chapyter / chapyter Goto Github PK
View Code? Open in Web Editor NEWChapyter: ChatGPT Code Interpreter in Jupyter Notebooks
License: BSD 3-Clause "New" or "Revised" License
Chapyter: ChatGPT Code Interpreter in Jupyter Notebooks
License: BSD 3-Clause "New" or "Revised" License
What is the feature difference between Chapyter and Jupyter-AI (https://github.com/jupyterlab/jupyter-ai)?
Can they coexist?
Please clarify.
Hi there, I want to configure the chapyter. However, when I use %chapyter openai_api_org = 'org-myorg', it's said that:
UsageError: Invalid usage of the chapyter command: openai_api_org = 'org-PrhJLJTejKb36yGXRldiR9RT'. It supports the following usage:
#2 Related to 2
When I run the command %%chat
, the generated code does not execute automatically.
Traceback (most recent call last):
File "E:\anaconda\Lib\site-packages\aiohttp\connector.py", line 980, in _wrap_create_connection
return await self._loop.create_connection(*args, **kwargs) # type: ignore[return-value] # noqa
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\anaconda\Lib\asyncio\base_events.py", line 1085, in create_connection
raise exceptions[0]
File "E:\anaconda\Lib\asyncio\base_events.py", line 1069, in create_connection
sock = await self._connect_sock(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\anaconda\Lib\asyncio\base_events.py", line 973, in _connect_sock
await self.sock_connect(sock, address)
File "E:\anaconda\Lib\asyncio\selector_events.py", line 634, in sock_connect
return await fut
^^^^^^^^^
File "E:\anaconda\Lib\asyncio\futures.py", line 287, in await
yield self # This tells Task to wait for completion.
^^^^^^^^^^
File "E:\anaconda\Lib\asyncio\tasks.py", line 339, in __wakeup
future.result()
File "E:\anaconda\Lib\asyncio\futures.py", line 203, in result
raise self._exception.with_traceback(self._exception_tb)
File "E:\anaconda\Lib\asyncio\selector_events.py", line 674, in _sock_connect_cb
raise OSError(err, f'Connect call failed {address}')
TimeoutError: [Errno 10060] Connect call failed ('199.59.148.6', 443)
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\openai\api_requestor.py", line 668, in arequest_raw
result = await session.request(**request_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\anaconda\Lib\site-packages\aiohttp\client.py", line 536, in _request
conn = await self._connector.connect(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\anaconda\Lib\site-packages\aiohttp\connector.py", line 540, in connect
proto = await self._create_connection(req, traces, timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\anaconda\Lib\site-packages\aiohttp\connector.py", line 901, in _create_connection
_, proto = await self._create_direct_connection(req, traces, timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\anaconda\Lib\site-packages\aiohttp\connector.py", line 1206, in _create_direct_connection
raise last_exc
File "E:\anaconda\Lib\site-packages\aiohttp\connector.py", line 1175, in _create_direct_connection
transp, proto = await self._wrap_create_connection(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\anaconda\Lib\site-packages\aiohttp\connector.py", line 988, in _wrap_create_connection
raise client_error(req.connection_key, exc) from exc
aiohttp.client_exceptions.ClientConnectorError: Cannot connect to host api.openai.com:443 ssl:default [Connect call failed ('199.59.148.6', 443)]
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance_program_executor.py", line 109, in run
await self.visit(self.parse_tree, VariableStack([self.program._variables], self))
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance_program_executor.py", line 559, in visit
visited_children.append(await self.visit(child, variable_stack, inner_next_node, inner_next_next_node, inner_prev_node, node, parent_node))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance_program_executor.py", line 524, in visit
command_output = await command_function(*positional_args, **named_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance\library_assistant.py", line 13, in assistant
return await role(role_name="assistant", hidden=hidden, _parser_context=_parser_context, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance\library_role.py", line 17, in role
new_content += await parser.visit(
^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance_program_executor.py", line 559, in visit
visited_children.append(await self.visit(child, variable_stack, inner_next_node, inner_next_next_node, inner_prev_node, node, parent_node))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance_program_executor.py", line 559, in visit
visited_children.append(await self.visit(child, variable_stack, inner_next_node, inner_next_next_node, inner_prev_node, node, parent_node))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance_program_executor.py", line 266, in visit
visited_children = [await self.visit(child, variable_stack, next_node, next_next_node, prev_node, node, parent_node) for child in node]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance_program_executor.py", line 266, in
visited_children = [await self.visit(child, variable_stack, next_node, next_next_node, prev_node, node, parent_node) for child in node]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance_program_executor.py", line 379, in visit
command_output = await command_function(*positional_args, **named_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance\library_gen.py", line 140, in gen
gen_obj = await parser.llm_session(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance\llms_openai.py", line 665, in call
out = await self.llm.caller(**call_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\guidance\llms_openai.py", line 370, in _library_call
out = await openai.ChatCompletion.acreate(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\openai\api_resources\chat_completion.py", line 45, in acreate
return await super().acreate(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 217, in acreate
response, _, api_key = await requestor.arequest(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\openai\api_requestor.py", line 372, in arequest
result = await self.arequest_raw(
^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\63268\AppData\Roaming\Python\Python311\site-packages\openai\api_requestor.py", line 685, in arequest_raw
raise error.APIConnectionError("Error communicating with OpenAI") from e
openai.error.APIConnectionError: Error communicating with OpenAI
Error in program: Error communicating with OpenAI
I tried a basic test of chapyter but it errors:
%load_ext chapyter
%%chat
hello
Trace:
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
Cell In[2], line 1
----> 1 get_ipython().run_cell_magic('chat', '', '\nhello\n')
File ~/miniconda/lib/python3.10/site-packages/IPython/core/interactiveshell.py:2430, in InteractiveShell.run_cell_magic(self, magic_name, line, cell)
2428 with self.builtin_trap:
2429 args = (magic_arg_s, cell)
-> 2430 result = fn(*args, **kwargs)
2432 # The code below prevents the output from being displayed
2433 # when using magics with decodator @output_can_be_silenced
2434 # when the last Python token in the expression is a ';'.
2435 if getattr(fn, magic.MAGIC_OUTPUT_CAN_BE_SILENCED, False):
File ~/miniconda/lib/python3.10/site-packages/chapyter/magic.py:183, in Chapyter.chat(self, line, cell)
180 return
181 current_message = cell
--> 183 program_out = self.agent.execute_chat(current_message, args, self.shell)
184 execution_id = self.shell.execution_count
185 program_out = f"# Assistant Code for Cell [{execution_id}]:\n" + program_out
File ~/miniconda/lib/python3.10/site-packages/chapyter/magic.py:114, in ChapyterAgent.execute_chat(self, message, args, shell, **kwargs)
106 def execute_chat(
107 self,
108 message: str,
(...)
111 **kwargs,
112 ):
113 program = self.get_program(args, kwargs.get("chatonly", False))
--> 114 llm = self.load_model(args, program)
116 response = program.execute(
117 message=message,
118 llm=llm,
(...)
121 **kwargs,
122 )
123 return response
File ~/miniconda/lib/python3.10/site-packages/chapyter/magic.py:74, in ChapyterAgent.load_model(self, args, program)
71 if program.model_name is not None:
72 model_name = program.model_name
---> 74 return self._load_model(model_name)
File ~/miniconda/lib/python3.10/site-packages/chapyter/magic.py:61, in ChapyterAgent._load_model(self, model_name)
60 def _load_model(self, model_name: Optional[str]) -> guidance.llms.LLM:
---> 61 model = guidance.llms.OpenAI(
62 model_name, organization=os.environ["OPENAI_ORGANIZATION"]
63 )
64 # TODO: Support Azure models
65 return model
File ~/miniconda/lib/python3.10/site-packages/guidance/llms/_openai.py:178, in OpenAI.__init__(self, model, caching, max_retries, max_calls_per_min, api_key, api_type, api_base, api_version, deployment_id, temperature, chat_mode, organization, rest_call, allowed_special_tokens, token, endpoint)
175 api_base = os.environ.get("OPENAI_API_BASE", None) or os.environ.get("OPENAI_ENDPOINT", None) # ENDPOINT is deprecated
177 import tiktoken
--> 178 self._tokenizer = tiktoken.get_encoding(tiktoken.encoding_for_model(model).name)
179 self.chat_mode = chat_mode
181 self.allowed_special_tokens = allowed_special_tokens
File ~/miniconda/lib/python3.10/site-packages/tiktoken/model.py:68, in encoding_for_model(model_name)
65 return get_encoding(model_encoding_name)
67 if encoding_name is None:
---> 68 raise KeyError(
69 f"Could not automatically map {model_name} to a tokeniser. "
70 "Please use `tiktok.get_encoding` to explicitly get the tokeniser you expect."
71 ) from None
73 return get_encoding(encoding_name)
KeyError: 'Could not automatically map gpt-4 to a tokeniser. Please use `tiktok.get_encoding` to explicitly get the tokeniser you expect.'
In the %%chatonly
mode, historical records are supported.
Can you tell me what is in "%chapyter azure_openai_api_base="https://.openai.azure.com/" ?I can't find the introduction for it.
There's no output appearing when used in the Notebook UI in any of the JetBrains IDEs. I assume this is related to #24 but just noting here in case it needs to be handled separately.
Support setting an environment variable for specifying the OpenAI model name to use.
If I want to save pennies by using gpt 3.5 instead of 4, it'd be nice not to have to include "-m gpt-3.5-turbo" in every cell magic invocation.
I'm trying to run Chapyter in Google Colab. After installing with pip and setting the api keys,
the %load_ext chapyter
works, but when I try to run something with %chat
, the command returns no output.
This may be a Python or Jupyter question but I've never encountered this before with an extension so just asking here in case it's related. Why do I need %load_ext chapyter
? I've used lots of extensions and have never encountered the need for %load_ext
before. Most (all) load automatically just by being installed with pip
.
I'm running JupyterLab 4.0.4 on a Mac and trying to use Chapyter.
I have an environment variable OPEN_AI_KEY set and can check this by: echo $OPENAI_API_KEY
Chapyter is installed and in my first cell I have:
%load_ext chapyter
And then:
%%chat
add numbers from 1 to 10
I get this error:
assert openai.api_key is not None, "You must provide an OpenAI API key to use the OpenAI LLM. Either pass it in the constructor, set the OPENAI_API_KEY environment variable, or create the file ~/.openai_api_key with your key in it."
I have passed in the API KEY and loaded the extension, when I tried to run
%%chat -m gpt-4-0613
List all the files in the folder
It raises this error.
Please add base url support for using openai of Azure.
OPENAI_BASE_URL=xxx
OPENAI_API_KEY=sk-xxxx
OPENAI_ORGANIZATION=org-xxxx
Of course, direct support for Azure is also possible.
https://learn.microsoft.com/en-us/azure/cognitive-services/openai/quickstart?tabs=command-line&pivots=programming-language-python
Can i use Llama 2 instead of chatGpt 4, is it even possible here?
its a silly question but I have to ask. I do not know much.
Thanks
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.