1639 - docs - generated

Author: monikakuster

docs/src/content/docs/reference/components/amazon-bedrock.md

@@ -56,6 +56,7 @@ Ask anything you want.
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Max Tokens | INTEGER | INTEGER  |  The maximum number of tokens to generate in the chat completion.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Temperature | NUMBER | NUMBER  |  Controls randomness:  Higher values will make the output more random, while lower values like will make it more focused and deterministic.  |
 | Top P | NUMBER | NUMBER  |  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.  |
 | Top K | INTEGER | INTEGER  |  Specify the number of token choices the generative uses to generate the next token.  |
@@ -75,6 +76,7 @@ Ask anything you want.
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Max Tokens | INTEGER | INTEGER  |  The maximum number of tokens to generate in the chat completion.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Temperature | NUMBER | NUMBER  |  Controls randomness:  Higher values will make the output more random, while lower values like will make it more focused and deterministic.  |
 | Top P | NUMBER | NUMBER  |  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.  |
 | Top K | INTEGER | INTEGER  |  Specify the number of token choices the generative uses to generate the next token.  |
@@ -93,6 +95,7 @@ Ask anything you want.
 | Model | STRING | SELECT  |  ID of the model to use.  |
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Max Tokens | INTEGER | INTEGER  |  The maximum number of tokens to generate in the chat completion.  |
 | Number of Chat Completion Choices | INTEGER | INTEGER  |  How many chat completion choices to generate for each input message.  |
 | Temperature | NUMBER | NUMBER  |  Controls randomness:  Higher values will make the output more random, while lower values like will make it more focused and deterministic.  |
@@ -116,6 +119,7 @@ Ask anything you want.
 | Model | STRING | SELECT  |  ID of the model to use.  |
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Min Tokens | INTEGER | INTEGER  |  The minimum number of tokens to generate in the chat completion.  |
 | Max Tokens | INTEGER | INTEGER  |  The maximum number of tokens to generate in the chat completion.  |
 | Prompt | STRING | TEXT  |  The text which the model is requested to continue.  |
@@ -141,6 +145,7 @@ Ask anything you want.
 | Model | STRING | SELECT  |  ID of the model to use.  |
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Max Tokens | INTEGER | INTEGER  |  The maximum number of tokens to generate in the chat completion.  |
 | Temperature | NUMBER | NUMBER  |  Controls randomness:  Higher values will make the output more random, while lower values like will make it more focused and deterministic.  |
 | Top P | NUMBER | NUMBER  |  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.  |
@@ -158,6 +163,7 @@ Ask anything you want.
 | Model | STRING | SELECT  |  ID of the model to use.  |
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Max Tokens | INTEGER | INTEGER  |  The maximum number of tokens to generate in the chat completion.  |
 | Temperature | NUMBER | NUMBER  |  Controls randomness:  Higher values will make the output more random, while lower values like will make it more focused and deterministic.  |
 | Top P | NUMBER | NUMBER  |  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.  |

docs/src/content/docs/reference/components/anthropic.md

@@ -54,6 +54,7 @@ Ask anything you want.
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Max Tokens | INTEGER | INTEGER  |  The maximum number of tokens to generate in the chat completion.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Temperature | NUMBER | NUMBER  |  Controls randomness:  Higher values will make the output more random, while lower values like will make it more focused and deterministic.  |
 | Top P | NUMBER | NUMBER  |  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.  |
 | Top K | INTEGER | INTEGER  |  Specify the number of token choices the generative uses to generate the next token.  |

docs/src/content/docs/reference/components/azure-openai.md

@@ -54,6 +54,7 @@ Ask anything you want.
 | Model | STRING | TEXT  |  Deployment name, written in string.  |
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Max Tokens | INTEGER | INTEGER  |  The maximum number of tokens to generate in the chat completion.  |
 | Number of Chat Completion Choices | INTEGER | INTEGER  |  How many chat completion choices to generate for each input message.  |
 | Temperature | NUMBER | NUMBER  |  Controls randomness:  Higher values will make the output more random, while lower values like will make it more focused and deterministic.  |

docs/src/content/docs/reference/components/groq.md

@@ -53,6 +53,7 @@ Ask anything you want.
 | Model | STRING | TEXT  |  ID of the model to use.  |
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Max Tokens | INTEGER | INTEGER  |  The maximum number of tokens to generate in the chat completion.  |
 | Number of Chat Completion Choices | INTEGER | INTEGER  |  How many chat completion choices to generate for each input message.  |
 | Temperature | NUMBER | NUMBER  |  Controls randomness:  Higher values will make the output more random, while lower values like will make it more focused and deterministic.  |

docs/src/content/docs/reference/components/hugging-face.md

@@ -53,6 +53,7 @@ Ask anything you want.
 | URL | STRING | TEXT  |  Url of the inference endpoint  |
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 
 
 

docs/src/content/docs/reference/components/mistral.md

@@ -53,6 +53,7 @@ Ask anything you want.
 | Model | STRING | SELECT  |  ID of the model to use.  |
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Max Tokens | INTEGER | INTEGER  |  The maximum number of tokens to generate in the chat completion.  |
 | Temperature | NUMBER | NUMBER  |  Controls randomness:  Higher values will make the output more random, while lower values like will make it more focused and deterministic.  |
 | Top P | NUMBER | NUMBER  |  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.  |

docs/src/content/docs/reference/components/nvidia.md

@@ -53,6 +53,7 @@ Ask anything you want.
 | Model | STRING | TEXT  |  ID of the model to use.  |
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Max Tokens | INTEGER | INTEGER  |  The maximum number of tokens to generate in the chat completion.  |
 | Number of Chat Completion Choices | INTEGER | INTEGER  |  How many chat completion choices to generate for each input message.  |
 | Temperature | NUMBER | NUMBER  |  Controls randomness:  Higher values will make the output more random, while lower values like will make it more focused and deterministic.  |

docs/src/content/docs/reference/components/ollama.md

@@ -53,6 +53,7 @@ Ask anything you want.
 | Model | STRING | SELECT  |  ID of the model to use.  |
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Response format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Keep alive for | STRING | TEXT  |  Controls how long the model will stay loaded into memory following the request  |
 | Num predict | INTEGER | INTEGER  |  Maximum number of tokens to predict when generating text. (-1 = infinite generation, -2 = fill context)  |
 | Temperature | NUMBER | NUMBER  |  Controls randomness:  Higher values will make the output more random, while lower values like will make it more focused and deterministic.  |

docs/src/content/docs/reference/components/openai.md

@@ -53,6 +53,7 @@ Ask anything you want.
 | Model | STRING | SELECT  |  ID of the model to use.  |
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Max Tokens | INTEGER | INTEGER  |  The maximum number of tokens to generate in the chat completion.  |
 | Number of Chat Completion Choices | INTEGER | INTEGER  |  How many chat completion choices to generate for each input message.  |
 | Temperature | NUMBER | NUMBER  |  Controls randomness:  Higher values will make the output more random, while lower values like will make it more focused and deterministic.  |

docs/src/content/docs/reference/components/watsonx.md

@@ -57,6 +57,7 @@ Ask anything you want.
 | Model | STRING | TEXT  |  Model is the identifier of the LLM Model to be used.  |
 | Messages | [{STRING\(content), STRING\(role)}] | ARRAY_BUILDER  |  A list of messages comprising the conversation so far.  |
 | Response Format | INTEGER | SELECT  |  In which format do you want the response to be in?  |
+| Response Schema | STRING | TEXT_AREA  |  Define the JSON schema for the response.  |
 | Decoding Method | STRING | TEXT  |  Decoding is the process that a model uses to choose the tokens in the generated output.  |
 | Repetition Penalty | NUMBER | NUMBER  |  Sets how strongly to penalize repetitions. A higher value (e.g., 1.8) will penalize repetitions more strongly, while a lower value (e.g., 1.1) will be more lenient.  |
 | Min Tokens | INTEGER | INTEGER  |  Sets how many tokens must the LLM generate.  |