mistralai
pixeltable.functions.mistralai
Pixeltable UDFs
that wrap various endpoints from the Mistral AI API. In order to use them, you must
first pip install mistralai
and configure your Mistral AI credentials, as described in
the Working with Mistral AI tutorial.
chat_completions
chat_completions(
messages: JsonT,
*,
model: str,
temperature: Optional[float] = 0.7,
top_p: Optional[float] = 1.0,
max_tokens: Optional[int] = None,
min_tokens: Optional[int] = None,
stop: Optional[JsonT] = None,
random_seed: Optional[int] = None,
response_format: Optional[JsonT] = None,
safe_prompt: Optional[bool] = False
) -> JsonT
Chat Completion API.
Equivalent to the Mistral AI chat/completions
API endpoint.
For additional details, see: https://docs.mistral.ai/api/#tag/chat
Requirements:
pip install mistralai
Parameters:
-
messages
(JsonT
) –The prompt(s) to generate completions for.
-
model
(str
) –ID of the model to use. (See overview here: https://docs.mistral.ai/getting-started/models/)
For details on the other parameters, see: https://docs.mistral.ai/api/#tag/chat
Returns:
-
JsonT
–A dictionary containing the response and other metadata.
Examples:
Add a computed column that applies the model mistral-latest-small
to an existing Pixeltable column tbl.prompt
of the table tbl
:
>>> messages = [{'role': 'user', 'content': tbl.prompt}]
... tbl['response'] = completions(messages, model='mistral-latest-small')
embeddings
embeddings(input: str, *, model: str) -> ArrayT
Embeddings API.
Equivalent to the Mistral AI embeddings
API endpoint.
For additional details, see: https://docs.mistral.ai/api/#tag/embeddings
Requirements:
pip install mistralai
Parameters:
-
input
(str
) –Text to embed.
-
model
(str
) –ID of the model to use. (See overview here: https://docs.mistral.ai/getting-started/models/)
Returns:
-
ArrayT
–An array representing the application of the given embedding to
input
.
fim_completions
fim_completions(
prompt: str,
*,
model: str,
temperature: Optional[float] = 0.7,
top_p: Optional[float] = 1.0,
max_tokens: Optional[int] = None,
min_tokens: Optional[int] = None,
stop: Optional[JsonT] = None,
random_seed: Optional[int] = None,
suffix: Optional[str] = None
) -> JsonT
Fill-in-the-middle Completion API.
Equivalent to the Mistral AI fim/completions
API endpoint.
For additional details, see: https://docs.mistral.ai/api/#tag/fim
Requirements:
pip install mistralai
Parameters:
-
prompt
(str
) –The text/code to complete.
-
model
(str
) –ID of the model to use. (See overview here: https://docs.mistral.ai/getting-started/models/)
For details on the other parameters, see: https://docs.mistral.ai/api/#tag/fim
Returns:
-
JsonT
–A dictionary containing the response and other metadata.
Examples:
Add a computed column that applies the model codestral-latest
to an existing Pixeltable column tbl.prompt
of the table tbl
:
>>> tbl['response'] = completions(tbl.prompt, model='codestral-latest')