ReqLLM.Providers.Venice (ReqLLM v1.14.0)

View Source

Venice AI provider – OpenAI-compatible Chat Completions API with privacy-first inference.

Implementation

Uses built-in OpenAI-style encoding/decoding defaults with Venice-specific extensions. Venice is fully OpenAI-compatible with additional parameters via venice_parameters.

Venice-Specific Extensions

Beyond standard OpenAI parameters, Venice supports provider-specific options via the venice_parameters object in the request body:

  • character_slug - Use a specific AI character persona
  • enable_web_search - Enable real-time web search (off, on, auto)
  • enable_web_scraping - Scrape URLs in user messages
  • enable_web_citations - Include citations in web search results
  • strip_thinking_response - Strip <think> blocks from response
  • disable_thinking - Disable reasoning mode entirely
  • include_venice_system_prompt - Include Venice's default system prompts

See provider_schema/0 for the complete Venice-specific schema and ReqLLM.Provider.Options for inherited OpenAI parameters.

Configuration

# Add to .env file (automatically loaded)
VENICE_API_KEY=your-api-key

Examples

# Basic usage
ReqLLM.generate_text("venice:llama-3.3-70b", "Hello!")

# With web search enabled
ReqLLM.generate_text("venice:zai-org-glm-4.7", "What happened today?",
  provider_options: [enable_web_search: "on"]
)

# With a Venice character
ReqLLM.generate_text("venice:venice-uncensored", "Tell me a story",
  provider_options: [character_slug: "my-character"]
)

Summary

Functions

attach(request, model_input, user_opts)

Default implementation of attach/3.

attach_stream(model, context, opts, finch_name)

Default implementation of attach_stream/4.

base_url()
build_body(request)

Default implementation of build_body/1.

decode_response(request_response)

Default implementation of decode_response/1.

decode_stream_event(event, model)

Default implementation of decode_stream_event/2.

default_base_url()
default_env_key()

Callback implementation for ReqLLM.Provider.default_env_key/0.

encode_body(request)

Default implementation of encode_body/1.

extract_usage(body, model)

Default implementation of extract_usage/2.

prepare_request(operation, model_spec, input, opts)

Default implementation of prepare_request/4.

provider_extended_generation_schema()
provider_id()
provider_schema()
translate_options(operation, model, opts)

Default implementation of translate_options/3.

Functions

attach(request, model_input, user_opts)

Default implementation of attach/3.

Sets up Bearer token authentication and standard pipeline steps.

attach_stream(model, context, opts, finch_name)

Default implementation of attach_stream/4.

Builds complete streaming requests using OpenAI-compatible format.

base_url()

build_body(request)

Default implementation of build_body/1.

Builds request body using OpenAI-compatible format for chat and embedding operations.

decode_response(request_response)

Default implementation of decode_response/1.

Handles success/error responses with standard ReqLLM.Response creation.

decode_stream_event(event, model)

Default implementation of decode_stream_event/2.

Decodes SSE events using OpenAI-compatible format.

default_base_url()

default_env_key()

Callback implementation for ReqLLM.Provider.default_env_key/0.

encode_body(request)

Default implementation of encode_body/1.

Encodes request body using OpenAI-compatible format for chat and embedding operations.

extract_usage(body, model)

Default implementation of extract_usage/2.

Extracts usage data from standard usage field in response body.

prepare_request(operation, model_spec, input, opts)

Default implementation of prepare_request/4.

Handles :chat, :object, and :embedding operations using OpenAI-compatible patterns.

provider_extended_generation_schema()

provider_id()

provider_schema()

translate_options(operation, model, opts)

Default implementation of translate_options/3.

Pass-through implementation that returns options unchanged.