GitHub API has a rate limit. For unauthenticated requests, the rate limit is 60 requests per hour. For authenticated requests, the rate limit is 5000 requests per hour.\"\n",
|
||||
"\u001B[32m>>>>>>>>Turing Review info: \n",
|
||||
"Pass(None)\u001B[0m\n",
|
||||
"\u001B[34m>>>>>>>>Turing Action report: \n",
|
||||
"execution succeeded,\n",
|
||||
"\n",
|
||||
"Issue ID: 2234707865\n",
|
||||
"Issue Title: [Bug] [remote_worker] 使用model-controller作为集群模式时，通过web进行知识库问答，会将所有模型请求一遍\n",
|
||||
"Issue URL: https://github.com/eosphoros-ai/DB-GPT/issues/1398\n",
|
||||
"Issue Created At: 2024-04-10T03:57:27Z\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Issue ID: 2234675367\n",
|
||||
"Issue Title: [Bug] LLMServer Generate Error, Please CheckErrorInfo.: CUDA error\n",
|
||||
"Issue URL: https://github.com/eosphoros-ai/DB-GPT/issues/1397\n",
|
||||
"Issue Created At: 2024-04-10T03:12:34Z\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Issue ID: 2234172353\n",
|
||||
"Issue Title: feat(agent): Release agent SDK\n",
|
||||
"Issue URL: https://github.com/eosphoros-ai/DB-GPT/pull/1396\n",
|
||||
"Issue Created At: 2024-04-09T19:35:04Z\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Issue ID: 2232992034\n",
|
||||
"Issue Title: feat(RAG):add metadata properties filters\n",
|
||||
"Issue URL: https://github.com/eosphoros-ai/DB-GPT/pull/1395\n",
|
||||
"Issue Created At: 2024-04-09T09:19:53Z\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Issue ID: 2232526474\n",
|
||||
"Issue Title: [Bug] [datasource] Unable to modify database table structure after executing query\n",
|
||||
"Issue URL: https://github.com/eosphoros-ai/DB-GPT/issues/1389\n",
|
||||
"Issue Created At: 2024-04-09T03:18:41Z\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Issue ID: 2230167238\n",
|
||||
"Issue Title: [Feature][RAG] Metadata Properties Filter\n",
|
||||
"Issue URL: https://github.com/eosphoros-ai/DB-GPT/issues/1387\n",
|
||||
"Issue Created At: 2024-04-08T03:15:31Z\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Issue ID: 2229746443\n",
|
||||
"Issue Title: Feat: support oceanbase monaco plugin\n",
|
||||
"Issue URL: https://github.com/eosphoros-ai/DB-GPT/pull/1386\n",
|
||||
"Issue Created At: 2024-04-07T12:29:13Z\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001B[0m\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"GroupChat select_speaker failed to resolve the next speaker's name. This is because the speaker selection OAI call returned:\n",
|
||||
"CodeEngineer\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mPlanManager\u001B[0m (to Turing)-[]:\n",
|
||||
"\n",
|
||||
"\"Read the result data of the dependent steps in the above historical message to complete the current goal:Analyze the retrieved issues data, extract the necessary information such as issue title, status, and created date.\"\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"un_stream ai response: From the historical message, we have the following issues data:\n",
|
||||
"\n",
|
||||
"1. Issue Title: [Bug] [remote_worker] 使用model-controller作为集群模式时，通过web进行知识库问答，会将所有模型请求一遍\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-10\n",
|
||||
"\n",
|
||||
"2. Issue Title: [Bug] LLMServer Generate Error, Please CheckErrorInfo.: CUDA error\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-10\n",
|
||||
"\n",
|
||||
"3. Issue Title: feat(agent): Release agent SDK\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-09\n",
|
||||
"\n",
|
||||
"4. Issue Title: feat(RAG):add metadata properties filters\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-09\n",
|
||||
"\n",
|
||||
"5. Issue Title: [Bug] [datasource] Unable to modify database table structure after executing query\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-09\n",
|
||||
"\n",
|
||||
"6. Issue Title: [Feature][RAG] Metadata Properties Filter\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-08\n",
|
||||
"\n",
|
||||
"7. Issue Title: Feat: support oceanbase monaco plugin\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-07\n",
|
||||
"\n",
|
||||
"Note: The status of the issues is not provided in the historical message. It could be open, closed, or in review. Further API calls would be needed to retrieve the current status of each issue.\n",
|
||||
"\u001B[31m\n",
|
||||
">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is unknown)...\u001B[0m\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mTuring\u001B[0m (to PlanManager)-[gpt-4]:\n",
|
||||
"\n",
|
||||
"\"From the historical message, we have the following issues data:\\n\\n1. Issue Title: [Bug] [remote_worker] 使用model-controller作为集群模式时，通过web进行知识库问答，会将所有模型请求一遍\\n Status: Not specified\\n Created Date: 2024-04-10\\n\\n2. Issue Title: [Bug] LLMServer Generate Error, Please CheckErrorInfo.: CUDA error\\n Status: Not specified\\n Created Date: 2024-04-10\\n\\n3. Issue Title: feat(agent): Release agent SDK\\n Status: Not specified\\n Created Date: 2024-04-09\\n\\n4. Issue Title: feat(RAG):add metadata properties filters\\n Status: Not specified\\n Created Date: 2024-04-09\\n\\n5. Issue Title: [Bug] [datasource] Unable to modify database table structure after executing query\\n Status: Not specified\\n Created Date: 2024-04-09\\n\\n6. Issue Title: [Feature][RAG] Metadata Properties Filter\\n Status: Not specified\\n Created Date: 2024-04-08\\n\\n7. Issue Title: Feat: support oceanbase monaco plugin\\n Status: Not specified\\n Created Date: 2024-04-07\\n\\nNote: The status of the issues is not provided in the historical message. It could be open, closed, or in review. Further API calls would be needed to retrieve the current status of each issue.\"\n",
|
||||
"\u001B[32m>>>>>>>>Turing Review info: \n",
|
||||
"Pass(None)\u001B[0m\n",
|
||||
"\u001B[34m>>>>>>>>Turing Action report: \n",
|
||||
"execution failed,\n",
|
||||
"exitcode: 1 (execution failed)\n",
|
||||
" \n",
|
||||
"unknown language unknown\u001B[0m\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mPlanManager\u001B[0m (to Turing)-[]:\n",
|
||||
"\n",
|
||||
"\"exitcode: 1 (execution failed)\\n \\nunknown language unknown\"\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"un_stream ai response: I apologize for the confusion. The information provided was not meant to be executed as a code but was an analysis of the issue data from the historical message. \n",
|
||||
"\n",
|
||||
"Here's a summary again:\n",
|
||||
"\n",
|
||||
"1. Issue Title: [Bug] [remote_worker] 使用model-controller作为集群模式时，通过web进行知识库问答，会将所有模型请求一遍\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-10\n",
|
||||
"\n",
|
||||
"2. Issue Title: [Bug] LLMServer Generate Error, Please CheckErrorInfo.: CUDA error\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-10\n",
|
||||
"\n",
|
||||
"3. Issue Title: feat(agent): Release agent SDK\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-09\n",
|
||||
"\n",
|
||||
"4. Issue Title: feat(RAG):add metadata properties filters\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-09\n",
|
||||
"\n",
|
||||
"5. Issue Title: [Bug] [datasource] Unable to modify database table structure after executing query\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-09\n",
|
||||
"\n",
|
||||
"6. Issue Title: [Feature][RAG] Metadata Properties Filter\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-08\n",
|
||||
"\n",
|
||||
"7. Issue Title: Feat: support oceanbase monaco plugin\n",
|
||||
" Status: Not specified\n",
|
||||
" Created Date: 2024-04-07\n",
|
||||
"\n",
|
||||
"Please note that this information is a summary and analysis of the issue data retrieved from the historical message and does not need to be executed as code.\n",
|
||||
"\u001B[31m\n",
|
||||
">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is unknown)...\u001B[0m\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mTuring\u001B[0m (to PlanManager)-[gpt-4]:\n",
|
||||
"\n",
|
||||
"\"I apologize for the confusion. The information provided was not meant to be executed as a code but was an analysis of the issue data from the historical message. \\n\\nHere's a summary again:\\n\\n1. Issue Title: [Bug] [remote_worker] 使用model-controller作为集群模式时，通过web进行知识库问答，会将所有模型请求一遍\\n Status: Not specified\\n Created Date: 2024-04-10\\n\\n2. Issue Title: [Bug] LLMServer Generate Error, Please CheckErrorInfo.: CUDA error\\n Status: Not specified\\n Created Date: 2024-04-10\\n\\n3. Issue Title: feat(agent): Release agent SDK\\n Status: Not specified\\n Created Date: 2024-04-09\\n\\n4. Issue Title: feat(RAG):add metadata properties filters\\n Status: Not specified\\n Created Date: 2024-04-09\\n\\n5. Issue Title: [Bug] [datasource] Unable to modify database table structure after executing query\\n Status: Not specified\\n Created Date: 2024-04-09\\n\\n6. Issue Title: [Feature][RAG] Metadata Properties Filter\\n Status: Not specified\\n Created Date: 2024-04-08\\n\\n7. Issue Title: Feat: support oceanbase monaco plugin\\n Status: Not specified\\n Created Date: 2024-04-07\\n\\nPlease note that this information is a summary and analysis of the issue data retrieved from the historical message and does not need to be executed as code.\"\n",
|
||||
"\u001B[32m>>>>>>>>Turing Review info: \n",
|
||||
"Pass(None)\u001B[0m\n",
|
||||
"\u001B[34m>>>>>>>>Turing Action report: \n",
|
||||
"execution failed,\n",
|
||||
"exitcode: 1 (execution failed)\n",
|
||||
" \n",
|
||||
"unknown language unknown\u001B[0m\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mPlanManager\u001B[0m (to Turing)-[]:\n",
|
||||
"\n",
|
||||
"\"exitcode: 1 (execution failed)\\n \\nunknown language unknown\"\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"un_stream ai response: I apologize for the confusion, it seems like there was a misunderstanding. The text provided was an analysis and not a code to be executed. \n",
|
||||
"\n",
|
||||
"However, if you want to format this information in a more structured way using Python code, you can use the following code:\n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"# python code\n",
|
||||
"issues_data = [\n",
|
||||
" {\"title\": \"[Bug] [remote_worker] 使用model-controller作为集群模式时，通过web进行知识库问答，会将所有模型请求一遍\", \"status\": \"Not specified\", \"created_date\": \"2024-04-10\"},\n",
|
||||
" {\"title\": \"[Bug] LLMServer Generate Error, Please CheckErrorInfo.: CUDA error\", \"status\": \"Not specified\", \"created_date\": \"2024-04-10\"},\n",
|
||||
" {\"title\": \"feat(agent): Release agent SDK\", \"status\": \"Not specified\", \"created_date\": \"2024-04-09\"},\n",
|
||||
" {\"title\": \"feat(RAG):add metadata properties filters\", \"status\": \"Not specified\", \"created_date\": \"2024-04-09\"},\n",
|
||||
" {\"title\": \"[Bug] [datasource] Unable to modify database table structure after executing query\", \"status\": \"Not specified\", \"created_date\": \"2024-04-09\"},\n",
|
||||
" {\"title\": \"[Feature][RAG] Metadata Properties Filter\", \"status\": \"Not specified\", \"created_date\": \"2024-04-08\"},\n",
|
||||
" {\"title\": \"Feat: support oceanbase monaco plugin\", \"status\": \"Not specified\", \"created_date\": \"2024-04-07\"}\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"for issue in issues_data:\n",
|
||||
" print(f\"Issue Title: {issue['title']}\\nStatus: {issue['status']}\\nCreated Date: {issue['created_date']}\\n\")\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"This code creates a list of dictionaries where each dictionary represents an issue with its title, status, and created date. The code then iterates over this list and prints the information for each issue.\n",
|
||||
"\u001B[31m\n",
|
||||
">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001B[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"execute_code was called without specifying a value for use_docker. Since the python docker package is not available, code will be run natively. Note: this fallback behavior is subject to change\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"un_stream ai response: True\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mTuring\u001B[0m (to PlanManager)-[gpt-4]:\n",
|
||||
"\n",
|
||||
"\"I apologize for the confusion, it seems like there was a misunderstanding. The text provided was an analysis and not a code to be executed. \\n\\nHowever, if you want to format this information in a more structured way using Python code, you can use the following code:\\n\\n```python\\n# python code\\nissues_data = [\\n {\\\"title\\\": \\\"[Bug] [remote_worker] 使用model-controller作为集群模式时，通过web进行知识库问答，会将所有模型请求一遍\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-10\\\"},\\n {\\\"title\\\": \\\"[Bug] LLMServer Generate Error, Please CheckErrorInfo.: CUDA error\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-10\\\"},\\n {\\\"title\\\": \\\"feat(agent): Release agent SDK\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-09\\\"},\\n {\\\"title\\\": \\\"feat(RAG):add metadata properties filters\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-09\\\"},\\n {\\\"title\\\": \\\"[Bug] [datasource] Unable to modify database table structure after executing query\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-09\\\"},\\n {\\\"title\\\": \\\"[Feature][RAG] Metadata Properties Filter\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-08\\\"},\\n {\\\"title\\\": \\\"Feat: support oceanbase monaco plugin\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-07\\\"}\\n]\\n\\nfor issue in issues_data:\\n print(f\\\"Issue Title: {issue['title']}\\\\nStatus: {issue['status']}\\\\nCreated Date: {issue['created_date']}\\\\n\\\")\\n```\\n\\nThis code creates a list of dictionaries where each dictionary represents an issue with its title, status, and created date. The code then iterates over this list and prints the information for each issue.\"\n",
|
||||
"\u001B[32m>>>>>>>>Turing Review info: \n",
|
||||
"Pass(None)\u001B[0m\n",
|
||||
"\u001B[34m>>>>>>>>Turing Action report: \n",
|
||||
"execution succeeded,\n",
|
||||
"\n",
|
||||
"Issue Title: [Bug] [remote_worker] 使用model-controller作为集群模式时，通过web进行知识库问答，会将所有模型请求一遍\n",
|
||||
"Status: Not specified\n",
|
||||
"Created Date: 2024-04-10\n",
|
||||
"\n",
|
||||
"Issue Title: [Bug] LLMServer Generate Error, Please CheckErrorInfo.: CUDA error\n",
|
||||
"Status: Not specified\n",
|
||||
"Created Date: 2024-04-10\n",
|
||||
"\n",
|
||||
"Issue Title: feat(agent): Release agent SDK\n",
|
||||
"Status: Not specified\n",
|
||||
"Created Date: 2024-04-09\n",
|
||||
"\n",
|
||||
"Issue Title: feat(RAG):add metadata properties filters\n",
|
||||
"Status: Not specified\n",
|
||||
"Created Date: 2024-04-09\n",
|
||||
"\n",
|
||||
"Issue Title: [Bug] [datasource] Unable to modify database table structure after executing query\n",
|
||||
"Status: Not specified\n",
|
||||
"Created Date: 2024-04-09\n",
|
||||
"\n",
|
||||
"Issue Title: [Feature][RAG] Metadata Properties Filter\n",
|
||||
"Status: Not specified\n",
|
||||
"Created Date: 2024-04-08\n",
|
||||
"\n",
|
||||
"Issue Title: Feat: support oceanbase monaco plugin\n",
|
||||
"Status: Not specified\n",
|
||||
"Created Date: 2024-04-07\n",
|
||||
"\n",
|
||||
"\u001B[0m\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"GroupChat select_speaker failed to resolve the next speaker's name. This is because the speaker selection OAI call returned:\n",
|
||||
"CodeEngineer\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mPlanManager\u001B[0m (to Turing)-[]:\n",
|
||||
"\n",
|
||||
"\"Read the result data of the dependent steps in the above historical message to complete the current goal:Group the extracted data by day and status.\"\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"un_stream ai response: ```python\n",
|
||||
"# filename: group_issues.py\n",
|
||||
"\n",
|
||||
"import pandas as pd\n",
|
||||
"from datetime import datetime\n",
|
||||
"\n",
|
||||
"# The issue data from the historical message\n",
|
||||
"issue_data = [\n",
|
||||
" {\"title\": \"[Bug] [remote_worker] 使用model-controller作为集群模式时，通过web进行知识库问答，会将所有模型请求一遍\", \"status\": \"Not specified\", \"created_date\": \"2024-04-10\"},\n",
|
||||
" {\"title\": \"[Bug] LLMServer Generate Error, Please CheckErrorInfo.: CUDA error\", \"status\": \"Not specified\", \"created_date\": \"2024-04-10\"},\n",
|
||||
" {\"title\": \"feat(agent): Release agent SDK\", \"status\": \"Not specified\", \"created_date\": \"2024-04-09\"},\n",
|
||||
" {\"title\": \"feat(RAG):add metadata properties filters\", \"status\": \"Not specified\", \"created_date\": \"2024-04-09\"},\n",
|
||||
" {\"title\": \"[Bug] [datasource] Unable to modify database table structure after executing query\", \"status\": \"Not specified\", \"created_date\": \"2024-04-09\"},\n",
|
||||
" {\"title\": \"[Feature][RAG] Metadata Properties Filter\", \"status\": \"Not specified\", \"created_date\": \"2024-04-08\"},\n",
|
||||
" {\"title\": \"Feat: support oceanbase monaco plugin\", \"status\": \"Not specified\", \"created_date\": \"2024-04-07\"},\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"# Convert the issue data into a DataFrame\n",
|
||||
"df = pd.DataFrame(issue_data)\n",
|
||||
"\n",
|
||||
"# Convert the 'created_date' column to datetime\n",
|
||||
"df['created_date'] = pd.to_datetime(df['created_date'])\n",
|
||||
"\n",
|
||||
"# Group the data by date and status\n",
|
||||
"grouped = df.groupby([df['created_date'].dt.date, 'status']).size()\n",
|
||||
"\n",
|
||||
"# Print the grouped data\n",
|
||||
"print(grouped)\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Please save this Python script as `group_issues.py` and execute it. It will group the extracted issue data by day and status and print the result.\n",
|
||||
"\u001B[31m\n",
|
||||
">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001B[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"execute_code was called without specifying a value for use_docker. Since the python docker package is not available, code will be run natively. Note: this fallback behavior is subject to change\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"un_stream ai response: True\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mTuring\u001B[0m (to PlanManager)-[gpt-4]:\n",
|
||||
"\n",
|
||||
"\"```python\\n# filename: group_issues.py\\n\\nimport pandas as pd\\nfrom datetime import datetime\\n\\n# The issue data from the historical message\\nissue_data = [\\n {\\\"title\\\": \\\"[Bug] [remote_worker] 使用model-controller作为集群模式时，通过web进行知识库问答，会将所有模型请求一遍\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-10\\\"},\\n {\\\"title\\\": \\\"[Bug] LLMServer Generate Error, Please CheckErrorInfo.: CUDA error\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-10\\\"},\\n {\\\"title\\\": \\\"feat(agent): Release agent SDK\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-09\\\"},\\n {\\\"title\\\": \\\"feat(RAG):add metadata properties filters\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-09\\\"},\\n {\\\"title\\\": \\\"[Bug] [datasource] Unable to modify database table structure after executing query\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-09\\\"},\\n {\\\"title\\\": \\\"[Feature][RAG] Metadata Properties Filter\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-08\\\"},\\n {\\\"title\\\": \\\"Feat: support oceanbase monaco plugin\\\", \\\"status\\\": \\\"Not specified\\\", \\\"created_date\\\": \\\"2024-04-07\\\"},\\n]\\n\\n# Convert the issue data into a DataFrame\\ndf = pd.DataFrame(issue_data)\\n\\n# Convert the 'created_date' column to datetime\\ndf['created_date'] = pd.to_datetime(df['created_date'])\\n\\n# Group the data by date and status\\ngrouped = df.groupby([df['created_date'].dt.date, 'status']).size()\\n\\n# Print the grouped data\\nprint(grouped)\\n```\\n\\nPlease save this Python script as `group_issues.py` and execute it. It will group the extracted issue data by day and status and print the result.\"\n",
|
||||
"\u001B[32m>>>>>>>>Turing Review info: \n",
|
||||
"Pass(None)\u001B[0m\n",
|
||||
"\u001B[34m>>>>>>>>Turing Action report: \n",
|
||||
"execution succeeded,\n",
|
||||
"\n",
|
||||
"created_date status \n",
|
||||
"2024-04-07 Not specified 1\n",
|
||||
"2024-04-08 Not specified 1\n",
|
||||
"2024-04-09 Not specified 3\n",
|
||||
"2024-04-10 Not specified 2\n",
|
||||
"dtype: int64\n",
|
||||
"\u001B[0m\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"GroupChat select_speaker failed to resolve the next speaker's name. This is because the speaker selection OAI call returned:\n",
|
||||
"CodeEngineer\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mPlanManager\u001B[0m (to Turing)-[]:\n",
|
||||
"\n",
|
||||
"\"Read the result data of the dependent steps in the above historical message to complete the current goal:Create a Markdown table with the grouped data.\"\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"un_stream ai response: To create a Markdown table with the grouped data, we can write a Python function that converts the data into a Markdown table format.\n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"# python code\n",
|
||||
"def create_markdown_table(data):\n",
|
||||
" header = \"| \" + \" | \".join(data.columns) + \" |\"\n",
|
||||
" separator = \"| \" + \" | \".join(\"---\" for _ in data.columns) + \" |\"\n",
|
||||
" rows = [\"| \" + \" | \".join(str(x) for x in row) + \" |\" for row in data.values]\n",
|
||||
" return \"\\n\".join([header, separator] + rows)\n",
|
||||
"\n",
|
||||
"# Assuming the data is stored in a pandas DataFrame named 'df'\n",
|
||||
"print(create_markdown_table(df))\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Please replace the `df` with the actual DataFrame that contains your data. This function will output a Markdown table as a string. The table can be copied and pasted into any Markdown file or Markdown-supported text field.\n",
|
||||
"\u001B[31m\n",
|
||||
">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001B[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"execute_code was called without specifying a value for use_docker. Since the python docker package is not available, code will be run natively. Note: this fallback behavior is subject to change\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mTuring\u001B[0m (to PlanManager)-[gpt-4]:\n",
|
||||
"\n",
|
||||
"\"To create a Markdown table with the grouped data, we can write a Python function that converts the data into a Markdown table format.\\n\\n```python\\n# python code\\ndef create_markdown_table(data):\\n header = \\\"| \\\" + \\\" | \\\".join(data.columns) + \\\" |\\\"\\n separator = \\\"| \\\" + \\\" | \\\".join(\\\"---\\\" for _ in data.columns) + \\\" |\\\"\\n rows = [\\\"| \\\" + \\\" | \\\".join(str(x) for x in row) + \\\" |\\\" for row in data.values]\\n return \\\"\\\\n\\\".join([header, separator] + rows)\\n\\n# Assuming the data is stored in a pandas DataFrame named 'df'\\nprint(create_markdown_table(df))\\n```\\n\\nPlease replace the `df` with the actual DataFrame that contains your data. This function will output a Markdown table as a string. The table can be copied and pasted into any Markdown file or Markdown-supported text field.\"\n",
|
||||
"\u001B[32m>>>>>>>>Turing Review info: \n",
|
||||
"Pass(None)\u001B[0m\n",
|
||||
"\u001B[34m>>>>>>>>Turing Action report: \n",
|
||||
"execution failed,\n",
|
||||
"exitcode: 1 (execution failed)\n",
|
||||
" \n",
|
||||
"Traceback (most recent call last):\n",
|
||||
" File \"\", line 9, in <module>\n",
|
||||
" print(create_markdown_table(df))\n",
|
||||
"NameError: name 'df' is not defined\n",
|
||||
"\u001B[0m\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mPlanManager\u001B[0m (to Turing)-[]:\n",
|
||||
"\n",
|
||||
"\"exitcode: 1 (execution failed)\\n \\nTraceback (most recent call last):\\n File \\\"\\\", line 9, in <module>\\n print(create_markdown_table(df))\\nNameError: name 'df' is not defined\\n\"\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"un_stream ai response: Apologies for the confusion. It seems there was a misunderstanding. The 'df' was a placeholder for your actual data. However, since there's no data provided in the context, I'll assume the data based on the previous responses and create a markdown table. \n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"# python code\n",
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"# Assuming the data is like this:\n",
|
||||
"data = {\n",
|
||||
" 'created_date': ['2024-04-07', '2024-04-08', '2024-04-09', '2024-04-10'],\n",
|
||||
" 'status': ['Not specified', 'Not specified', 'Not specified', 'Not specified'],\n",
|
||||
" 'count': [1, 1, 3, 2]\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"df = pd.DataFrame(data)\n",
|
||||
"\n",
|
||||
"def create_markdown_table(data):\n",
|
||||
" header = \"| \" + \" | \".join(data.columns) + \" |\"\n",
|
||||
" separator = \"| \" + \" | \".join(\"---\" for _ in data.columns) + \" |\"\n",
|
||||
" rows = [\"| \" + \" | \".join(str(x) for x in row) + \" |\" for row in data.values]\n",
|
||||
" return \"\\n\".join([header, separator] + rows)\n",
|
||||
"\n",
|
||||
"print(create_markdown_table(df))\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Please replace the 'data' dictionary with your actual data in the same format. This script will create a markdown table from the given data.\n",
|
||||
"\u001B[31m\n",
|
||||
">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001B[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"execute_code was called without specifying a value for use_docker. Since the python docker package is not available, code will be run natively. Note: this fallback behavior is subject to change\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"un_stream ai response: True\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mTuring\u001B[0m (to PlanManager)-[gpt-4]:\n",
|
||||
"\n",
|
||||
"\"Apologies for the confusion. It seems there was a misunderstanding. The 'df' was a placeholder for your actual data. However, since there's no data provided in the context, I'll assume the data based on the previous responses and create a markdown table. \\n\\n```python\\n# python code\\nimport pandas as pd\\n\\n# Assuming the data is like this:\\ndata = {\\n 'created_date': ['2024-04-07', '2024-04-08', '2024-04-09', '2024-04-10'],\\n 'status': ['Not specified', 'Not specified', 'Not specified', 'Not specified'],\\n 'count': [1, 1, 3, 2]\\n}\\n\\ndf = pd.DataFrame(data)\\n\\ndef create_markdown_table(data):\\n header = \\\"| \\\" + \\\" | \\\".join(data.columns) + \\\" |\\\"\\n separator = \\\"| \\\" + \\\" | \\\".join(\\\"---\\\" for _ in data.columns) + \\\" |\\\"\\n rows = [\\\"| \\\" + \\\" | \\\".join(str(x) for x in row) + \\\" |\\\" for row in data.values]\\n return \\\"\\\\n\\\".join([header, separator] + rows)\\n\\nprint(create_markdown_table(df))\\n```\\n\\nPlease replace the 'data' dictionary with your actual data in the same format. This script will create a markdown table from the given data.\"\n",
|
||||
"\u001B[32m>>>>>>>>Turing Review info: \n",
|
||||
"Pass(None)\u001B[0m\n",
|
||||
"\u001B[34m>>>>>>>>Turing Action report: \n",
|
||||
"execution succeeded,\n",
|
||||
"\n",
|
||||
"| created_date | status | count |\n",
|
||||
"| --- | --- | --- |\n",
|
||||
"| 2024-04-07 | Not specified | 1 |\n",
|
||||
"| 2024-04-08 | Not specified | 1 |\n",
|
||||
"| 2024-04-09 | Not specified | 3 |\n",
|
||||
"| 2024-04-10 | Not specified | 2 |\n",
|
||||
"\u001B[0m\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"\u001B[33mPlanManager\u001B[0m (to User)-[]:\n",
|
||||
"\n",
|
||||
"\"Obtain simple information about issues in the repository 'eosphoros-ai/DB-GPT' in the past three days and analyze the data. Create a Markdown table grouped by day and status.\"\n",
|
||||
"\u001B[32m>>>>>>>>PlanManager Review info: \n",
|
||||
"Pass(None)\u001B[0m\n",
|
||||
"\u001B[34m>>>>>>>>PlanManager Action report: \n",
|
||||
"execution succeeded,\n",
|
||||
"```vis-code\n",
|
||||
"{\"exit_success\": true, \"language\": \"python\", \"code\": [[\"python\", \"# python code\\nimport pandas as pd\\n\\n# Assuming the data is like this:\\ndata = {\\n 'created_date': ['2024-04-07', '2024-04-08', '2024-04-09', '2024-04-10'],\\n 'status': ['Not specified', 'Not specified', 'Not specified', 'Not specified'],\\n 'count': [1, 1, 3, 2]\\n}\\n\\ndf = pd.DataFrame(data)\\n\\ndef create_markdown_table(data):\\n header = \\\"| \\\" + \\\" | \\\".join(data.columns) + \\\" |\\\"\\n separator = \\\"| \\\" + \\\" | \\\".join(\\\"---\\\" for _ in data.columns) + \\\" |\\\"\\n rows = [\\\"| \\\" + \\\" | \\\".join(str(x) for x in row) + \\\" |\\\" for row in data.values]\\n return \\\"\\\\n\\\".join([header, separator] + rows)\\n\\nprint(create_markdown_table(df))\"]], \"log\": \"\\n| created_date | status | count |\\n| --- | --- | --- |\\n| 2024-04-07 | Not specified | 1 |\\n| 2024-04-08 | Not specified | 1 |\\n| 2024-04-09 | Not specified | 3 |\\n| 2024-04-10 | Not specified | 2 |\\n\"}\n",
|
||||
"```\u001B[0m\n",
|
||||
"\n",
|
||||
"--------------------------------------------------------------------------------\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"execution_count": 4
|
||||
"execution_count": 4,
|
||||
"outputs": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
||||
Reference in New Issue
Block a user