| Title: | Tidy Integration of Large Language Models |
|---|---|
| Description: | A tidy interface for integrating large language model (LLM) APIs such as 'Claude', 'Openai', 'Groq','Mistral' and local models via 'Ollama' into R workflows. The package supports text and media-based interactions, interactive message history, batch request APIs, and a tidy, pipeline-oriented interface for streamlined integration into data workflows. Web services are available at <https://www.anthropic.com>, <https://openai.com>, <https://groq.com>, <https://mistral.ai/> and <https://ollama.com>. |
| Authors: | Eduard Brüll [aut, cre], Jia Zhang [ctb] |
| Maintainer: | Eduard Brüll <[email protected]> |
| License: | MIT + file LICENSE |
| Version: | 0.3.0 |
| Built: | 2024-12-09 09:43:57 UTC |
| Source: | CRAN |
The azure_openai() function acts as an interface for interacting with the Azure OpenAI API
through main tidyllm verbs.
azure_openai(..., .called_from = NULL)azure_openai(..., .called_from = NULL)
... |
Parameters to be passed to the Azure OpenAI API specific function, such as model configuration, input text, or API-specific options. |
.called_from |
An internal argument that specifies which action (e.g.,
|
azure_openai() currently routes messages only to azure_openai_chat() when used with chat().
The result of the requested action, depending on the specific function invoked
(currently, only an updated LLMMessage object for azure_openai_chat()).
This function sends a message history to the Azure OpenAI Chat Completions API and returns the assistant's reply. This function is work in progress and not fully tested
azure_openai_chat( .llm, .endpoint_url = Sys.getenv("AZURE_ENDPOINT_URL"), .deployment = "gpt-4o-mini", .api_version = "2024-08-01-preview", .max_completion_tokens = NULL, .frequency_penalty = NULL, .logit_bias = NULL, .logprobs = FALSE, .top_logprobs = NULL, .presence_penalty = NULL, .seed = NULL, .stop = NULL, .stream = FALSE, .temperature = NULL, .top_p = NULL, .timeout = 60, .verbose = FALSE, .json_schema = NULL, .dry_run = FALSE, .max_tries = 3 )azure_openai_chat( .llm, .endpoint_url = Sys.getenv("AZURE_ENDPOINT_URL"), .deployment = "gpt-4o-mini", .api_version = "2024-08-01-preview", .max_completion_tokens = NULL, .frequency_penalty = NULL, .logit_bias = NULL, .logprobs = FALSE, .top_logprobs = NULL, .presence_penalty = NULL, .seed = NULL, .stop = NULL, .stream = FALSE, .temperature = NULL, .top_p = NULL, .timeout = 60, .verbose = FALSE, .json_schema = NULL, .dry_run = FALSE, .max_tries = 3 )
.llm |
An |
.endpoint_url |
Base URL for the API (default: Sys.getenv("AZURE_ENDPOINT_URL")). |
.deployment |
The identifier of the model that is deployed (default: "gpt-4o-mini"). |
.api_version |
Which version of the API is deployed (default: "2024-08-01-preview") |
.max_completion_tokens |
An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. |
.frequency_penalty |
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far. |
.logit_bias |
A named list modifying the likelihood of specified tokens appearing in the completion. |
.logprobs |
Whether to return log probabilities of the output tokens (default: FALSE). |
.top_logprobs |
An integer between 0 and 20 specifying the number of most likely tokens to return at each token position. |
.presence_penalty |
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far. |
.seed |
If specified, the system will make a best effort to sample deterministically. |
.stop |
Up to 4 sequences where the API will stop generating further tokens. |
.stream |
If set to TRUE, the answer will be streamed to console as it comes (default: FALSE). |
.temperature |
What sampling temperature to use, between 0 and 2. Higher values make the output more random. |
.top_p |
An alternative to sampling with temperature, called nucleus sampling. |
.timeout |
Request timeout in seconds (default: 60). |
.verbose |
Should additional information be shown after the API call (default: FALSE). |
.json_schema |
A JSON schema object as R list to enforce the output structure (If defined has precedence over JSON mode). |
.dry_run |
If TRUE, perform a dry run and return the request object (default: FALSE). |
.max_tries |
Maximum retries to perform request |
A new LLMMessage object containing the original messages plus the assistant's response.
## Not run: # Basic usage msg <- llm_message("What is R programming?") result <- azure_openai_chat(msg) # With custom parameters result2 <- azure_openai_chat(msg, .deployment = "gpt-4o-mini", .temperature = 0.7, .max_tokens = 1000) ## End(Not run)## Not run: # Basic usage msg <- llm_message("What is R programming?") result <- azure_openai_chat(msg) # With custom parameters result2 <- azure_openai_chat(msg, .deployment = "gpt-4o-mini", .temperature = 0.7, .max_tokens = 1000) ## End(Not run)
Generate Embeddings Using OpenAI API on Azure
azure_openai_embedding( .input, .deployment = "text-embedding-3-small", .endpoint_url = Sys.getenv("AZURE_ENDPOINT_URL"), .api_version = "2023-05-15", .truncate = TRUE, .timeout = 120, .dry_run = FALSE, .max_tries = 3 )azure_openai_embedding( .input, .deployment = "text-embedding-3-small", .endpoint_url = Sys.getenv("AZURE_ENDPOINT_URL"), .api_version = "2023-05-15", .truncate = TRUE, .timeout = 120, .dry_run = FALSE, .max_tries = 3 )
.input |
A character vector of texts to embed or an |
.deployment |
The embedding model identifier (default: "text-embedding-3-small"). |
.endpoint_url |
Base URL for the API (default: Sys.getenv("AZURE_ENDPOINT_URL")). |
.api_version |
What API-Version othe Azure OpenAI API should be used (default: "2023-05-15") |
.truncate |
Whether to truncate inputs to fit the model's context length (default: TRUE). |
.timeout |
Timeout for the API request in seconds (default: 120). |
.dry_run |
If TRUE, perform a dry run and return the request object. |
.max_tries |
Maximum retry attempts for requests (default: 3). |
A tibble with two columns: input and embeddings.
The input column contains the texts sent to embed, and the embeddings column
is a list column where each row contains an embedding vector of the sent input.
This function cancels an in-progress batch created through the OpenAI API. The batch will be moved to a "cancelling" state and, eventually, "cancelled."
cancel_openai_batch(.batch_id, .dry_run = FALSE, .max_tries = 3, .timeout = 60)cancel_openai_batch(.batch_id, .dry_run = FALSE, .max_tries = 3, .timeout = 60)
.batch_id |
Character; the unique identifier for the batch to cancel. |
.dry_run |
Logical; if |
.max_tries |
Integer; maximum number of retries if the request fails (default: |
.timeout |
Integer; request timeout in seconds (default: |
A list containing the response from the OpenAI API about the cancellation status.
The chat() function sends a message to a language model via a specified provider and returns the response.
It routes the provided LLMMessage object to the appropriate provider-specific chat function,
while allowing for the specification of common arguments applicable across different providers.
chat( .llm, .provider = getOption("tidyllm_chat_default"), .dry_run = NULL, .stream = NULL, .temperature = NULL, .timeout = NULL, .top_p = NULL, .max_tries = NULL, .model = NULL, .verbose = NULL, .json_schema = NULL, .seed = NULL, .stop = NULL, .frequency_penalty = NULL, .presence_penalty = NULL )chat( .llm, .provider = getOption("tidyllm_chat_default"), .dry_run = NULL, .stream = NULL, .temperature = NULL, .timeout = NULL, .top_p = NULL, .max_tries = NULL, .model = NULL, .verbose = NULL, .json_schema = NULL, .seed = NULL, .stop = NULL, .frequency_penalty = NULL, .presence_penalty = NULL )
.llm |
An |
.provider |
A function or function call specifying the language model provider and any additional parameters.
This should be a call to a provider function like |
.dry_run |
Logical; if |
.stream |
Logical; if |
.temperature |
Numeric; controls the randomness of the model's output (0 = deterministic). |
.timeout |
Numeric; the maximum time (in seconds) to wait for a response. |
.top_p |
Numeric; nucleus sampling parameter, which limits the sampling to the top cumulative probability |
.max_tries |
Integer; the maximum number of retries for failed requests. |
.model |
Character; the model identifier to use (e.g., |
.verbose |
Logical; if |
.json_schema |
List; A JSON schema object as R list to enforce the output structure |
.seed |
Integer; sets a random seed for reproducibility. |
.stop |
Character vector; specifies sequences where the model should stop generating further tokens. |
.frequency_penalty |
Numeric; adjusts the likelihood of repeating tokens (positive values decrease repetition). |
.presence_penalty |
Numeric; adjusts the likelihood of introducing new tokens (positive values encourage novelty). |
The chat() function provides a unified interface for interacting with different language model providers.
Common arguments such as .temperature, .model, and .stream are supported by most providers and can be
passed directly to chat(). If a provider does not support a particular argument, an error will be raised.
Advanced provider-specific configurations can be accessed via the provider functions.
An updated LLMMessage object containing the response from the language model.
## Not run: # Basic usage with OpenAI provider llm_message("Hello World") |> chat(ollama(.ollama_server = "https://my-ollama-server.de"),.model="mixtral") chat(mistral,.model="mixtral") # Use streaming with Claude provider llm_message("Tell me a story") |> chat(claude(),.stream=TRUE) ## End(Not run)## Not run: # Basic usage with OpenAI provider llm_message("Hello World") |> chat(ollama(.ollama_server = "https://my-ollama-server.de"),.model="mixtral") chat(mistral,.model="mixtral") # Use streaming with Claude provider llm_message("Tell me a story") |> chat(claude(),.stream=TRUE) ## End(Not run)
The chatgpt function is an alias for the openai() provider function.
It provides a convenient way to interact with the OpenAI API for tasks such
as sending chat messages, generating embeddings, and handling batch operations
using tidyllm verbs like chat(), embed(), and send_batch().
chatgpt(..., .called_from = NULL)chatgpt(..., .called_from = NULL)
... |
Parameters to be passed to the appropriate OpenAI-specific function, such as model configuration, input text, or other API-specific options. |
.called_from |
An internal argument that specifies the context (e.g.,
|
The result of the requested action, depending on the specific function invoked
(e.g., an updated LLMMessage object for chat(), or a matrix for embed()).
This function retrieves the processing status and other details of a specified
batchid or a list of LLMMessage objects with batch attribute.
It routes the input to the appropriate provider-specific batch API function.
check_batch( .llms, .provider = getOption("tidyllm_cbatch_default"), .dry_run = NULL, .max_tries = NULL, .timeout = NULL )check_batch( .llms, .provider = getOption("tidyllm_cbatch_default"), .dry_run = NULL, .max_tries = NULL, .timeout = NULL )
.llms |
A list of |
.provider |
A function or function call specifying the language model provider and any additional parameters.
This should be a call to a provider function like |
.dry_run |
Logical; if TRUE, returns the prepared request object without executing it |
.max_tries |
Maximum retries to perform the request |
.timeout |
Integer specifying the request timeout in seconds |
A tibble with information about the status of batch processing.
This function retrieves the processing status and other details of a specified Claude batch ID from the Claude API.
check_claude_batch( .llms = NULL, .batch_id = NULL, .api_url = "https://api.anthropic.com/", .dry_run = FALSE, .max_tries = 3, .timeout = 60 )check_claude_batch( .llms = NULL, .batch_id = NULL, .api_url = "https://api.anthropic.com/", .dry_run = FALSE, .max_tries = 3, .timeout = 60 )
.llms |
A list of LLMMessage objects |
.batch_id |
A manually set batchid |
.api_url |
Character; base URL of the Claude API (default: "https://api.anthropic.com/"). |
.dry_run |
Logical; if TRUE, returns the prepared request object without executing it (default: FALSE). |
.max_tries |
Maximum retries to peform request |
.timeout |
Integer specifying the request timeout in seconds (default: 60). |
A tibble with information about the status of batch processing
This function retrieves the processing status and other details of a specified Mistral batch ID from the Mistral Batch API.
check_mistral_batch( .llms = NULL, .batch_id = NULL, .dry_run = FALSE, .max_tries = 3, .timeout = 60 )check_mistral_batch( .llms = NULL, .batch_id = NULL, .dry_run = FALSE, .max_tries = 3, .timeout = 60 )
.llms |
A list of LLMMessage objects. |
.batch_id |
A manually set batch ID. |
.dry_run |
Logical; if TRUE, returns the prepared request object without executing it (default: FALSE). |
.max_tries |
Maximum retries to perform the request (default: 3). |
.timeout |
Integer specifying the request timeout in seconds (default: 60). |
A tibble with information about the status of batch processing.
This function retrieves the processing status and other details of a specified OpenAI batch ID from the OpenAI Batch API.
check_openai_batch( .llms = NULL, .batch_id = NULL, .dry_run = FALSE, .max_tries = 3, .timeout = 60 )check_openai_batch( .llms = NULL, .batch_id = NULL, .dry_run = FALSE, .max_tries = 3, .timeout = 60 )
.llms |
A list of LLMMessage objects. |
.batch_id |
A manually set batch ID. |
.dry_run |
Logical; if TRUE, returns the prepared request object without executing it (default: FALSE). |
.max_tries |
Maximum retries to perform the request (default: 3). |
.timeout |
Integer specifying the request timeout in seconds (default: 60). |
A tibble with information about the status of batch processing.
The claude() function acts as an interface for interacting with the Anthropic API
through main tidyllm verbs such as chat(), embed(), and
send_batch(). It dynamically routes requests to Claude-specific functions
like claude_chat() and send_claude_batch() based on the context of the call.
claude(..., .called_from = NULL)claude(..., .called_from = NULL)
... |
Parameters to be passed to the appropriate OpenAI-specific function, such as model configuration, input text, or API-specific options. |
.called_from |
An internal argument that specifies which action (e.g.,
|
The result of the requested action, depending on the specific function invoked
(e.g., an updated LLMMessage object for chat(), or a matrix for embed()).
Interact with Claude AI models via the Anthropic API
claude_chat( .llm, .model = "claude-3-5-sonnet-20241022", .max_tokens = 1024, .temperature = NULL, .top_k = NULL, .top_p = NULL, .metadata = NULL, .stop_sequences = NULL, .tools = NULL, .api_url = "https://api.anthropic.com/", .verbose = FALSE, .max_tries = 3, .timeout = 60, .stream = FALSE, .dry_run = FALSE )claude_chat( .llm, .model = "claude-3-5-sonnet-20241022", .max_tokens = 1024, .temperature = NULL, .top_k = NULL, .top_p = NULL, .metadata = NULL, .stop_sequences = NULL, .tools = NULL, .api_url = "https://api.anthropic.com/", .verbose = FALSE, .max_tries = 3, .timeout = 60, .stream = FALSE, .dry_run = FALSE )
.llm |
An LLMMessage object containing the conversation history and system prompt. |
.model |
Character string specifying the Claude model version (default: "claude-3-5-sonnet-20241022"). |
.max_tokens |
Integer specifying the maximum number of tokens in the response (default: 1024). |
.temperature |
Numeric between 0 and 1 controlling response randomness. |
.top_k |
Integer controlling diversity by limiting the top K tokens. |
.top_p |
Numeric between 0 and 1 for nucleus sampling. |
.metadata |
List of additional metadata to include with the request. |
.stop_sequences |
Character vector of sequences that will halt response generation. |
.tools |
List of additional tools or functions the model can use. |
.api_url |
Base URL for the Anthropic API (default: "https://api.anthropic.com/"). |
.verbose |
Logical; if TRUE, displays additional information about the API call (default: FALSE). |
.max_tries |
Maximum retries to peform request |
.timeout |
Integer specifying the request timeout in seconds (default: 60). |
.stream |
Logical; if TRUE, streams the response piece by piece (default: FALSE). |
.dry_run |
Logical; if TRUE, returns the prepared request object without executing it (default: FALSE). |
A new LLMMessage object containing the original messages plus Claude's response.
## Not run: # Basic usage msg <- llm_message("What is R programming?") result <- claude_chat(msg) # With custom parameters result2 <- claude_chat(msg, .temperature = 0.7, .max_tokens = 1000) ## End(Not run)## Not run: # Basic usage msg <- llm_message("What is R programming?") result <- claude_chat(msg) # With custom parameters result2 <- claude_chat(msg, .temperature = 0.7, .max_tokens = 1000) ## End(Not run)
This function converts a data frame into an LLMMessage object representing a conversation history.
The data frame must have specific columns (role and content), with each row representing a message.
df_llm_message(.df)df_llm_message(.df)
.df |
A data frame with at least two rows and columns |
An LLMMessage object representing the structured conversation.
Other Message Creation Utilities:
llm_message()
The embed() function allows you to embed a text via a specified provider.
It routes the input to the appropriate provider-specific embedding function.
embed( .input, .provider = getOption("tidyllm_embed_default"), .model = NULL, .truncate = NULL, .timeout = NULL, .dry_run = NULL, .max_tries = NULL )embed( .input, .provider = getOption("tidyllm_embed_default"), .model = NULL, .truncate = NULL, .timeout = NULL, .dry_run = NULL, .max_tries = NULL )
.input |
A character vector of texts to embed or an |
.provider |
A function or function call specifying the language model provider and any additional parameters.
This should be a call to a provider function like |
.model |
The embedding model to use |
.truncate |
Whether to truncate inputs to fit the model's context length |
.timeout |
Timeout for the API request in seconds |
.dry_run |
If TRUE, perform a dry run and return the request object. |
.max_tries |
Maximum retry attempts for requests |
A tibble with two columns: input and embeddings.
The input column contains the texts sent to embed, and the embeddings column
is a list column where each row contains an embedding vector of the sent input.
## Not run: c("What is the meaning of life, the universe and everything?", "How much wood would a woodchuck chuck?", "How does the brain work?") |> embed(gemini) ## End(Not run)## Not run: c("What is the meaning of life, the universe and everything?", "How much wood would a woodchuck chuck?", "How does the brain work?") |> embed(gemini) ## End(Not run)
This function retrieves the results of a completed batch and updates
the provided list of LLMMessage objects with the responses. It aligns each
response with the original request using the custom_ids generated in send_batch().
fetch_batch( .llms, .provider = getOption("tidyllm_fbatch_default"), .dry_run = NULL, .max_tries = NULL, .timeout = NULL )fetch_batch( .llms, .provider = getOption("tidyllm_fbatch_default"), .dry_run = NULL, .max_tries = NULL, .timeout = NULL )
.llms |
A list of |
.provider |
A function or function call specifying the language model provider and any additional parameters.
This should be a call to a provider function like |
.dry_run |
Logical; if |
.max_tries |
Integer; maximum number of retries if the request fails |
.timeout |
Integer; request timeout in seconds |
The function routes the input to the appropriate provider-specific batch API function.
A list of updated LLMMessage objects, each with the assistant's response added if successful.
This function retrieves the results of a completed Claude batch and updates
the provided list of LLMMessage objects with the responses. It aligns each
response with the original request using the custom_ids generated in send_claude_batch().
fetch_claude_batch( .llms, .batch_id = NULL, .api_url = "https://api.anthropic.com/", .dry_run = FALSE, .max_tries = 3, .timeout = 60 )fetch_claude_batch( .llms, .batch_id = NULL, .api_url = "https://api.anthropic.com/", .dry_run = FALSE, .max_tries = 3, .timeout = 60 )
.llms |
A list of |
.batch_id |
Character; the unique identifier for the batch. By default this is NULL
and the function will attempt to use the |
.api_url |
Character; the base URL for the Claude API (default: "https://api.anthropic.com/"). |
.dry_run |
Logical; if |
.max_tries |
Integer; maximum number of retries if the request fails (default: |
.timeout |
Integer; request timeout in seconds (default: |
A list of updated LLMMessage objects, each with the assistant's response added if successful.
This function retrieves the results of a completed Mistral batch and updates
the provided list of LLMMessage objects with the responses. It aligns each
response with the original request using the custom_ids generated in send_mistral_batch().
fetch_mistral_batch( .llms, .batch_id = NULL, .dry_run = FALSE, .max_tries = 3, .timeout = 60 )fetch_mistral_batch( .llms, .batch_id = NULL, .dry_run = FALSE, .max_tries = 3, .timeout = 60 )
.llms |
A list of |
.batch_id |
Character; the unique identifier for the batch. By default this is NULL
and the function will attempt to use the |
.dry_run |
Logical; if |
.max_tries |
Integer; maximum number of retries if the request fails (default: |
.timeout |
Integer; request timeout in seconds (default: |
A list of updated LLMMessage objects, each with the assistant's response added if successful.
This function retrieves the results of a completed OpenAI batch and updates
the provided list of LLMMessage objects with the responses. It aligns each
response with the original request using the custom_ids generated in send_openai_batch().
fetch_openai_batch( .llms, .batch_id = NULL, .dry_run = FALSE, .max_tries = 3, .timeout = 60 )fetch_openai_batch( .llms, .batch_id = NULL, .dry_run = FALSE, .max_tries = 3, .timeout = 60 )
.llms |
A list of |
.batch_id |
Character; the unique identifier for the batch. By default this is NULL
and the function will attempt to use the |
.dry_run |
Logical; if |
.max_tries |
Integer; maximum number of retries if the request fails (default: |
.timeout |
Integer; request timeout in seconds (default: |
A list of updated LLMMessage objects, each with the assistant's response added if successful.
The gemini() function acts as a provider interface for interacting with the Google Gemini API
through tidyllm's main verbs such as chat() and embed().
It dynamically routes requests to Gemini-specific functions
like gemini_chat() and gemini_embedding() based on the context of the call.
gemini(..., .called_from = NULL)gemini(..., .called_from = NULL)
... |
Parameters to be passed to the appropriate Gemini-specific function, such as model configuration, input text, or API-specific options. |
.called_from |
An internal argument specifying which action (e.g.,
|
Some functions, such as gemini_upload_file() and gemini_delete_file(),
are specific to Gemini and do not have general verb counterparts.
The result of the requested action, depending on the specific function invoked
(e.g., an updated LLMMessage object for chat()).
Send LLMMessage to Gemini API
gemini_chat( .llm, .model = "gemini-1.5-flash", .fileid = NULL, .temperature = NULL, .max_output_tokens = NULL, .top_p = NULL, .top_k = NULL, .grounding_threshold = NULL, .presence_penalty = NULL, .frequency_penalty = NULL, .stop_sequences = NULL, .safety_settings = NULL, .json_schema = NULL, .timeout = 120, .dry_run = FALSE, .max_tries = 3, .verbose = FALSE, .stream = FALSE )gemini_chat( .llm, .model = "gemini-1.5-flash", .fileid = NULL, .temperature = NULL, .max_output_tokens = NULL, .top_p = NULL, .top_k = NULL, .grounding_threshold = NULL, .presence_penalty = NULL, .frequency_penalty = NULL, .stop_sequences = NULL, .safety_settings = NULL, .json_schema = NULL, .timeout = 120, .dry_run = FALSE, .max_tries = 3, .verbose = FALSE, .stream = FALSE )
.llm |
An existing LLMMessage object or an initial text prompt. |
.model |
The model identifier (default: "gemini-1.5-flash"). |
.fileid |
Optional vector of file IDs uploaded via |
.temperature |
Controls randomness in generation (default: NULL, range: 0.0-2.0). |
.max_output_tokens |
Maximum tokens in the response (default: NULL). |
.top_p |
Controls nucleus sampling (default: NULL, range: 0.0-1.0). |
.top_k |
Controls diversity in token selection (default: NULL, range: 0 or more). |
.grounding_threshold |
A grounding threshold between 0 and 1. With lower grounding thresholds Gemini will use Google to search for relevant information before answering. (default: NULL). |
.presence_penalty |
Penalizes new tokens (default: NULL, range: -2.0 to 2.0). |
.frequency_penalty |
Penalizes frequent tokens (default: NULL, range: -2.0 to 2.0). |
.stop_sequences |
Optional character sequences to stop generation (default: NULL, up to 5). |
.safety_settings |
A list of safety settings (default: NULL). |
.json_schema |
A JSON schema object as R list to enforce the output structure |
.timeout |
When should our connection time out (default: 120 seconds). |
.dry_run |
If TRUE, perform a dry run and return the request object. |
.max_tries |
Maximum retries to perform request (default: 3). |
.verbose |
Should additional information be shown after the API call. |
.stream |
Should the response be streamed (default: FALSE). |
Returns an updated LLMMessage object.
Deletes a specific file from the Gemini API using its file ID.
gemini_delete_file(.file_name)gemini_delete_file(.file_name)
.file_name |
The file ID (e.g., "files/abc-123") to delete. |
Invisibly returns NULL. Prints a confirmation message upon successful deletion.
Generate Embeddings Using the Google Gemini API
gemini_embedding( .input, .model = "text-embedding-004", .truncate = TRUE, .timeout = 120, .dry_run = FALSE, .max_tries = 3 )gemini_embedding( .input, .model = "text-embedding-004", .truncate = TRUE, .timeout = 120, .dry_run = FALSE, .max_tries = 3 )
.input |
A character vector of texts to embed or an |
.model |
The embedding model identifier (default: "text-embedding-3-small"). |
.truncate |
Whether to truncate inputs to fit the model's context length (default: TRUE). |
.timeout |
Timeout for the API request in seconds (default: 120). |
.dry_run |
If TRUE, perform a dry run and return the request object. |
.max_tries |
Maximum retry attempts for requests (default: 3). |
A matrix where each column corresponds to the embedding of a message in the message history.
Retrieves metadata for a specific file uploaded to the Gemini API.
gemini_file_metadata(.file_name)gemini_file_metadata(.file_name)
.file_name |
The file ID (e.g., "files/abc-123") to retrieve metadata for. |
A tibble containing metadata fields such as name, display name, MIME type, size, and URI.
Lists metadata for files uploaded to the Gemini API, supporting pagination.
gemini_list_files(.page_size = 10, .page_token = NULL)gemini_list_files(.page_size = 10, .page_token = NULL)
.page_size |
The maximum number of files to return per page (default: 10, maximum: 100). |
.page_token |
A token for fetching the next page of results (default: NULL). |
A tibble containing metadata for each file, including fields such as name, display name, MIME type, and URI.
Uploads a file to the Gemini API and returns its metadata as a tibble.
gemini_upload_file(.file_path)gemini_upload_file(.file_path)
.file_path |
The local file path of the file to upload. |
A tibble containing metadata about the uploaded file, including its name, URI, and MIME type.
Retrieves metadata from assistant replies within an LLMMessage object.
It returns the metadata as a tibble.
get_metadata(.llm, .index = NULL) last_metadata(.llm)get_metadata(.llm, .index = NULL) last_metadata(.llm)
.llm |
An |
.index |
A positive integer specifying which assistant reply's metadata to extract.
If |
Metadata columns may include:
model: The model used for generating the reply.
timestamp: The time when the reply was generated.
prompt_tokens: The number of tokens in the input prompt.
completion_tokens: The number of tokens in the assistant's reply.
total_tokens: The total number of tokens (prompt + completion).
api_specific: A list column with API-specific metadata.
For convenience, last_metadata() is provided to retrieve the metadata for the last message.
A tibble containing metadata for the specified assistant reply or all replies.
Extracts the plain text content of the assistant's reply from an LLMMessage object.
Use get_reply_data() for structured replies in JSON format.
get_reply(.llm, .index = NULL) last_reply(.llm)get_reply(.llm, .index = NULL) last_reply(.llm)
.llm |
An |
.index |
A positive integer indicating the index of the assistant reply to retrieve.
Defaults to |
This function is the core utility for retrieving assistant replies by index.
For convenience, last_reply() is provided as a wrapper to retrieve the
latest assistant reply.
Returns a character string containing the assistant's reply, or NA_character_ if no reply exists.
get_reply_data(), last_reply()
Parses the assistant's reply as JSON and returns the corresponding structured data. If the reply is not marked as JSON, attempts to extract and parse JSON content from the text.
get_reply_data(.llm, .index = NULL) last_reply_data(.llm)get_reply_data(.llm, .index = NULL) last_reply_data(.llm)
.llm |
An |
.index |
A positive integer indicating the index of the assistant reply to retrieve.
Defaults to |
For convenience, last_reply_data() is provided as a wrapper to retrieve the
latest assistant reply's data.
Returns the parsed data from the assistant's reply, or NULL if parsing fails.
get_reply(), last_reply_data()
Extracts the content of a user's message from an LLMMessage object at a specific index.
get_user_message(.llm, .index = NULL) last_user_message(.llm)get_user_message(.llm, .index = NULL) last_user_message(.llm)
.llm |
An |
.index |
A positive integer indicating which user message to retrieve. Defaults to |
For convenience, last_user_message() is provided as a wrapper to retrieve the
latest user message without specifying an index.
Returns the content of the user's message at the specified index. If no messages are found, returns NA_character_.
The groq() function acts as an interface for interacting with the Groq API
through tidyllm's main verbs. Currently, Groq only supports groq_chat()
for chat-based interactions and groq_transcribe() for transcription tasks.
groq(..., .called_from = NULL)groq(..., .called_from = NULL)
... |
Parameters to be passed to the Groq-specific function, such as model configuration, input text, or API-specific options. |
.called_from |
An internal argument that specifies which action (e.g.,
|
Since groq_transcribe() is unique to Groq and does not have a general verb counterpart,
groq() currently routes messages only to groq_chat() when used with verbs like chat().
The result of the requested action, depending on the specific function invoked
(currently, only an updated LLMMessage object for groq_chat()).
This function sends a message history to the Groq Chat API and returns the assistant's reply.
groq_chat( .llm, .model = "llama-3.2-11b-vision-preview", .max_tokens = 1024, .temperature = NULL, .top_p = NULL, .frequency_penalty = NULL, .presence_penalty = NULL, .stop = NULL, .seed = NULL, .api_url = "https://api.groq.com/", .json = FALSE, .timeout = 60, .verbose = FALSE, .stream = FALSE, .dry_run = FALSE, .max_tries = 3 )groq_chat( .llm, .model = "llama-3.2-11b-vision-preview", .max_tokens = 1024, .temperature = NULL, .top_p = NULL, .frequency_penalty = NULL, .presence_penalty = NULL, .stop = NULL, .seed = NULL, .api_url = "https://api.groq.com/", .json = FALSE, .timeout = 60, .verbose = FALSE, .stream = FALSE, .dry_run = FALSE, .max_tries = 3 )
.llm |
An |
.model |
The identifier of the model to use (default: "llama-3.2-11b-vision-preview"). |
.max_tokens |
The maximum number of tokens that can be generated in the response (default: 1024). |
.temperature |
Controls the randomness in the model's response. Values between 0 and 2 are allowed, where higher values increase randomness (optional). |
.top_p |
Nucleus sampling parameter that controls the proportion of probability mass considered. Values between 0 and 1 are allowed (optional). |
.frequency_penalty |
Number between -2.0 and 2.0. Positive values penalize repeated tokens, reducing likelihood of repetition (optional). |
.presence_penalty |
Number between -2.0 and 2.0. Positive values encourage new topics by penalizing tokens that have appeared so far (optional). |
.stop |
One or more sequences where the API will stop generating further tokens. Can be a string or a list of strings (optional). |
.seed |
An integer for deterministic sampling. If specified, attempts to return the same result for repeated requests with identical parameters (optional). |
.api_url |
Base URL for the Groq API (default: "https://api.groq.com/"). |
.json |
Whether the response should be structured as JSON (default: FALSE). |
.timeout |
Request timeout in seconds (default: 60). |
.verbose |
If TRUE, displays additional information after the API call, including rate limit details (default: FALSE). |
.stream |
Logical; if TRUE, streams the response piece by piece (default: FALSE). |
.dry_run |
If TRUE, performs a dry run and returns the constructed request object without executing it (default: FALSE). |
.max_tries |
Maximum retries to peform request |
A new LLMMessage object containing the original messages plus the assistant's response.
## Not run: # Basic usage msg <- llm_message("What is Groq?") result <- groq_chat(msg) # With custom parameters result2 <- groq_chat(msg, .model = "llama-3.2-vision", .temperature = 0.5, .max_tokens = 512) ## End(Not run)## Not run: # Basic usage msg <- llm_message("What is Groq?") result <- groq_chat(msg) # With custom parameters result2 <- groq_chat(msg, .model = "llama-3.2-vision", .temperature = 0.5, .max_tokens = 512) ## End(Not run)
This function reads an audio file and sends it to the Groq transcription API for transcription.
groq_transcribe( .audio_file, .model = "whisper-large-v3", .language = NULL, .prompt = NULL, .temperature = 0, .api_url = "https://api.groq.com/openai/v1/audio/transcriptions", .dry_run = FALSE, .verbose = FALSE, .max_tries = 3 )groq_transcribe( .audio_file, .model = "whisper-large-v3", .language = NULL, .prompt = NULL, .temperature = 0, .api_url = "https://api.groq.com/openai/v1/audio/transcriptions", .dry_run = FALSE, .verbose = FALSE, .max_tries = 3 )
.audio_file |
The path to the audio file (required). Supported formats include flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. |
.model |
The model to use for transcription (default: "whisper-large-v3"). |
.language |
The language of the input audio, in ISO-639-1 format (optional). |
.prompt |
A prompt to guide the transcription style. It should match the audio language (optional). |
.temperature |
Sampling temperature, between 0 and 1, with higher values producing more randomness (default: 0). |
.api_url |
Base URL for the API (default: "https://api.groq.com/openai/v1/audio/transcriptions"). |
.dry_run |
Logical; if TRUE, performs a dry run and returns the request object without making the API call (default: FALSE). |
.verbose |
Logical; if TRUE, rate limiting info is displayed after the API request (default: FALSE). |
.max_tries |
Maximum retries to peform request |
A character vector containing the transcription.
## Not run: # Basic usage groq_transcribe(.audio_file = "example.mp3") ## End(Not run)## Not run: # Basic usage groq_transcribe(.audio_file = "example.mp3") ## End(Not run)
List all Batch Requests on a Batch API
list_batches(.provider = getOption("tidyllm_lbatch_default"))list_batches(.provider = getOption("tidyllm_lbatch_default"))
.provider |
A function or function call specifying the language model provider and any additional parameters.
This should be a call to a provider function like |
A tibble with information about the status of batch processing.
Retrieves batch request details from the Claude API.
list_claude_batches( .api_url = "https://api.anthropic.com/", .limit = 20, .max_tries = 3, .timeout = 60 )list_claude_batches( .api_url = "https://api.anthropic.com/", .limit = 20, .max_tries = 3, .timeout = 60 )
.api_url |
Base URL for the Claude API (default: "https://api.anthropic.com/"). |
.limit |
Maximum number of batches to retrieve (default: 20). |
.max_tries |
Maximum retry attempts for requests (default: 3). |
.timeout |
Request timeout in seconds (default: 60). |
A tibble with batch details: batch ID, status, creation time, expiration time, and request counts (succeeded, errored, expired, canceled).
Retrieves batch request details from the OpenAI Batch API.
list_mistral_batches( .limit = 100, .max_tries = 3, .timeout = 60, .status = NULL, .created_after = NULL )list_mistral_batches( .limit = 100, .max_tries = 3, .timeout = 60, .status = NULL, .created_after = NULL )
.limit |
Maximum number of batches to retrieve (default: 20). |
.max_tries |
Maximum retry attempts for requests (default: 3). |
.timeout |
Request timeout in seconds (default: 60). |
.status |
Filter by status. (default: NULL) |
.created_after |
created after a string specifiying a date-time (default: NULL) |
A tibble with batch details for all batches fitting the request
Retrieves batch request details from the OpenAI Batch API.
list_openai_batches(.limit = 20, .max_tries = 3, .timeout = 60)list_openai_batches(.limit = 20, .max_tries = 3, .timeout = 60)
.limit |
Maximum number of batches to retrieve (default: 20). |
.max_tries |
Maximum retry attempts for requests (default: 3). |
.timeout |
Request timeout in seconds (default: 60). |
A tibble with batch details: batch ID, status, creation time, expiration time, and request counts (total, completed, failed).
This function creates a new LLMMessage object or updates an existing one.
It supports adding text prompts and various media types, such as images, PDFs, text files, or plots.
llm_message( .llm = NULL, .prompt = NULL, .role = "user", .system_prompt = "You are a helpful assistant", .imagefile = NULL, .pdf = NULL, .textfile = NULL, .capture_plot = FALSE, .f = NULL )llm_message( .llm = NULL, .prompt = NULL, .role = "user", .system_prompt = "You are a helpful assistant", .imagefile = NULL, .pdf = NULL, .textfile = NULL, .capture_plot = FALSE, .f = NULL )
.llm |
An existing LLMMessage object or an initial text prompt. |
.prompt |
Text prompt to add to the message history. |
.role |
The role of the message sender, typically "user" or "assistant". |
.system_prompt |
Default system prompt if a new LLMMessage needs to be created. |
.imagefile |
Path to an image file to be attached (optional). |
.pdf |
Path to a PDF file to be attached (optional). Can be a character vector of length one (file path), or a list with |
.textfile |
Path to a text file to be read and attached (optional). |
.capture_plot |
Boolean to indicate whether a plot should be captured and attached as an image (optional). |
.f |
An R function or an object coercible to a function via |
Returns an updated or new LLMMessage object.
Other Message Creation Utilities:
df_llm_message()
LLMMessage is an S7 class for managing a conversation history intended for use with large language models (LLMs). Please use
llm_message()to create or modify LLMMessage objects.
LLMMessage(message_history = list(), system_prompt = character(0))LLMMessage(message_history = list(), system_prompt = character(0))
message_history |
A list containing messages. Each message is a named list with keys like |
system_prompt |
A character string representing the default system prompt used for the conversation. |
The LLMMessage class includes the following features:
Stores message history in a structured format.
Supports attaching media and metadata to messages.
Provides generics like add_message(), has_image(), and remove_message() for interaction.
Enables API-specific formatting through the to_api_format() generic.
message_history: A list containing messages. Each message is a named list with keys like role, content, media, etc.
system_prompt: A character string representing the default system prompt used for the conversation.
The mistral() function acts as an interface for interacting with the Mistral API
through main tidyllm verbs such as chat() and embed().
It dynamically routes requests to Mistral-specific functions
like mistral_chat() and mistral_embedding() based on the context of the call.
mistral(..., .called_from = NULL)mistral(..., .called_from = NULL)
... |
Parameters to be passed to the appropriate Mistral-specific function, such as model configuration, input text, or API-specific options. |
.called_from |
An internal argument that specifies which action (e.g.,
|
The result of the requested action, depending on the specific function invoked
(e.g., an updated LLMMessage object for chat(), or a matrix for embed()).
Send LLMMessage to Mistral API
mistral_chat( .llm, .model = "mistral-large-latest", .stream = FALSE, .seed = NULL, .json = FALSE, .temperature = 0.7, .top_p = 1, .stop = NULL, .safe_prompt = FALSE, .timeout = 120, .max_tries = 3, .max_tokens = 1024, .min_tokens = NULL, .dry_run = FALSE, .verbose = FALSE )mistral_chat( .llm, .model = "mistral-large-latest", .stream = FALSE, .seed = NULL, .json = FALSE, .temperature = 0.7, .top_p = 1, .stop = NULL, .safe_prompt = FALSE, .timeout = 120, .max_tries = 3, .max_tokens = 1024, .min_tokens = NULL, .dry_run = FALSE, .verbose = FALSE )
.llm |
An |
.model |
The model identifier to use (default: |
.stream |
Whether to stream back partial progress to the console. (default: |
.seed |
The seed to use for random sampling. If set, different calls will generate deterministic results (optional). |
.json |
Whether the output should be in JSON mode(default: |
.temperature |
Sampling temperature to use, between |
.top_p |
Nucleus sampling parameter, between |
.stop |
Stop generation if this token is detected, or if one of these tokens is detected when providing a list (optional). |
.safe_prompt |
Whether to inject a safety prompt before all conversations (default: |
.timeout |
When should our connection time out in seconds (default: |
.max_tries |
Maximum retries to peform request |
.max_tokens |
The maximum number of tokens to generate in the completion. Must be |
.min_tokens |
The minimum number of tokens to generate in the completion. Must be |
.dry_run |
If |
.verbose |
Should additional information be shown after the API call? (default: |
Returns an updated LLMMessage object.
Generate Embeddings Using Mistral API
mistral_embedding( .input, .model = "mistral-embed", .timeout = 120, .max_tries = 3, .dry_run = FALSE )mistral_embedding( .input, .model = "mistral-embed", .timeout = 120, .max_tries = 3, .dry_run = FALSE )
.input |
A character vector of texts to embed or an |
.model |
The embedding model identifier (default: "mistral-embed"). |
.timeout |
Timeout for the API request in seconds (default: 120). |
.max_tries |
Maximum retries to peform request |
.dry_run |
If TRUE, perform a dry run and return the request object. |
A matrix where each column corresponds to the embedding of a message in the message history.
The ollama() function acts as an interface for interacting with local AI models via the Ollama API.
It integrates seamlessly with the main tidyllm verbs such as chat() and embed().
ollama(..., .called_from = NULL)ollama(..., .called_from = NULL)
... |
Parameters to be passed to the appropriate Ollama-specific function, such as model configuration, input text, or API-specific options. |
.called_from |
An internal argument specifying the verb (e.g., |
Some functionalities, like ollama_download_model() or ollama_list_models()
are unique to the Ollama API and do not have a general verb counterpart.
These functions can be only accessed directly.
Supported Verbs:
chat(): Sends a message to an Ollama model and retrieves the model's response.
embed(): Generates embeddings for input texts using an Ollama model.
The result of the requested action:
For chat(): An updated LLMMessage object containing the model's response.
For embed(): A matrix where each column corresponds to an embedding.
Interact with local AI models via the Ollama API
ollama_chat( .llm, .model = "gemma2", .stream = FALSE, .seed = NULL, .json_schema = NULL, .temperature = NULL, .num_ctx = 2048, .num_predict = NULL, .top_k = NULL, .top_p = NULL, .min_p = NULL, .mirostat = NULL, .mirostat_eta = NULL, .mirostat_tau = NULL, .repeat_last_n = NULL, .repeat_penalty = NULL, .tfs_z = NULL, .stop = NULL, .ollama_server = "http://localhost:11434", .timeout = 120, .keep_alive = NULL, .dry_run = FALSE )ollama_chat( .llm, .model = "gemma2", .stream = FALSE, .seed = NULL, .json_schema = NULL, .temperature = NULL, .num_ctx = 2048, .num_predict = NULL, .top_k = NULL, .top_p = NULL, .min_p = NULL, .mirostat = NULL, .mirostat_eta = NULL, .mirostat_tau = NULL, .repeat_last_n = NULL, .repeat_penalty = NULL, .tfs_z = NULL, .stop = NULL, .ollama_server = "http://localhost:11434", .timeout = 120, .keep_alive = NULL, .dry_run = FALSE )
.llm |
An LLMMessage object containing the conversation history and system prompt. |
.model |
Character string specifying the Ollama model to use (default: "gemma2") |
.stream |
Logical; whether to stream the response (default: FALSE) |
.seed |
Integer; seed for reproducible generation (default: NULL) |
.json_schema |
A JSON schema object as R list to enforce the output structure (default: NULL) |
.temperature |
Float between 0-2; controls randomness in responses (default: NULL) |
.num_ctx |
Integer; sets the context window size (default: 2048) |
.num_predict |
Integer; maximum number of tokens to predict (default: NULL) |
.top_k |
Integer; controls diversity by limiting top tokens considered (default: NULL) |
.top_p |
Float between 0-1; nucleus sampling threshold (default: NULL) |
.min_p |
Float between 0-1; minimum probability threshold (default: NULL) |
.mirostat |
Integer (0,1,2); enables Mirostat sampling algorithm (default: NULL) |
.mirostat_eta |
Float; Mirostat learning rate (default: NULL) |
.mirostat_tau |
Float; Mirostat target entropy (default: NULL) |
.repeat_last_n |
Integer; tokens to look back for repetition (default: NULL) |
.repeat_penalty |
Float; penalty for repeated tokens (default: NULL) |
.tfs_z |
Float; tail free sampling parameter (default: NULL) |
.stop |
Character; custom stop sequence(s) (default: NULL) |
.ollama_server |
String; Ollama API endpoint (default: "http://localhost:11434") |
.timeout |
Integer; API request timeout in seconds (default: 120) |
.keep_alive |
Character; How long should the ollama model be kept in memory after request (default: NULL - 5 Minutes) |
.dry_run |
Logical; if TRUE, returns request object without execution (default: FALSE) |
The function provides extensive control over the generation process through various parameters:
Temperature (0-2): Higher values increase creativity, lower values make responses more focused
Top-k/Top-p: Control diversity of generated text
Mirostat: Advanced sampling algorithm for maintaining consistent complexity
Repeat penalties: Prevent repetitive text
Context window: Control how much previous conversation is considered
A new LLMMessage object containing the original messages plus the model's response
## Not run: llm_message("user", "Hello, how are you?") response <- ollama_chat(llm, .model = "gemma2", .temperature = 0.7) # With custom parameters response <- ollama_chat( llm, .model = "llama2", .temperature = 0.8, .top_p = 0.9, .num_ctx = 4096 ) ## End(Not run)## Not run: llm_message("user", "Hello, how are you?") response <- ollama_chat(llm, .model = "gemma2", .temperature = 0.7) # With custom parameters response <- ollama_chat( llm, .model = "llama2", .temperature = 0.8, .top_p = 0.9, .num_ctx = 4096 ) ## End(Not run)
This function sends a request to the Ollama API to download a specified model from Ollama's large online library of models.
ollama_download_model(.model, .ollama_server = "http://localhost:11434")ollama_download_model(.model, .ollama_server = "http://localhost:11434")
.model |
The name of the model to download. |
.ollama_server |
The base URL of the Ollama API (default is "http://localhost:11434"). |
Generate Embeddings Using Ollama API
ollama_embedding( .input, .model = "all-minilm", .truncate = TRUE, .ollama_server = "http://localhost:11434", .timeout = 120, .dry_run = FALSE )ollama_embedding( .input, .model = "all-minilm", .truncate = TRUE, .ollama_server = "http://localhost:11434", .timeout = 120, .dry_run = FALSE )
.input |
Aa charachter vector of texts to embed or an |
.model |
The embedding model identifier (default: "all-minilm"). |
.truncate |
Whether to truncate inputs to fit the model's context length (default: TRUE). |
.ollama_server |
The URL of the Ollama server to be used (default: "http://localhost:11434"). |
.timeout |
Timeout for the API request in seconds (default: 120). |
.dry_run |
If TRUE, perform a dry run and return the request object. |
A matrix where each column corresponds to the embedding of a message in the message history.
This function connects to the Ollama API and retrieves information about available models, returning it as a tibble.
ollama_list_models(.ollama_server = "http://localhost:11434")ollama_list_models(.ollama_server = "http://localhost:11434")
.ollama_server |
The URL of the ollama server to be used |
A tibble containing model information, or NULL if no models are found.
The openai() function acts as an interface for interacting with the OpenAI API
through main tidyllm verbs such as chat(), embed(), and
send_batch(). It dynamically routes requests to OpenAI-specific functions
like openai_chat() and openai_embedding() based on the context of the call.
openai(..., .called_from = NULL)openai(..., .called_from = NULL)
... |
Parameters to be passed to the appropriate OpenAI-specific function, such as model configuration, input text, or API-specific options. |
.called_from |
An internal argument that specifies which action (e.g.,
|
The result of the requested action, depending on the specific function invoked
(e.g., an updated LLMMessage object for chat(), or a matrix for embed()).
This function sends a message history to the OpenAI Chat Completions API and returns the assistant's reply.
openai_chat( .llm, .model = "gpt-4o", .max_completion_tokens = NULL, .frequency_penalty = NULL, .logit_bias = NULL, .presence_penalty = NULL, .seed = NULL, .stop = NULL, .stream = FALSE, .temperature = NULL, .top_p = NULL, .api_url = "https://api.openai.com/", .timeout = 60, .verbose = FALSE, .json_schema = NULL, .max_tries = 3, .dry_run = FALSE, .compatible = FALSE, .api_path = "/v1/chat/completions" )openai_chat( .llm, .model = "gpt-4o", .max_completion_tokens = NULL, .frequency_penalty = NULL, .logit_bias = NULL, .presence_penalty = NULL, .seed = NULL, .stop = NULL, .stream = FALSE, .temperature = NULL, .top_p = NULL, .api_url = "https://api.openai.com/", .timeout = 60, .verbose = FALSE, .json_schema = NULL, .max_tries = 3, .dry_run = FALSE, .compatible = FALSE, .api_path = "/v1/chat/completions" )
.llm |
An |
.model |
The identifier of the model to use (default: "gpt-4o"). |
.max_completion_tokens |
An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. |
.frequency_penalty |
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far. |
.logit_bias |
A named list modifying the likelihood of specified tokens appearing in the completion. |
.presence_penalty |
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far. |
.seed |
If specified, the system will make a best effort to sample deterministically. |
.stop |
Up to 4 sequences where the API will stop generating further tokens. |
.stream |
If set to TRUE, the answer will be streamed to console as it comes (default: FALSE). |
.temperature |
What sampling temperature to use, between 0 and 2. Higher values make the output more random. |
.top_p |
An alternative to sampling with temperature, called nucleus sampling. |
.api_url |
Base URL for the API (default: "https://api.openai.com/"). |
.timeout |
Request timeout in seconds (default: 60). |
.verbose |
Should additional information be shown after the API call (default: FALSE). |
.json_schema |
A JSON schema object as R list to enforce the output structure (If defined has precedence over JSON mode). |
.max_tries |
Maximum retries to perform request |
.dry_run |
If TRUE, perform a dry run and return the request object (default: FALSE). |
.compatible |
If TRUE, skip API and rate-limit checks for OpenAI compatible APIs (default: FALSE). |
.api_path |
The path relative to the base |
A new LLMMessage object containing the original messages plus the assistant's response.
Generate Embeddings Using OpenAI API
openai_embedding( .input, .model = "text-embedding-3-small", .truncate = TRUE, .timeout = 120, .dry_run = FALSE, .max_tries = 3, .verbose = FALSE )openai_embedding( .input, .model = "text-embedding-3-small", .truncate = TRUE, .timeout = 120, .dry_run = FALSE, .max_tries = 3, .verbose = FALSE )
.input |
An existing LLMMessage object (or a character vector of texts to embed) |
.model |
The embedding model identifier (default: "text-embedding-3-small"). |
.truncate |
Whether to truncate inputs to fit the model's context length (default: TRUE). |
.timeout |
Timeout for the API request in seconds (default: 120). |
.dry_run |
If TRUE, perform a dry run and return the request object. |
.max_tries |
Maximum retry attempts for requests (default: 3). |
.verbose |
Should information about current ratelimits be printed? (default: FALSE) |
A tibble with two columns: input and embeddings.
The input column contains the texts sent to embed, and the embeddings column
is a list column where each row contains an embedding vector of the sent input.
This function processes a PDF file page by page. For each page, it extracts the text and converts the page into an image. It creates a list of LLMMessage objects with the text and the image for multimodal processing. Users can specify a range of pages to process and provide a custom function to generate prompts for each page.
pdf_page_batch( .pdf, .general_prompt, .system_prompt = "You are a helpful assistant", .page_range = NULL, .prompt_fn = NULL )pdf_page_batch( .pdf, .general_prompt, .system_prompt = "You are a helpful assistant", .page_range = NULL, .prompt_fn = NULL )
.pdf |
Path to the PDF file. |
.general_prompt |
A default prompt that is applied to each page if |
.system_prompt |
Optional system prompt to initialize the LLMMessage (default is "You are a helpful assistant"). |
.page_range |
A vector of two integers specifying the start and end pages to process. If NULL, all pages are processed. |
.prompt_fn |
An optional custom function that generates a prompt for each page. The function takes the page text as input
and returns a string. If NULL, |
A list of LLMMessage objects, each containing the text and image for a page.
The perplexity() function acts as a provider interface for interacting with the Perplexity API
through tidyllm's chat() verb.
It dynamically routes requests to Perplxeity-specific function. At the moment this is only
perplexity_chat()
perplexity(..., .called_from = NULL)perplexity(..., .called_from = NULL)
... |
Parameters to be passed to the appropriate Perplexity-specific function, such as model configuration, input text, or API-specific options. |
.called_from |
An internal argument specifying which action (e.g.,
|
The result of the requested action, depending on the specific function invoked
(e.g., an updated LLMMessage object for chat()).
This function sends a message history to the Perplexity Chat API and returns the assistant's reply.
perplexity_chat( .llm, .model = "llama-3.1-sonar-small-128k-online", .max_tokens = 1024, .temperature = NULL, .top_p = NULL, .frequency_penalty = NULL, .presence_penalty = NULL, .stop = NULL, .search_domain_filter = NULL, .return_images = FALSE, .search_recency_filter = NULL, .api_url = "https://api.perplexity.ai/", .json = FALSE, .timeout = 60, .verbose = FALSE, .stream = FALSE, .dry_run = FALSE, .max_tries = 3 )perplexity_chat( .llm, .model = "llama-3.1-sonar-small-128k-online", .max_tokens = 1024, .temperature = NULL, .top_p = NULL, .frequency_penalty = NULL, .presence_penalty = NULL, .stop = NULL, .search_domain_filter = NULL, .return_images = FALSE, .search_recency_filter = NULL, .api_url = "https://api.perplexity.ai/", .json = FALSE, .timeout = 60, .verbose = FALSE, .stream = FALSE, .dry_run = FALSE, .max_tries = 3 )
.llm |
An |
.model |
The identifier of the model to use (default: "llama-3.2-11b-vision-preview"). |
.max_tokens |
The maximum number of tokens that can be generated in the response (default: 1024). |
.temperature |
Controls the randomness in the model's response. Values between 0 (exclusive) and 2 (exclusive) are allowed, where higher values increase randomness (optional). |
.top_p |
Nucleus sampling parameter that controls the proportion of probability mass considered. Values between 0 (exclusive) and 1 (exclusive) are allowed (optional). |
.frequency_penalty |
Number greater than 0. Values > 1.0 penalize repeated tokens, reducing the likelihood of repetition (optional). |
.presence_penalty |
Number between -2.0 and 2.0. Positive values encourage new topics by penalizing tokens that have appeared so far (optional). |
.stop |
One or more sequences where the API will stop generating further tokens. Can be a string or a list of strings (optional). |
.search_domain_filter |
A vector of domains to limit or exclude from search results. For exclusion, prefix domains with a "-" (optional, currently in closed beta). |
.return_images |
Logical; if TRUE, enables returning images from the model's response (default: FALSE, currently in closed beta). |
.search_recency_filter |
Limits search results to a specific time interval (e.g., "month", "week", "day", or "hour"). Only applies to online models (optional). |
.api_url |
Base URL for the Perplexity API (default: "https://api.perplexity.ai/"). |
.json |
Whether the response should be structured as JSON (default: FALSE). |
.timeout |
Request timeout in seconds (default: 60). |
.verbose |
If TRUE, displays additional information after the API call, including rate limit details (default: FALSE). |
.stream |
Logical; if TRUE, streams the response piece by piece (default: FALSE). |
.dry_run |
If TRUE, performs a dry run and returns the constructed request object without executing it (default: FALSE). |
.max_tries |
Maximum retries to perform the request (default: 3). |
A new LLMMessage object containing the original messages plus the assistant's response.
This function retrieves the rate limit details for the specified API, or for all APIs stored in the .tidyllm_rate_limit_env if no API is specified.
rate_limit_info(.api_name = NULL)rate_limit_info(.api_name = NULL)
.api_name |
(Optional) The name of the API whose rate limit info you want to get If not provided, the rate limit info for all APIs in the environment will be returned |
A tibble containing the rate limit information.
The send_batch() function allows you to send a list of LLMMessage objects
to an API.
It routes the input to the appropriate provider-specific batch API function.
send_batch( .llms, .provider = getOption("tidyllm_sbatch_default"), .dry_run = NULL, .temperature = NULL, .timeout = NULL, .top_p = NULL, .max_tries = NULL, .model = NULL, .verbose = NULL, .json_schema = NULL, .seed = NULL, .stop = NULL, .frequency_penalty = NULL, .presence_penalty = NULL, .id_prefix = NULL )send_batch( .llms, .provider = getOption("tidyllm_sbatch_default"), .dry_run = NULL, .temperature = NULL, .timeout = NULL, .top_p = NULL, .max_tries = NULL, .model = NULL, .verbose = NULL, .json_schema = NULL, .seed = NULL, .stop = NULL, .frequency_penalty = NULL, .presence_penalty = NULL, .id_prefix = NULL )
.llms |
A list of |
.provider |
A function or function call specifying the language model provider and any additional parameters.
This should be a call to a provider function like |
.dry_run |
Logical; if |
.temperature |
Numeric; controls the randomness of the model's output (0 = deterministic). |
.timeout |
Numeric; the maximum time (in seconds) to wait for a response. |
.top_p |
Numeric; nucleus sampling parameter, which limits the sampling to the top cumulative probability |
.max_tries |
Integer; the maximum number of retries for failed requests. |
.model |
Character; the model identifier to use (e.g., |
.verbose |
Logical; if |
.json_schema |
List; A JSON schema object as R list to enforce the output structure |
.seed |
Integer; sets a random seed for reproducibility. |
.stop |
Character vector; specifies sequences where the model should stop generating further tokens. |
.frequency_penalty |
Numeric; adjusts the likelihood of repeating tokens (positive values decrease repetition). |
.presence_penalty |
Numeric; adjusts the likelihood of introducing new tokens (positive values encourage novelty). |
.id_prefix |
Character string to specify a prefix for generating custom IDs when names in |
An updated and named list of .llms with identifiers that align with batch responses, including a batch_id attribute.
This function creates and submits a batch of messages to the Claude API for asynchronous processing.
send_claude_batch( .llms, .model = "claude-3-5-sonnet-20241022", .max_tokens = 1024, .temperature = NULL, .top_k = NULL, .top_p = NULL, .stop_sequences = NULL, .api_url = "https://api.anthropic.com/", .verbose = FALSE, .dry_run = FALSE, .overwrite = FALSE, .max_tries = 3, .timeout = 60, .id_prefix = "tidyllm_claude_req_" )send_claude_batch( .llms, .model = "claude-3-5-sonnet-20241022", .max_tokens = 1024, .temperature = NULL, .top_k = NULL, .top_p = NULL, .stop_sequences = NULL, .api_url = "https://api.anthropic.com/", .verbose = FALSE, .dry_run = FALSE, .overwrite = FALSE, .max_tries = 3, .timeout = 60, .id_prefix = "tidyllm_claude_req_" )
.llms |
A list of LLMMessage objects containing conversation histories. |
.model |
Character string specifying the Claude model version (default: "claude-3-5-sonnet-20241022"). |
.max_tokens |
Integer specifying the maximum tokens per response (default: 1024). |
.temperature |
Numeric between 0 and 1 controlling response randomness. |
.top_k |
Integer for diversity by limiting the top K tokens. |
.top_p |
Numeric between 0 and 1 for nucleus sampling. |
.stop_sequences |
Character vector of sequences that halt response generation. |
.api_url |
Base URL for the Claude API (default: "https://api.anthropic.com/"). |
.verbose |
Logical; if TRUE, prints a message with the batch ID (default: FALSE). |
.dry_run |
Logical; if TRUE, returns the prepared request object without executing it (default: FALSE). |
.overwrite |
Logical; if TRUE, allows overwriting an existing batch ID associated with the request (default: FALSE). |
.max_tries |
Maximum number of retries to perform the request. |
.timeout |
Integer specifying the request timeout in seconds (default: 60). |
.id_prefix |
Character string to specify a prefix for generating custom IDs when names in |
An updated and named list of .llms with identifiers that align with batch responses, including a batch_id attribute.
Send a Batch of Requests to the Mistral API
send_mistral_batch( .llms, .model = "mistral-small-latest", .endpoint = "/v1/chat/completions", .metadata = NULL, .temperature = 0.7, .top_p = 1, .max_tokens = 1024, .min_tokens = NULL, .seed = NULL, .stop = NULL, .dry_run = FALSE, .overwrite = FALSE, .max_tries = 3, .timeout = 60, .id_prefix = "tidyllm_mistral_req_" )send_mistral_batch( .llms, .model = "mistral-small-latest", .endpoint = "/v1/chat/completions", .metadata = NULL, .temperature = 0.7, .top_p = 1, .max_tokens = 1024, .min_tokens = NULL, .seed = NULL, .stop = NULL, .dry_run = FALSE, .overwrite = FALSE, .max_tries = 3, .timeout = 60, .id_prefix = "tidyllm_mistral_req_" )
.llms |
A list of LLMMessage objects containing conversation histories. |
.model |
The Mistral model version (default: "mistral-small-latest"). |
.endpoint |
The API endpoint (default: "/v1/chat/completions"). |
.metadata |
Optional metadata for the batch. |
.temperature |
Sampling temperature to use, between |
.top_p |
Nucleus sampling parameter, between |
.max_tokens |
The maximum number of tokens to generate in the completion (default: |
.min_tokens |
The minimum number of tokens to generate (optional). |
.seed |
Random seed for deterministic outputs (optional). |
.stop |
Stop generation at specific tokens or strings (optional). |
.dry_run |
Logical; if |
.overwrite |
Logical; if |
.max_tries |
Maximum retry attempts for requests (default: |
.timeout |
Request timeout in seconds (default: |
.id_prefix |
Prefix for generating custom IDs (default: |
The prepared_llms list with the batch_id attribute attached.
This function creates and submits a batch of messages to the OpenAI Batch API for asynchronous processing.
send_openai_batch( .llms, .model = "gpt-4o", .max_completion_tokens = NULL, .frequency_penalty = NULL, .logit_bias = NULL, .presence_penalty = NULL, .seed = NULL, .stop = NULL, .temperature = NULL, .top_p = NULL, .dry_run = FALSE, .overwrite = FALSE, .json_schema = NULL, .max_tries = 3, .timeout = 60, .verbose = FALSE, .id_prefix = "tidyllm_openai_req_" )send_openai_batch( .llms, .model = "gpt-4o", .max_completion_tokens = NULL, .frequency_penalty = NULL, .logit_bias = NULL, .presence_penalty = NULL, .seed = NULL, .stop = NULL, .temperature = NULL, .top_p = NULL, .dry_run = FALSE, .overwrite = FALSE, .json_schema = NULL, .max_tries = 3, .timeout = 60, .verbose = FALSE, .id_prefix = "tidyllm_openai_req_" )
.llms |
A list of LLMMessage objects containing conversation histories. |
.model |
Character string specifying the OpenAI model version (default: "gpt-4o"). |
.max_completion_tokens |
Integer specifying the maximum tokens per response (default: NULL). |
.frequency_penalty |
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far. |
.logit_bias |
A named list modifying the likelihood of specified tokens appearing in the completion. |
.presence_penalty |
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far. |
.seed |
If specified, the system will make a best effort to sample deterministically. |
.stop |
Up to 4 sequences where the API will stop generating further tokens. |
.temperature |
What sampling temperature to use, between 0 and 2. Higher values make the output more random. |
.top_p |
An alternative to sampling with temperature, called nucleus sampling. |
.dry_run |
Logical; if TRUE, returns the prepared request object without executing it (default: FALSE). |
.overwrite |
Logical; if TRUE, allows overwriting an existing batch ID associated with the request (default: FALSE). |
.json_schema |
A JSON schema object as R list to enforce the output structure (default: NULL). |
.max_tries |
Maximum number of retries to perform the request (default: 3). |
.timeout |
Integer specifying the request timeout in seconds (default: 60). |
.verbose |
Logical; if TRUE, additional info about the requests is printed (default: FALSE). |
.id_prefix |
Character string to specify a prefix for generating custom IDs when names in |
An updated and named list of .llms with identifiers that align with batch responses, including a batch_id attribute.
This function creates a JSON schema suitable for use with the API functions in tidyllm.
tidyllm_schema(name = "tidyllm_schema", ...)tidyllm_schema(name = "tidyllm_schema", ...)
name |
A character vector specifying the schema name. This serves as an identifier for the schema (Default: "tidyllm_schema"). |
... |
Named arguments where each name represents a field in the schema and each value specifies the type. Supported types include R data types:
|
The tidyllm_schema() function is designed to make defining JSON schemas for tidyllm more concise and user-friendly. It maps R-like types to JSON schema types and validates inputs to enforce tidy data principles. Nested structures are not allowed to maintain compatibility with tidy data conventions.
A list representing the JSON schema with the specified fields and types, suitable for passing to openai()'s .json_schema parameter.
Factor types (factor(...)) are treated as enumerations in JSON and are limited to a set of allowable string values. Arrays of a given type can be specified by appending [] to the type.
## Not run: # Define a schema with tidy data principles json_schema <- tidyllm_schema( name = "DocumentAnalysisSchema", Title = "character", Authors = "character[]", SuggestedFilename = "character", Type = "factor(Policy, Research)", Answer_Q1 = "character", Answer_Q2 = "character", Answer_Q3 = "character", Answer_Q4 = "character", KeyCitations = "character[]" ) # Pass the schema to openai() result <- openai( .llm = msg, .json_schema = json_schema ) ## End(Not run)## Not run: # Define a schema with tidy data principles json_schema <- tidyllm_schema( name = "DocumentAnalysisSchema", Title = "character", Authors = "character[]", SuggestedFilename = "character", Type = "factor(Policy, Research)", Answer_Q1 = "character", Answer_Q2 = "character", Answer_Q3 = "character", Answer_Q4 = "character", KeyCitations = "character[]" ) # Pass the schema to openai() result <- openai( .llm = msg, .json_schema = json_schema ) ## End(Not run)