Codeunit 7765 "AOAI Text Completion Params"

System Application · System.AI · BC23-30 · source at ea08af5e · facts from BC29

Properties

Procedures

• GetMaxTokens(): Integer: Get the maximum number of tokens to generate in the completion.
• GetTemperature(): Decimal: Get the sampling temperature to use.
• GetTopP(): Decimal: Get the nucleus sampling to use.
• GetSuffix(): Text: Get the suffix that comes after a completion of inserted text.
• GetPresencePenalty(): Decimal: Get the presence penalty to use.
• GetFrequencyPenalty(): Decimal: Get the frequency penalty to use.
• SetMaxTokens(NewMaxTokens: Integer): The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens can’t exceed the model’s context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).
• SetTemperature(NewTemperature: Decimal): Sets the sampling temperature to use, between 0 and 2. A higher temperature increases the likelihood that the next most probable token will not be selected. When requesting structured data, set the temperature to 0. For human sounding speech, 0.7 is a typical value
• SetTopP(NewTopP: Decimal): 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…
• SetSuffix(NewSuffix: Text): The suffix that comes after a completion of inserted text.
• SetPresencePenalty(NewPresencePenalty: Decimal): 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.
• SetFrequencyPenalty(NewFrequencyPenalty: Decimal): 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.
• AddCompletionsParametersToPayload(var Payload: JsonObject) (internal): Add the completion parameters to the payload.

Calls

From the extracted call graph of BC29 (graphify-al on the snapshot checkout): calls whose target is known from a declared type or an Object::"Name" argument. Interface dispatch and calls through events are not counted, so the list is not complete.

• Codeunit 7766 “AOAI TextCompletionParams Impl” (13 calls: AddCompletionsParametersToPayload → AddCompletionsParametersToPayload, GetFrequencyPenalty → GetFrequencyPenalty, GetMaxTokens → GetMaxTokens, …)

Recent changes

• 2026-08-17 #10205 Deprecate Text Completion API in AI SDK (work item 621038) (main, BC30, obsoletion)

Deprecations

• object: Pending 29.0 (#if not CLEAN29), “Text completion models are retired by Azure OpenAI. Use GenerateChatCompletion instead.”

Source: AL metadata extracted from the code (names, ids, signatures, properties); no code bodies (D10).

Ask your agent

Procedure bodies are not stored here (D10). The call sections above are our own, per object, from the BC29 call graph. For a procedure body or the calls of one procedure, ask bc-code-atlas (external, by Stefan Maron, MIT; default corpus w1-28), which the bc-observatory plugin connects: bcatlas_resolve_node(object_type: "codeunit", object_name: "AOAI Text Completion Params"), then bcatlas_get_procedure_body or bcatlas_get_neighbors on the returned id.