# cosette
## Install
``` sh
pip install cosette
```
## Getting started
OpenAI’s Python SDK will automatically be installed with Cosette, if you
don’t already have it.
``` python
from cosette import *
```
Cosette only exports the symbols that are needed to use the library, so
you can use `import *` to import them. Alternatively, just use:
``` python
import cosette
```
…and then add the prefix `cosette.` to any usages of the module.
Cosette provides `models`, which is a list of models currently available
from the SDK.
``` python
' '.join(models)
```
For these examples, we’ll use GPT-5-mini.
``` python
model = first(m for m in models if 'mini' in m)
```
## Chat
The main interface to Cosette is the
[`Chat`](https://AnswerDotAI.github.io/cosette/core.html#chat) class,
which provides a stateful interface to the models. You can pass message
keywords to either
[`Chat`](https://AnswerDotAI.github.io/cosette/core.html#chat) or when
you call the model.
``` python
chatkw = dict(
text={ "verbosity": "low" },
reasoning={ "effort": "minimal" }
)
```
``` python
chat = Chat(model, sp="You are a helpful and concise assistant.", **chatkw)
chat("I'm Jeremy")
```
Nice to meet you, Jeremy. How can I help you today?
- id: resp_0d3d0fd9abbe53b800691bb8f36a8081a287420e10bd559959
- created_at: 1763424499.0
- error: None
- incomplete_details: None
- instructions: You are a helpful and concise assistant.
- metadata: {}
- model: gpt-5-mini-2025-08-07
- object: response
- output:
\[ResponseReasoningItem(id=‘rs_0d3d0fd9abbe53b800691bb8f3f96481a2b973102cdd2f71ae’,
summary=\[\], type=‘reasoning’, content=None, encrypted_content=None,
status=None),
ResponseOutputMessage(id=‘msg_0d3d0fd9abbe53b800691bb8f42c2081a2844a8c1c40c9e319’,
content=\[ResponseOutputText(annotations=\[\], text=‘Nice to meet you,
Jeremy. How can I help you today?’, type=‘output_text’,
logprobs=\[\])\], role=‘assistant’, status=‘completed’,
type=‘message’)\]
- parallel_tool_calls: True
- temperature: 1.0
- tool_choice: auto
- tools: \[\]
- top_p: 1.0
- background: False
- conversation: None
- max_output_tokens: 4096
- max_tool_calls: None
- previous_response_id: None
- prompt: None
- prompt_cache_key: None
- prompt_cache_retention: None
- reasoning: Reasoning(effort=‘minimal’, generate_summary=None,
summary=None)
- safety_identifier: None
- service_tier: default
- status: completed
- text: ResponseTextConfig(format=ResponseFormatText(type=‘text’),
verbosity=‘low’)
- top_logprobs: 0
- truncation: disabled
- usage: ResponseUsage(input_tokens=20,
input_tokens_details=InputTokensDetails(cached_tokens=0),
output_tokens=20,
output_tokens_details=OutputTokensDetails(reasoning_tokens=0),
total_tokens=40)
- user: None
- billing: {‘payer’: ‘developer’}
- store: True
``` python
r = chat("What's my name?")
r
```
Your name is Jeremy.
- id: resp_0d3d0fd9abbe53b800691bb8f4f94481a2810c8643c0b3d40a
- created_at: 1763424500.0
- error: None
- incomplete_details: None
- instructions: You are a helpful and concise assistant.
- metadata: {}
- model: gpt-5-mini-2025-08-07
- object: response
- output:
\[ResponseReasoningItem(id=‘rs_0d3d0fd9abbe53b800691bb8f60dfc81a29e49561b99db8e9f’,
summary=\[\], type=‘reasoning’, content=None, encrypted_content=None,
status=None),
ResponseOutputMessage(id=‘msg_0d3d0fd9abbe53b800691bb8f63d2881a29391dc42f032a3ed’,
content=\[ResponseOutputText(annotations=\[\], text=‘Your name is
Jeremy.’, type=‘output_text’, logprobs=\[\])\], role=‘assistant’,
status=‘completed’, type=‘message’)\]
- parallel_tool_calls: True
- temperature: 1.0
- tool_choice: auto
- tools: \[\]
- top_p: 1.0
- background: False
- conversation: None
- max_output_tokens: 4096
- max_tool_calls: None
- previous_response_id: None
- prompt: None
- prompt_cache_key: None
- prompt_cache_retention: None
- reasoning: Reasoning(effort=‘minimal’, generate_summary=None,
summary=None)
- safety_identifier: None
- service_tier: default
- status: completed
- text: ResponseTextConfig(format=ResponseFormatText(type=‘text’),
verbosity=‘low’)
- top_logprobs: 0
- truncation: disabled
- usage: ResponseUsage(input_tokens=48,
input_tokens_details=InputTokensDetails(cached_tokens=0),
output_tokens=11,
output_tokens_details=OutputTokensDetails(reasoning_tokens=0),
total_tokens=59)
- user: None
- billing: {‘payer’: ‘developer’}
- store: True
As you see above, displaying the results of a call in a notebook shows
just the message contents, with the other details hidden behind a
collapsible section. Alternatively you can `print` the details:
``` python
print(r)
```
Response(id='resp_0d3d0fd9abbe53b800691bb8f4f94481a2810c8643c0b3d40a', created_at=1763424500.0, error=None, incomplete_details=None, instructions='You are a helpful and concise assistant.', metadata={}, model='gpt-5-mini-2025-08-07', object='response', output=[ResponseReasoningItem(id='rs_0d3d0fd9abbe53b800691bb8f60dfc81a29e49561b99db8e9f', summary=[], type='reasoning', content=None, encrypted_content=None, status=None), ResponseOutputMessage(id='msg_0d3d0fd9abbe53b800691bb8f63d2881a29391dc42f032a3ed', content=[ResponseOutputText(annotations=[], text='Your name is Jeremy.', type='output_text', logprobs=[])], role='assistant', status='completed', type='message')], parallel_tool_calls=True, temperature=1.0, tool_choice='auto', tools=[], top_p=1.0, background=False, conversation=None, max_output_tokens=4096, max_tool_calls=None, previous_response_id=None, prompt=None, prompt_cache_key=None, prompt_cache_retention=None, reasoning=Reasoning(effort='minimal', generate_summary=None, summary=None), safety_identifier=None, service_tier='default', status='completed', text=ResponseTextConfig(format=ResponseFormatText(type='text'), verbosity='low'), top_logprobs=0, truncation='disabled', usage=In: 48; Out: 11; Total: 59, user=None, billing={'payer': 'developer'}, store=True)
You can use `stream=True` to stream the results as soon as they arrive
(although you will only see the gradual generation if you execute the
notebook yourself, of course!)
``` python
for o in chat("What's your name?", stream=True): print(o, end='')
```
I'm ChatGPT.
## Model Capabilities
Different OpenAI models have different capabilities. Some models such as
o1-mini do not have support for streaming, system prompts, or
temperature. Query these capbilities using these functions:
``` python
# o1 does not support streaming or setting the temperature
can_stream('o1'), can_set_sp('o1'), can_set_temp('o1')
```
(True, True, False)
``` python
# gpt-4o has these capabilities
can_stream('gpt-4o'), can_set_sp('gpt-4o'), can_set_temp('gpt-4o')
```
(True, True, True)
## Tool use
[Tool use](https://docs.openai.com/claude/docs/tool-use) lets the model
use external tools.
We use [docments](https://fastcore.fast.ai/docments.html) to make
defining Python functions as ergonomic as possible. Each parameter (and
the return value) should have a type, and a docments comment with the
description of what it is. As an example we’ll write a simple function
that adds numbers together, and will tell us when it’s being called:
``` python
def sums(
a:int, # First thing to sum
b:int=1 # Second thing to sum
) -> int: # The sum of the inputs
"Adds a + b."
print(f"Finding the sum of {a} and {b}")
return a + b
```
Sometimes the model will say something like “according to the `sums`
tool the answer is” – generally we’d rather it just tells the user the
answer, so we can use a system prompt to help with this:
``` python
sp = "Never mention what tools you use."
```
We’ll get the model to add up some long numbers:
``` python
a,b = 604542,6458932
pr = f"What is {a}+{b}?"
pr
```
'What is 604542+6458932?'
To use tools, pass a list of them to
[`Chat`](https://AnswerDotAI.github.io/cosette/core.html#chat):
``` python
chat = Chat(model, sp=sp, tools=[sums], **chatkw)
```
Now when we call that with our prompt, the model doesn’t return the
answer, but instead returns a `tool_use` message, which means we have to
call the named tool with the provided parameters:
``` python
r = chat(pr)
r.output
```
Finding the sum of 604542 and 6458932
[ResponseReasoningItem(id='rs_0e80f673f989086700691bb8f93f808196a2d8be5fabc7ab32', summary=[], type='reasoning', content=None, encrypted_content=None, status=None),
ResponseFunctionToolCall(arguments='{"a":604542,"b":6458932}', call_id='call_G8jd6G7UGQtVFcJHiCYfLN8b', name='sums', type='function_call', id='fc_0e80f673f989086700691bb8f9f3dc81969e7bfce86b2e8cdc', status='completed')]
Cosette handles all that for us – we just have to pass along the
message, and it all happens automatically:
``` python
chat()
```
7,063,474
- id: resp_0e80f673f989086700691bb8fb04ec8196854dd7610c320811
- created_at: 1763424507.0
- error: None
- incomplete_details: None
- instructions: Never mention what tools you use.
- metadata: {}
- model: gpt-5-mini-2025-08-07
- object: response
- output:
\[ResponseOutputMessage(id=‘msg_0e80f673f989086700691bb8fbaf4081969d32466017fe56b9’,
content=\[ResponseOutputText(annotations=\[\], text=‘7,063,474’,
type=‘output_text’, logprobs=\[\])\], role=‘assistant’,
status=‘completed’, type=‘message’)\]
- parallel_tool_calls: True
- temperature: 1.0
- tool_choice: auto
- tools: \[FunctionTool(name=‘sums’, parameters={‘type’: ‘object’,
‘properties’: {‘a’: {‘type’: ‘integer’, ‘description’: ‘First thing to
sum’}, ‘b’: {‘type’: ‘integer’, ‘description’: ‘Second thing to sum’,
‘default’: 1}}, ‘required’: \[‘a’, ‘b’\], ‘additionalProperties’:
False}, strict=True, type=‘function’, description=‘Adds a + b.:- type:
integer’)\]
- top_p: 1.0
- background: False
- conversation: None
- max_output_tokens: 4096
- max_tool_calls: None
- previous_response_id: None
- prompt: None
- prompt_cache_key: None
- prompt_cache_retention: None
- reasoning: Reasoning(effort=‘minimal’, generate_summary=None,
summary=None)
- safety_identifier: None
- service_tier: default
- status: completed
- text: ResponseTextConfig(format=ResponseFormatText(type=‘text’),
verbosity=‘low’)
- top_logprobs: 0
- truncation: disabled
- usage: ResponseUsage(input_tokens=142,
input_tokens_details=InputTokensDetails(cached_tokens=0),
output_tokens=9,
output_tokens_details=OutputTokensDetails(reasoning_tokens=0),
total_tokens=151)
- user: None
- billing: {‘payer’: ‘developer’}
- store: True
You can see how many tokens have been used at any time by checking the
`use` property.
``` python
chat.use
```
In: 231; Out: 36; Total: 267
### Tool loop
``` python
def show(x):
if getattr(x, 'output_text', None): display(x)
```
We can do everything needed to use tools in a single step, by using
[`Chat.toolloop`](https://AnswerDotAI.github.io/cosette/toolloop.html#chat.toolloop).
This can even call multiple tools as needed solve a problem. For
example, let’s define a tool to handle multiplication:
``` python
def mults(
a:int, # First thing to multiply
b:int=1 # Second thing to multiply
) -> int: # The product of the inputs
"Multiplies a * b."
print(f"Finding the product of {a} and {b}")
return a * b
```
Now with a single call we can calculate `(a+b)*2`:
``` python
chat = Chat(model, tools=[sums,mults], **chatkw)
pr = f'Calculate ({a}+{b})*2 and display the result as US$'
pr
```
'Calculate (604542+6458932)*2 and display the result as US$'
``` python
r = chat.toolloop(pr)
```
``` python
for o in r: show(o)
```
Finding the sum of 604542 and 6458932
Finding the product of 7063474 and 2
US$14,126,948
- id: resp_0b2a84d51ad623c400691bb900c6d08195b323fdb870a37bec
- created_at: 1763424512.0
- error: None
- incomplete_details: None
- instructions: None
- metadata: {}
- model: gpt-5-mini-2025-08-07
- object: response
- output:
\[ResponseOutputMessage(id=‘msg_0b2a84d51ad623c400691bb9014e088195b6bf52d37fafebf7’,
content=\[ResponseOutputText(annotations=\[\], text=‘US$14,126,948’,
type=‘output_text’, logprobs=\[\])\], role=‘assistant’,
status=‘completed’, type=‘message’)\]
- parallel_tool_calls: True
- temperature: 1.0
- tool_choice: auto
- tools: \[FunctionTool(name=‘sums’, parameters={‘type’: ‘object’,
‘properties’: {‘a’: {‘type’: ‘integer’, ‘description’: ‘First thing to
sum’}, ‘b’: {‘type’: ‘integer’, ‘description’: ‘Second thing to sum’,
‘default’: 1}}, ‘required’: \[‘a’, ‘b’\], ‘additionalProperties’:
False}, strict=True, type=‘function’, description=‘Adds a + b.:- type:
integer’), FunctionTool(name=‘mults’, parameters={‘type’: ‘object’,
‘properties’: {‘a’: {‘type’: ‘integer’, ‘description’: ‘First thing to
multiply’}, ‘b’: {‘type’: ‘integer’, ‘description’: ‘Second thing to
multiply’, ‘default’: 1}}, ‘required’: \[‘a’, ‘b’\],
‘additionalProperties’: False}, strict=True, type=‘function’,
description=‘Multiplies a \* b.:- type: integer’)\]
- top_p: 1.0
- background: False
- conversation: None
- max_output_tokens: 4096
- max_tool_calls: None
- previous_response_id: None
- prompt: None
- prompt_cache_key: None
- prompt_cache_retention: None
- reasoning: Reasoning(effort=‘minimal’, generate_summary=None,
summary=None)
- safety_identifier: None
- service_tier: default
- status: completed
- text: ResponseTextConfig(format=ResponseFormatText(type=‘text’),
verbosity=‘low’)
- top_logprobs: 0
- truncation: disabled
- usage: ResponseUsage(input_tokens=225,
input_tokens_details=InputTokensDetails(cached_tokens=0),
output_tokens=11,
output_tokens_details=OutputTokensDetails(reasoning_tokens=0),
total_tokens=236)
- user: None
- billing: {‘payer’: ‘developer’}
- store: True
## Images
As everyone knows, when testing image APIs you have to use a cute puppy.
``` python
fn = Path('samples/puppy.jpg')
Image(filename=fn, width=200)
```
We create a
[`Chat`](https://AnswerDotAI.github.io/cosette/core.html#chat) object as
before:
``` python
chat = Chat(model, **chatkw)
```
Claudia expects images as a list of bytes, so we read in the file:
``` python
img = fn.read_bytes()
```
Prompts to Claudia can be lists, containing text, images, or both, eg:
``` python
chat([img, "In brief, what color flowers are in this image?"])
```
They are purple.
- id: resp_07fbd059d2633f7000691bb902fd98819194e5dbe9d2bb9909
- created_at: 1763424515.0
- error: None
- incomplete_details: None
- instructions: None
- metadata: {}
- model: gpt-5-mini-2025-08-07
- object: response
- output:
\[ResponseReasoningItem(id=‘rs_07fbd059d2633f7000691bb90390cc819181e8ec1955d1f7ed’,
summary=\[\], type=‘reasoning’, content=None, encrypted_content=None,
status=None),
ResponseOutputMessage(id=‘msg_07fbd059d2633f7000691bb903d1b081918d272dbb0556c7d0’,
content=\[ResponseOutputText(annotations=\[\], text=‘They are
purple.’, type=‘output_text’, logprobs=\[\])\], role=‘assistant’,
status=‘completed’, type=‘message’)\]
- parallel_tool_calls: True
- temperature: 1.0
- tool_choice: auto
- tools: \[\]
- top_p: 1.0
- background: False
- conversation: None
- max_output_tokens: 4096
- max_tool_calls: None
- previous_response_id: None
- prompt: None
- prompt_cache_key: None
- prompt_cache_retention: None
- reasoning: Reasoning(effort=‘minimal’, generate_summary=None,
summary=None)
- safety_identifier: None
- service_tier: default
- status: completed
- text: ResponseTextConfig(format=ResponseFormatText(type=‘text’),
verbosity=‘low’)
- top_logprobs: 0
- truncation: disabled
- usage: ResponseUsage(input_tokens=102,
input_tokens_details=InputTokensDetails(cached_tokens=0),
output_tokens=10,
output_tokens_details=OutputTokensDetails(reasoning_tokens=0),
total_tokens=112)
- user: None
- billing: {‘payer’: ‘developer’}
- store: True
The image is included as input tokens.
``` python
chat.use
```
In: 102; Out: 10; Total: 112
Alternatively, Cosette supports creating a multi-stage chat with
separate image and text prompts. For instance, you can pass just the
image as the initial prompt (in which case the model will make some
general comments about what it sees), and then follow up with questions
in additional prompts:
``` python
chat = Chat(model, **chatkw)
chat(img)
```
This is a small puppy lying on grass next to purple flowers. It has
white fur with brown patches, long floppy ears, and dark eyes—appears to
be a young spaniel-type dog (e.g., Cavalier King Charles Spaniel).
- id: resp_04ca2ec79ffca3d500691bb904744c81958f7812565de27daa
- created_at: 1763424516.0
- error: None
- incomplete_details: None
- instructions: None
- metadata: {}
- model: gpt-5-mini-2025-08-07
- object: response
- output:
\[ResponseReasoningItem(id=‘rs_04ca2ec79ffca3d500691bb904d1fc8195a696751f6ac10748’,
summary=\[\], type=‘reasoning’, content=None, encrypted_content=None,
status=None),
ResponseOutputMessage(id=‘msg_04ca2ec79ffca3d500691bb90503008195ac8efa68f28eccd1’,
content=\[ResponseOutputText(annotations=\[\], text=‘This is a small
puppy lying on grass next to purple flowers. It has white fur with
brown patches, long floppy ears, and dark eyes—appears to be a young
spaniel-type dog (e.g., Cavalier King Charles Spaniel).’,
type=‘output_text’, logprobs=\[\])\], role=‘assistant’,
status=‘completed’, type=‘message’)\]
- parallel_tool_calls: True
- temperature: 1.0
- tool_choice: auto
- tools: \[\]
- top_p: 1.0
- background: False
- conversation: None
- max_output_tokens: 4096
- max_tool_calls: None
- previous_response_id: None
- prompt: None
- prompt_cache_key: None
- prompt_cache_retention: None
- reasoning: Reasoning(effort=‘minimal’, generate_summary=None,
summary=None)
- safety_identifier: None
- service_tier: default
- status: completed
- text: ResponseTextConfig(format=ResponseFormatText(type=‘text’),
verbosity=‘low’)
- top_logprobs: 0
- truncation: disabled
- usage: ResponseUsage(input_tokens=92,
input_tokens_details=InputTokensDetails(cached_tokens=0),
output_tokens=56,
output_tokens_details=OutputTokensDetails(reasoning_tokens=0),
total_tokens=148)
- user: None
- billing: {‘payer’: ‘developer’}
- store: True
``` python
chat('What direction is the puppy facing?')
```
The puppy is facing toward the camera (front-facing).
- id: resp_04ca2ec79ffca3d500691bb906d068819599b648197ed3ff12
- created_at: 1763424518.0
- error: None
- incomplete_details: None
- instructions: None
- metadata: {}
- model: gpt-5-mini-2025-08-07
- object: response
- output:
\[ResponseReasoningItem(id=‘rs_04ca2ec79ffca3d500691bb9078c048195861906ac7c42938a’,
summary=\[\], type=‘reasoning’, content=None, encrypted_content=None,
status=None),
ResponseOutputMessage(id=‘msg_04ca2ec79ffca3d500691bb907b5188195a62b8261e5561acb’,
content=\[ResponseOutputText(annotations=\[\], text=‘The puppy is
facing toward the camera (front-facing).’, type=‘output_text’,
logprobs=\[\])\], role=‘assistant’, status=‘completed’,
type=‘message’)\]
- parallel_tool_calls: True
- temperature: 1.0
- tool_choice: auto
- tools: \[\]
- top_p: 1.0
- background: False
- conversation: None
- max_output_tokens: 4096
- max_tool_calls: None
- previous_response_id: None
- prompt: None
- prompt_cache_key: None
- prompt_cache_retention: None
- reasoning: Reasoning(effort=‘minimal’, generate_summary=None,
summary=None)
- safety_identifier: None
- service_tier: default
- status: completed
- text: ResponseTextConfig(format=ResponseFormatText(type=‘text’),
verbosity=‘low’)
- top_logprobs: 0
- truncation: disabled
- usage: ResponseUsage(input_tokens=159,
input_tokens_details=InputTokensDetails(cached_tokens=0),
output_tokens=17,
output_tokens_details=OutputTokensDetails(reasoning_tokens=0),
total_tokens=176)
- user: None
- billing: {‘payer’: ‘developer’}
- store: True
``` python
chat('What color is it?')
```
The puppy is mostly white with brown patches (especially on the ears and
around the eyes).
- id: resp_04ca2ec79ffca3d500691bb90888b8819596a6c054a1750183
- created_at: 1763424520.0
- error: None
- incomplete_details: None
- instructions: None
- metadata: {}
- model: gpt-5-mini-2025-08-07
- object: response
- output:
\[ResponseReasoningItem(id=‘rs_04ca2ec79ffca3d500691bb9093cc48195baa2c98e9038941c’,
summary=\[\], type=‘reasoning’, content=None, encrypted_content=None,
status=None),
ResponseOutputMessage(id=‘msg_04ca2ec79ffca3d500691bb90965b48195ba6d501e5be77817’,
content=\[ResponseOutputText(annotations=\[\], text=‘The puppy is
mostly white with brown patches (especially on the ears and around the
eyes).’, type=‘output_text’, logprobs=\[\])\], role=‘assistant’,
status=‘completed’, type=‘message’)\]
- parallel_tool_calls: True
- temperature: 1.0
- tool_choice: auto
- tools: \[\]
- top_p: 1.0
- background: False
- conversation: None
- max_output_tokens: 4096
- max_tool_calls: None
- previous_response_id: None
- prompt: None
- prompt_cache_key: None
- prompt_cache_retention: None
- reasoning: Reasoning(effort=‘minimal’, generate_summary=None,
summary=None)
- safety_identifier: None
- service_tier: default
- status: completed
- text: ResponseTextConfig(format=ResponseFormatText(type=‘text’),
verbosity=‘low’)
- top_logprobs: 0
- truncation: disabled
- usage: ResponseUsage(input_tokens=185,
input_tokens_details=InputTokensDetails(cached_tokens=0),
output_tokens=24,
output_tokens_details=OutputTokensDetails(reasoning_tokens=0),
total_tokens=209)
- user: None
- billing: {‘payer’: ‘developer’}
- store: True
Note that the image is passed in again for every input in the dialog, so
that number of input tokens increases quickly with this kind of chat.
``` python
chat.use
```
In: 436; Out: 97; Total: 533
## Other providers
Here’s an example of using the library with Groq:
``` python
groq_c = Client(
model="openai/gpt-oss-20b",
api_key_env="GROQ_KEY",
base_url="https://api.groq.com/openai/v1"
)
groq_c("Hello! What's 2+2?")
```
Sure! 2 + 2 equals **4**.
- id: resp_01kaa4wr25fb9sg6j2t0h74115
- created_at: 1763424755.0
- error: None
- incomplete_details: None
- instructions:
- metadata: {}
- model: openai/gpt-oss-20b
- object: response
- output: \[ResponseReasoningItem(id=‘resp_01kaa4wr25fba9v3q7sqdmnmhr’,
summary=\[\], type=‘reasoning’, content=\[Content(text=‘We need to
respond as ChatGPT with a friendly answer: 2+2=4. Ensure no policy
conflicts.’, type=‘reasoning_text’)\], encrypted_content=None,
status=‘completed’),
ResponseOutputMessage(id=‘msg_01kaa4wr25fbas7kjb537b2yw1’,
content=\[ResponseOutputText(annotations=\[\], text=‘Sure! 202f+02f2
equals **4**.’, type=‘output_text’, logprobs=None)\],
role=‘assistant’, status=‘completed’, type=‘message’)\]
- parallel_tool_calls: True
- temperature: 1.0
- tool_choice: auto
- tools: \[\]
- top_p: 1.0
- background: False
- conversation: None
- max_output_tokens: 4096
- max_tool_calls: None
- previous_response_id: None
- prompt: None
- prompt_cache_key: None
- prompt_cache_retention: None
- reasoning: Reasoning(effort=‘medium’, generate_summary=None,
summary=None)
- safety_identifier: None
- service_tier: default
- status: completed
- text: ResponseTextConfig(format=ResponseFormatText(type=‘text’),
verbosity=None)
- top_logprobs: None
- truncation: disabled
- usage: ResponseUsage(input_tokens=79,
input_tokens_details=InputTokensDetails(cached_tokens=0),
output_tokens=47,
output_tokens_details=OutputTokensDetails(reasoning_tokens=25),
total_tokens=126)
- user: None
- store: False
``` python
gchat = Chat(cli=groq_c)
gchat("Hello! I'm Jeremy")
```
Hello Jeremy! How can I help you today?
- id: resp_01kaa4wsaze4ms5ezjrezw1baa
- created_at: 1763424757.0
- error: None
- incomplete_details: None
- instructions:
- metadata: {}
- model: openai/gpt-oss-20b
- object: response
- output: \[ResponseReasoningItem(id=‘resp_01kaa4wsaze4n9hze8pq6vvv75’,
summary=\[\], type=‘reasoning’, content=\[Content(text=‘User: “Hello!
I'm Jeremy” We can greet. Possibly ask how can help.’,
type=‘reasoning_text’)\], encrypted_content=None, status=‘completed’),
ResponseOutputMessage(id=‘msg_01kaa4wsaze4nsb4xcv927zww0’,
content=\[ResponseOutputText(annotations=\[\], text=‘Hello Jeremy! How
can I help you today?’, type=‘output_text’, logprobs=None)\],
role=‘assistant’, status=‘completed’, type=‘message’)\]
- parallel_tool_calls: True
- temperature: 1.0
- tool_choice: auto
- tools: \[\]
- top_p: 1.0
- background: False
- conversation: None
- max_output_tokens: 4096
- max_tool_calls: None
- previous_response_id: None
- prompt: None
- prompt_cache_key: None
- prompt_cache_retention: None
- reasoning: Reasoning(effort=‘medium’, generate_summary=None,
summary=None)
- safety_identifier: None
- service_tier: default
- status: completed
- text: ResponseTextConfig(format=ResponseFormatText(type=‘text’),
verbosity=None)
- top_logprobs: None
- truncation: disabled
- usage: ResponseUsage(input_tokens=75,
input_tokens_details=InputTokensDetails(cached_tokens=0),
output_tokens=38,
output_tokens_details=OutputTokensDetails(reasoning_tokens=19),
total_tokens=113)
- user: None
- store: False
``` python
gchat("What's my name?")
```
You’re Jeremy!
- id: resp_01kaa4wtmcfbrb3fn5vzpd2fvy
- created_at: 1763424758.0
- error: None
- incomplete_details: None
- instructions:
- metadata: {}
- model: openai/gpt-oss-20b
- object: response
- output: \[ResponseReasoningItem(id=‘resp_01kaa4wtmcfbrrd02tzsq8z47y’,
summary=\[\], type=‘reasoning’, content=\[Content(text=‘User asks
“What's my name?” The name is Jeremy from the greeting. So answer:
Jeremy.’, type=‘reasoning_text’)\], encrypted_content=None,
status=‘completed’),
ResponseOutputMessage(id=‘msg_01kaa4wtmcfbs8pa0xnvdkdkpq’,
content=\[ResponseOutputText(annotations=\[\], text=‘You’re Jeremy!’,
type=‘output_text’, logprobs=None)\], role=‘assistant’,
status=‘completed’, type=‘message’)\]
- parallel_tool_calls: True
- temperature: 1.0
- tool_choice: auto
- tools: \[\]
- top_p: 1.0
- background: False
- conversation: None
- max_output_tokens: 4096
- max_tool_calls: None
- previous_response_id: None
- prompt: None
- prompt_cache_key: None
- prompt_cache_retention: None
- reasoning: Reasoning(effort=‘medium’, generate_summary=None,
summary=None)
- safety_identifier: None
- service_tier: default
- status: completed
- text: ResponseTextConfig(format=ResponseFormatText(type=‘text’),
verbosity=None)
- top_logprobs: None
- truncation: disabled
- usage: ResponseUsage(input_tokens=99,
input_tokens_details=InputTokensDetails(cached_tokens=0),
output_tokens=34,
output_tokens_details=OutputTokensDetails(reasoning_tokens=21),
total_tokens=133)
- user: None
- store: False