Openai model "gpt-3.5-turbo-0613" streaming=True raise error

[HalfMAI]

The bug Using "gpt-3.5-turbo" won't raise error but not streaming result #244

Using "gpt-3.5-turbo-0613" raise this error:

Traceback (most recent call last):
  File "d:\test\.venv\lib\site-packages\guidance\_program_executor.py", line 111, in run
    await self.visit(self.parse_tree, VariableStack([self.program._variables], self))
  File "d:\test\.venv\lib\site-packages\guidance\_program_executor.py", line 535, 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 "d:\test\.venv\lib\site-packages\guidance\_program_executor.py", line 500, in visit
    command_output = await command_function(*positional_args, **named_args)
  File "d:\test\.venv\lib\site-packages\guidance\library\_assistant.py", line 13, in assistant
    return await role(name="assistant", hidden=hidden, _parser_context=_parser_context)
  File "d:\test\.venv\lib\site-packages\guidance\library\_role.py", line 17, in role
    new_content += await parser.visit(
  File "d:\test\.venv\lib\site-packages\guidance\_program_executor.py", line 535, 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 "d:\test\.venv\lib\site-packages\guidance\_program_executor.py", line 535, 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 "d:\test\.venv\lib\site-packages\guidance\_program_executor.py", line 256, 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 "d:\test\.venv\lib\site-packages\guidance\_program_executor.py", line 256, in <listcomp>
    visited_children = [await self.visit(child, variable_stack, next_node, next_next_node, prev_node, node, parent_node) for child in node]
  File "d:\test\.venv\lib\site-packages\guidance\_program_executor.py", line 353, in visit
    command_output = await command_function(*positional_args, **named_args)
  File "d:\test\.venv\lib\site-packages\guidance\library\_gen.py", line 163, in gen
    async for resp in gen_obj:
  File "d:\test\.venv\lib\site-packages\guidance\llms\_openai.py", line 186, in stream_then_save
    async for curr_out in gen:
  File "d:\test\.venv\lib\site-packages\guidance\llms\_openai.py", line 45, in add_text_to_chat_mode_generator
    c['text'] = c['delta']['content']
  File "d:\test\.venv\lib\site-packages\openai\openai_object.py", line 71, in __setitem__
    raise ValueError(
ValueError: You cannot set text to an empty string. We interpret empty strings as None in requests.You may set {
  "delta": {
    "content": "",
    "role": "assistant"
  },
  "finish_reason": null,
  "index": 0
}.text = None to delete the property

Error in program:  You cannot set text to an empty string. We interpret empty strings as None in requests.You may set {
  "delta": {
    "content": "",
    "role": "assistant"
  },
  "finish_reason": null,
  "index": 0
}.text = None to delete the property

To Reproduce Give a full working code snippet that can be pasted into a notebook cell or python file. Make sure to include the LLM load step so we know which model you are using.

import guidance
guidance.llm = guidance.llms.OpenAI("gpt-3.5-turbo-0613")
program = guidance('''
{{#system~}}
You are helpful assistant.
{{~/system}}
{{#user}}
Write me a long poem.
{{/user}}
{{#assistant~}}
    {{gen "answer" save_prompt="prompt" max_tokens=300}}
{{~/assistant}}
''') # type: ignore

pos = 0
for p in program(stream=True, silent=True, caching=False):
    val = p.get("answer", "")
    print(val[pos:], end="", flush=True)
    pos = len(val)

System info (please complete the following information):

• OS (e.g. Ubuntu, Windows 11, Mac OS, etc.):
  • Windows 11, Python 3.10.4
• Guidance Version (guidance.__version__):
  • '0.0.63'

[HalfMAI]

Version 0.0.64 fixed