+ ~jz^RIHt^RIHtHtHtHt^RIHtH t ^RI t ^RI H t ^RI Ht^RIHtHtHtHtHtHtHtHt^RIHtHtHt^R IHt^R IHtH t ^R I!H"t"H#t#^R I$H%t%H&t&^R I'H(t(^RI)H*t*^RI+H,t,RR.t-!RR]4t.!RR] 4t/!RR4t0!RR4t1!RR4t2!RR4t3R#)) annotations)DictUnionIterableOptional)LiteraloverloadN)_legacy_response)completion_create_params)BodyOmitQueryHeadersNotGivenSequenceNotStromit not_given) required_argsmaybe_transformasync_maybe_transform)cached_property)SyncAPIResourceAsyncAPIResource)to_streamed_response_wrapper"async_to_streamed_response_wrapper)Stream AsyncStream)make_request_options) Completion) ChatCompletionStreamOptionsParam CompletionsAsyncCompletionsc)]tRt^tRt]RRl4t]RRl4t]R] R] R] R ] R ] R ] R ] R ] R] R] R] R] R] R] R] R] RRRRRRR] /RRll4t ]R] R] R] R ] R ] R ] R ] R ] R] R] R] R] R] R] R] RRRRRRR] /RRll4t ]R] R] R] R ] R ] R ] R ] R ] R] R] R] R] R] R] R] RRRRRRR] /RR ll4t ] !R!R"..R&O4R] R] R] R ] R ] R ] R ] R ] R] R] R] R] R] R] R] R] RRRRRRR] /R#R$ll4t R%t R#)'r! Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position. cV^8dQhRR/#)returnCompletionsWithRawResponse)formats"q/Users/mitch_tango/dev/rabbit-r1-livekit/agent/.venv/lib/python3.14/site-packages/openai/resources/completions.py __annotate__Completions.__annotate__!s00#=0c \V4#z This property can be used as a prefix for any HTTP method call to return the raw response object instead of the parsed content. For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers )r(selfs&r+with_raw_responseCompletions.with_raw_response s*$//r.cV^8dQhRR/#)r&r' CompletionsWithStreamingResponser))r*s"r+r,r-+s66)I6r.c \V4#z An alternative to `.with_raw_response` that doesn't eagerly read the response body. For more information, see https://www.github.com/openai/openai-python#with_streaming_response )r6r1s&r+with_streaming_response#Completions.with_streaming_response*s055r.best_ofechofrequency_penalty logit_biaslogprobs max_tokensnpresence_penaltyseedstopstreamstream_optionssuffix temperaturetop_puser extra_headersN extra_query extra_bodytimeoutc.tV^8dQhRRRRRRRRR R R R R RRRRRRR RRRRRRRRRRRR RR RRRRR R!R"R#R$R%R&R'/#(r&modelKUnion[str, Literal['gpt-3.5-turbo-instruct', 'davinci-002', 'babbage-002']]promptMUnion[str, SequenceNotStr[str], Iterable[int], Iterable[Iterable[int]], None]r;Optional[int] | Omitr<Optional[bool] | Omitr=Optional[float] | Omitr>Optional[Dict[str, int]] | Omitr?r@rArBrCrD6Union[Optional[str], SequenceNotStr[str], None] | OmitrEzOptional[Literal[False]] | OmitrF1Optional[ChatCompletionStreamOptionsParam] | OmitrGOptional[str] | OmitrHrIrJ str | OmitrKHeaders | NonerL Query | NonerM Body | NonerN'float | httpx.Timeout | None | NotGivenr'rr))r*s"r+r,r-4[ [ [[ ^ [ & [ $ [ 2[ 4[ '[ )[  [ 1[ #[ E[ 0[ J![ "%#[ $,%[ &&'[ ()[ .&/[ 0"1[ 2 3[ 495[ 6 7[ r.c R#u Creates a completion for the provided prompt and parameters. Returns a completion object, or a sequence of completion objects if the request is streamed. Args: model: ID of the model to use. You can use the [List models](https://platform.openai.com/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](https://platform.openai.com/docs/models) for descriptions of them. prompt: The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document. best_of: Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. When used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return – `best_of` must be greater than `n`. **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. echo: Echo back the prompt in addition to the completion frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation) logit_bias: Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token from being generated. logprobs: Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response. The maximum value for `logprobs` is 5. max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. n: How many completions to generate for each prompt. **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation) seed: If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. stop: Not supported with latest reasoning models `o3` and `o4-mini`. Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. stream: Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). stream_options: Options for streaming response. Only set this when you set `stream: true`. suffix: The suffix that comes after a completion of inserted text. This parameter is only supported for `gpt-3.5-turbo-instruct`. temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. top_p: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. user: A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids). extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Nr)r2rQrSr;r<r=r>r?r@rArBrCrDrErFrGrHrIrJrKrLrMrNs&$$$$$$$$$$$$$$$$$$$$$$r+createCompletions.create3x r.c.tV^8dQhRRRRRRRRR R R R R RRRRRRRRR RRRRRRRRRR RR RRRRR R!R"R#R$R%R&R'/#)(r&rQrRrSrTrE Literal[True]r;rUr<rVr=rWr>rXr?r@rArBrCrDrYrFrZrGr[rHrIrJr\rKr]rLr^rMr_rNr`r'zStream[Completion]r))r*s"r+r,r-s[ [ [[ ^ [  [ & [ $[ 2[ 4[ '[ )[  [ 1[ #[ E[ J![ "%#[ $,%[ &&'[ ()[ .&/[ 0"1[ 2 3[ 495[ 6 7[ r.c R#u Creates a completion for the provided prompt and parameters. Returns a completion object, or a sequence of completion objects if the request is streamed. Args: model: ID of the model to use. You can use the [List models](https://platform.openai.com/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](https://platform.openai.com/docs/models) for descriptions of them. prompt: The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document. stream: Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). best_of: Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. When used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return – `best_of` must be greater than `n`. **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. echo: Echo back the prompt in addition to the completion frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation) logit_bias: Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token from being generated. logprobs: Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response. The maximum value for `logprobs` is 5. max_tokens: The maximum number of [tokens](/tokenizer) that can be generated in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. n: How many completions to generate for each prompt. **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation) seed: If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. stop: Not supported with latest reasoning models `o3` and `o4-mini`. Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. stream_options: Options for streaming response. Only set this when you set `stream: true`. suffix: The suffix that comes after a completion of inserted text. This parameter is only supported for `gpt-3.5-turbo-instruct`. temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. top_p: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. user: A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids). extra_headers: Send extra headers extra_query: Add additional query parameters to the request extra_body: Add additional JSON properties to the request timeout: Override the client-level default timeout for this request, in seconds Nr)r2rQrSrEr;r<r=r>r?r@rArBrCrDrFrGrHrIrJrKrLrMrNs&$$$$$$$$$$$$$$$$$$$$$$r+rerfrgr.c.tV^8dQhRRRRRRRRR R R R R RRRRRRRRR RRRRRRRRRR RR RRRRR R!R"R#R$R%R&R'/#)(r&rQrRrSrTrEboolr;rUr<rVr=rWr>rXr?r@rArBrCrDrYrFrZrGr[rHrIrJr\rKr]rLr^rMr_rNr`r'Completion | Stream[Completion]r))r*s"r+r,r-ps[ [ [[ ^ [  [ & [ $[ 2[ 4[ '[ )[  [ 1[ #[ E[ J![ "%#[ $,%[ &&'[ ()[ .&/[ 0"1[ 2 3[ 495[ 6 )7[ r.c R#rkr)rls&$$$$$$$$$$$$$$$$$$$$$$r+rerforgr.rQrSc.tV^8dQhRRRRRRRRR R R R R RRRRRRR RRRRRRRRRRRR RR RRRRR R!R"R#R$R%R&R'/#)(r&rQrRrSrTr;rUr<rVr=rWr>rXr?r@rArBrCrDrYrE/Optional[Literal[False]] | Literal[True] | OmitrFrZrGr[rHrIrJr\rKr]rLr^rMr_rNr`r'ror))r*s"r+r,r-sA A [A ^ A & A $ A 2A 4A 'A )A  A 1A #A EA @A J!A "%#A $,%A &&'A ()A .&/A 0"1A 2 3A 495A 6 )7A r.c  XTPR\/RVbRVbRVbRVbRVbRVbRVbRVbR V bR V bR V bR V bR V bRVbRVbRVbRVbRV/CV 'd\PM\P4\ VVVVRR/R7\ T ;'gR\\ ,R7#) /completionsrQrSr;r<r=r>r?r@rArBrCrDrErFrGrHrIrJ bearer_authTrKrLrMrNsecurityFbodyoptionscast_torE stream_cls)_postrr CompletionCreateParamsStreaming"CompletionCreateParamsNonStreamingrrrrds&$$$$$$$$$$$$$$$$$$$$$$r+rerf sN:zz  UfwD  ():  !* !*'(8DDf%nf ";!"U#$D%*)HH-PP/2)+'%'. ??Uj)I% % r.r)rQrSrE__name__ __module__ __qualname____firstlineno____doc__rr3r9r rrrer__static_attributes__r)r.r+r!r!s0066[ )- [ '+ [ 59[ 7;[ *.[ ,0[ #'[ 48[ &*[ HL[ 37[ MQ![ "(,#[ $/3%[ &)-'[ ( )[ .)-/[ 0%)1[ 2#'3[ 4r?r@rArBrCrDrErFrGrHrIrJrKNrLrMrNc.tV^8dQhRRRRRRRRR R R R R RRRRRRR RRRRRRRRRRRR RR RRRRR R!R"R#R$R%R&R'/#rPr))r*s"r+r,rkrar.c "R#5ircr)rds&$$$$$$$$$$$$$$$$$$$$$$r+reAsyncCompletions.createj x c.tV^8dQhRRRRRRRRR R R R R RRRRRRRRR RRRRRRRRRR RR RRRRR R!R"R#R$R%R&R'/#)(r&rQrRrSrTrErir;rUr<rVr=rWr>rXr?r@rArBrCrDrYrFrZrGr[rHrIrJr\rKr]rLr^rMr_rNr`r'zAsyncStream[Completion]r))r*s"r+r,r s[ [ [[ ^ [  [ & [ $[ 2[ 4[ '[ )[  [ 1[ #[ E[ J![ "%#[ $,%[ &&'[ ()[ .&/[ 0"1[ 2 3[ 495[ 6 !7[ r.c "R#5irkr)rls&$$$$$$$$$$$$$$$$$$$$$$r+rerrrc.tV^8dQhRRRRRRRRR R R R R RRRRRRRRR RRRRRRRRRR RR RRRRR R!R"R#R$R%R&R'/#)(r&rQrRrSrTrErnr;rUr<rVr=rWr>rXr?r@rArBrCrDrYrFrZrGr[rHrIrJr\rKr]rLr^rMr_rNr`r'$Completion | AsyncStream[Completion]r))r*s"r+r,rs[ [ [[ ^ [  [ & [ $[ 2[ 4[ '[ )[  [ 1[ #[ E[ J![ "%#[ $,%[ &&'[ ()[ .&/[ 0"1[ 2 3[ 495[ 6 .7[ r.c "R#5irkr)rls&$$$$$$$$$$$$$$$$$$$$$$r+rerrrrQrSc.tV^8dQhRRRRRRRRR R R R R RRRRRRR RRRRRRRRRRRR RR RRRRR R!R"R#R$R%R&R'/#)(r&rQrRrSrTr;rUr<rVr=rWr>rXr?r@rArBrCrDrYrErrrFrZrGr[rHrIrJr\rKr]rLr^rMr_rNr`r'rr))r*s"r+r,rEsA A [A ^ A & A $ A 2A 4A 'A )A  A 1A #A EA @A J!A "%#A $,%A &&'A ()A .&/A 0"1A 2 3A 495A 6 .7A r.c "TPR\/RVbRVbRVbRVbRVbRVbRVbRVbR V bR V bR V bR V bR V bRVbRVbRVbRVbRV/CV 'd\PM\P4GRjxL \ VVVVRR/R7\ T ;'gR\\ ,R7GRjxL #LBL5i)rtrQrSr;r<r=r>r?r@rArBrCrDrErFrGrHrIrJNruTrvFrx)r}rr r~rrrrrds&$$$$$$$$$$$$$$$$$$$$$$r+rerDse:ZZ ,UfwD  ():  !* !*'(8DDf%nf ";!"U#$D%*)HH-PP/2)+'%'. ??U":.I % % % % s*A9C;B> >     r.rreNrrrrrrr)r.r+r(r(   r.r(c"]tRtRtRRltRtR#)ric V^8dQhRRRR/#r&rr"r'rr))r*s"r+r,,AsyncCompletionsWithRawResponse.__annotate__  $4  r.c \Wn\P!VP4VnR#r)rr async_to_raw_response_wrapperrers&&r+r(AsyncCompletionsWithRawResponse.__init__s#'&DD     r.rNrr)r.r+rrrr.rc"]tRtRtRRltRtR#)r6ic V^8dQhRRRR/#rr))r*s"r+r,-CompletionsWithStreamingResponse.__annotate__rr.c FWn\VP4VnR#r)rrrers&&r+r)CompletionsWithStreamingResponse.__init__s'2     r.rNrr)r.r+r6r6rr.r6c"]tRtRtRRltRtR#)ric V^8dQhRRRR/#rr))r*s"r+r,2AsyncCompletionsWithStreamingResponse.__annotate__rr.c FWn\VP4VnR#r)rrrers&&r+r.AsyncCompletionsWithStreamingResponse.__init__s'8     r.rNrr)r.r+rrrr.r)4 __future__rtypingrrrrtyping_extensionsrr httpxr typesr _typesr r rrrrrr_utilsrrr_compatr _resourcerr _responserr _streamingrr _base_clientrtypes.completionr/types.chat.chat_completion_stream_options_paramr __all__r!r"r(rr6rr)r.r+rs#22/ ,ZZZJJ%9X,*^ , -t /t nt 't n        r.