From 9a75d2cdb354b34d0af591e056096a2166160c09 Mon Sep 17 00:00:00 2001
From: J S <49557684+svilupp@users.noreply.github.com>
Date: Sun, 15 Sep 2024 14:44:19 +0100
Subject: [PATCH] OpenRouter support, new OpenAI o1 models (#207)

---
 CHANGELOG.md                           |  6 ++
 docs/src/frequently_asked_questions.md | 40 ++++++++++++
 examples/adding_custom_API.jl          | 85 ++++++++++++++++++++++++++
 src/llm_anthropic.jl                   | 15 ++++-
 src/llm_google.jl                      | 15 ++++-
 src/llm_interface.jl                   | 15 +++++
 src/llm_ollama.jl                      | 12 +++-
 src/llm_openai.jl                      | 27 +++++++-
 src/llm_shared.jl                      | 17 ++++--
 src/user_preferences.jl                | 52 +++++++++++++++-
 test/llm_shared.jl                     | 29 ++++++++-
 11 files changed, 293 insertions(+), 20 deletions(-)
 create mode 100644 examples/adding_custom_API.jl

diff --git a/CHANGELOG.md b/CHANGELOG.md
index bb5a5fb4f..c61ed96e7 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -14,6 +14,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 - Added support for OpenAI's JSON mode for `aiextract` (just provide kwarg `json_mode=true`). Reference [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs).
+- Added support for OpenRouter's API (you must set ENV `OPENROUTER_API_KEY`) to provide access to more models like Cohere Command R+ and OpenAI's o1 series. Reference [OpenRouter](https://openrouter.ai/).
+- Added new OpenRouter hosted models to the model registry (prefixed with `or`): `oro1` (OpenAI's o1-preview), `oro1m` (OpenAI's o1-mini), `orcop` (Cohere's command-r-plus), `orco` (Cohere's command-r). The `or` prefix is to avoid conflicts with existing models and OpenAI's aliases, then the goal is to provide 2 letters for each model and 1 letter for additional qualifier (eg, "p" for plus, "m" for mini) -> `orcop` (OpenRouter cohere's COmmand-r-Plus).
+
+### Updated
+- Updated FAQ with instructions on how to access new OpenAI o1 models via OpenRouter.
+- Updated FAQ with instructions on how to add custom APIs (with an example `examples/adding_custom_API.jl`).
 
 ### Fixed
 - Fixed a bug in `aiclassify` for the OpenAI GPT4o models that have a different tokenizer. Unknown model IDs will throw an error.
diff --git a/docs/src/frequently_asked_questions.md b/docs/src/frequently_asked_questions.md
index d9a89d431..5e6c3ea54 100644
--- a/docs/src/frequently_asked_questions.md
+++ b/docs/src/frequently_asked_questions.md
@@ -119,6 +119,33 @@ Assuming the price per call was $0.0001, you'd pay 2 cents for the job and save
 Resources:
 - [OpenAI Pricing per 1000 tokens](https://openai.com/pricing)
 
+## How to try new OpenAI models if I'm not Tier 5 customer?
+
+As of September 2024, you cannot access the new o1 models via API unless you're a Tier 5 customer.
+
+Fortunately, you can use OpenRouter to access these new models.
+
+1) Get your API key from [OpenRouter](https://openrouter.ai/keys)
+2) Add some minimum [Credits](https://openrouter.ai/credits) to the account (eg, $5).
+3) Set it as an environment variable (or use local preferences): `ENV["OPENROUTER_API_KEY"] = "<your key>"`
+4) Use the model aliases with `or` prefix, eg, `oro1` for o1-preview or `oro1m` for o1-mini.
+
+Example:
+```julia
+# Let's use o1-preview model hosted on OpenRouter ("or" prefix)
+msg = aigenerate("What is the meaning of life?"; model="oro1")
+```
+
+Note: There are some quirks for the o1 models. 
+For example, the new o1 series does NOT support `SystemMessage` yet, so OpenRouter does some tricks (likely converting them to normal user messages).
+To be in control of this behavior and have comparable behavior to the native OpenAI API, you can use kwarg `no_system_message=true` in `aigenerate` to ensure OpenRouter does not do any tricks.
+
+Example:
+```julia
+# Let's use o1-mini and disable adding automatic system message
+msg = aigenerate("What is the meaning of life?"; model="oro1m", no_system_message=true)
+```
+
 ## Configuring the Environment Variable for API Key
 
 This is a guide for OpenAI's API key, but it works for any other API key you might need (eg, `MISTRALAI_API_KEY` for MistralAI API).
@@ -202,6 +229,19 @@ There are three ways how you can customize your workflows (especially when you u
 2) Register your model and its associated schema  (`PT.register_model!(; name="123", schema=PT.OllamaSchema())`). You won't have to specify the schema anymore only the model name. See [Working with Ollama](#working-with-ollama) for more information.
 3) Override your default model (`PT.MODEL_CHAT`) and schema (`PT.PROMPT_SCHEMA`). It can be done persistently with Preferences, eg, `PT.set_preferences!("PROMPT_SCHEMA" => "OllamaSchema", "MODEL_CHAT"=>"llama2")`.
 
+## Using Custom API Providers like Azure or Databricks
+
+Several providers are directly supported (eg, Databricks), check the available prompt schemas (eg, `subtypes(PT.AbstractOpenAISchema)`).
+
+If you need a custom URL or a few keyword parameters, refer to the implementation of DatabricksOpenAISchema.
+You effectively need to create your own prompt schema (`struct MySchema <: PT.AbstractOpenAISchema`) and override the OpenAI.jl behavior. The easiest way is to provide your custom method for `OpenAI.create_chat` and customize the `url`, `api_key`, and other `kwargs` fields.
+You can follow the implementation of `create_chat` for `DatabricksOpenAISchema` in `src/llm_openAI.jl`.
+
+Once your schema is ready, you can register the necessary models via `PT.register_model!(; name="myschema", schema=MySchema())`.
+You can also add aliases for easier access (eg, `PT.MODEL_ALIASES["mymodel"] = "my-model-with-really-long-name"`).
+
+If you would like to use some heavily customized API, eg, your company's internal LLM proxy (to change headers, URL paths, etc.), refer to the example `examples/adding_custom_API.jl` in the repo.
+
 ## How to have Multi-turn Conversations?
 
 Let's say you would like to respond back to a model's response. How to do it?
diff --git a/examples/adding_custom_API.jl b/examples/adding_custom_API.jl
new file mode 100644
index 000000000..9f242d2dc
--- /dev/null
+++ b/examples/adding_custom_API.jl
@@ -0,0 +1,85 @@
+# Example of custom API integration, eg, custom enterprise proxy with special headers
+#
+# This should NOT be necessary unless you have a private LLM / private proxy with specialized API structure and headers.
+# For most new APIs, you should check out the FAQ on "Using Custom API Providers like Azure or Databricks"
+# DatabricksOpenAISchema is a good example how to do simple API integration.
+#
+# For heavily customized APIs, follow the example below. Again, do this only if you have no other choice!!
+
+# We will need to provide a custom "provider" and custom methods for `OpenAI.jl` to override how it builds the AUTH headers and URL.
+
+using PromptingTools
+const PT = PromptingTools
+using HTTP
+using JSON3
+
+## OpenAI.jl work
+# Define a custom provider for OpenAI to override the default behavior
+abstract type MyCustomProvider <: PT.AbstractCustomProvider end
+
+@kwdef struct MyModelProvider <: MyCustomProvider
+    api_key::String = ""
+    base_url::String = "https://api.example.com/v1239123/modelxyz/completions_that_are_not_standard"
+    api_version::String = ""
+end
+
+# Tell OpenAI not to use "api" (=endpoints)
+function PT.OpenAI.build_url(provider::MyCustomProvider, api::AbstractString = "")
+    string(provider.base_url)
+end
+
+function PT.OpenAI.auth_header(
+        provider::MyCustomProvider, api_key::AbstractString = provider.api_key)
+    ## Note this DOES NOT have any Basic Auth! Assumes you use something custom
+    ["Content-Type" => "application/json", "Extra-custom-authorization" => api_key]
+end
+
+## PromptingTools.jl work
+# Define a custom schema
+struct MyCustomSchema <: PT.AbstractOpenAISchema end
+
+# Implement create_chat for the custom schema
+function PT.OpenAI.create_chat(schema::MyCustomSchema,
+        api_key::AbstractString,
+        model::AbstractString,
+        conversation;
+        url::String = "",
+        ## Add any required kwargs here, APIs may have different requirements
+        max_tokens::Int = 2048,
+        kwargs...)
+    ## Depending on your needs, you can get api_key from ENV variable!!
+    ## Eg, api_key = get(ENV, "CUSTOM_API_KEY", "")
+    provider = MyModelProvider(; api_key, base_url = url)
+
+    ## The first arg will be ignored, doesn't matter what you put there
+    PT.OpenAI.openai_request("ignore-me", provider;
+        method = "POST",
+        messages = conversation,
+        streamcallback = nothing,
+        max_tokens = max_tokens,
+        model = model,
+        kwargs...)
+end
+
+## Model registration
+## Any alias you like (can be many)
+PromptingTools.MODEL_ALIASES["myprecious"] = "custom-model-xyz"
+## Register the exact model name to send to your API
+PromptingTools.register_model!(;
+    name = "custom-model-xyz",
+    schema = MyCustomSchema())
+
+## Example usage
+api_key = "..." # use ENV to provide this automatically
+url = "..."  # use ENV to provide this or hardcode in your create_chat function!!
+msg = aigenerate("Hello, how are you?"; model = "myprecious", api_kwargs = (; api_key, url))
+
+## Custom usage - no need to register anything
+function myai(msg::AbstractString)
+    model = "custom-model-xyz"
+    schema = MyCustomSchema()
+    api_key = "..." # use ENV to provide this automatically
+    url = "..."  # use ENV to provide this or hardcode in your create_chat function!!
+    aigenerate(schema, msg; model, api_kwargs = (; api_key, url))
+end
+msg = myai("Hello, how are you?")
diff --git a/src/llm_anthropic.jl b/src/llm_anthropic.jl
index c3e6fc8d2..0a0a8153a 100644
--- a/src/llm_anthropic.jl
+++ b/src/llm_anthropic.jl
@@ -9,6 +9,7 @@
         messages::Vector{<:AbstractMessage};
         aiprefill::Union{Nothing, AbstractString} = nothing,
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         tools::Vector{<:Dict{String, <:Any}} = Dict{String, Any}[],
         cache::Union{Nothing, Symbol} = nothing,
         kwargs...)
@@ -18,6 +19,7 @@ Builds a history of the conversation to provide the prompt to the API. All unspe
 # Keyword Arguments
 - `aiprefill`: A string to be used as a prefill for the AI response. This steer the AI response in a certain direction (and potentially save output tokens).
 - `conversation`: Past conversation to be included in the beginning of the prompt (for continued conversations).
+- `no_system_message`: If `true`, do not include the default system message in the conversation history OR convert any provided system message to a user message.
 - `tools`: A list of tools to be used in the conversation. Added to the end of the system prompt to enforce its use.
 - `cache`: A symbol representing the caching strategy to be used. Currently only `nothing` (no caching), `:system`, `:tools`,`:last` and `:all` are supported.
 """
@@ -25,6 +27,7 @@ function render(schema::AbstractAnthropicSchema,
         messages::Vector{<:AbstractMessage};
         aiprefill::Union{Nothing, AbstractString} = nothing,
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         tools::Vector{<:Dict{String, <:Any}} = Dict{String, Any}[],
         cache::Union{Nothing, Symbol} = nothing,
         kwargs...)
@@ -35,7 +38,8 @@ function render(schema::AbstractAnthropicSchema,
     system = nothing
 
     ## First pass: keep the message types but make the replacements provided in `kwargs`
-    messages_replaced = render(NoSchema(), messages; conversation, kwargs...)
+    messages_replaced = render(
+        NoSchema(), messages; conversation, no_system_message, kwargs...)
 
     ## Second pass: convert to the message-based schema
     conversation = Dict{String, Any}[]
@@ -73,7 +77,7 @@ function render(schema::AbstractAnthropicSchema,
     if is_valid_conversation && (cache == :last || cache == :all)
         conversation[end]["content"][end]["cache_control"] = Dict("type" => "ephemeral")
     end
-    if !isnothing(system) && (cache == :system || cache == :all)
+    if !no_system_message && !isnothing(system) && (cache == :system || cache == :all)
         ## Apply cache for system message
         system = [Dict("type" => "text", "text" => system,
             "cache_control" => Dict("type" => "ephemeral"))]
@@ -214,6 +218,7 @@ end
         return_all::Bool = false, dry_run::Bool = false,
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
         streamcallback::Any = nothing,
+        no_system_message::Bool = false,
         aiprefill::Union{Nothing, AbstractString} = nothing,
         http_kwargs::NamedTuple = NamedTuple(), api_kwargs::NamedTuple = NamedTuple(),
         cache::Union{Nothing, Symbol} = nothing,
@@ -232,6 +237,7 @@ Generate an AI response based on a given prompt using the Anthropic API.
 - `conversation::AbstractVector{<:AbstractMessage}=[]`: Not allowed for this schema. Provided only for compatibility.
 - `streamcallback::Any`: A callback function to handle streaming responses. Can be simply `stdout` or `StreamCallback` object. See `?StreamCallback` for details.
   Note: We configure the `StreamCallback` (and necessary `api_kwargs`) for you, unless you specify the `flavor`. See `?configure_callback!` for details.
+- `no_system_message::Bool=false`: If `true`, do not include the default system message in the conversation history OR convert any provided system message to a user message.
 - `aiprefill::Union{Nothing, AbstractString}`: A string to be used as a prefill for the AI response. This steer the AI response in a certain direction (and potentially save output tokens). It MUST NOT end with a trailing with space. Useful for JSON formatting.
 - `http_kwargs::NamedTuple`: Additional keyword arguments for the HTTP request. Defaults to empty `NamedTuple`.
 - `api_kwargs::NamedTuple`: Additional keyword arguments for the Ollama API. Defaults to an empty `NamedTuple`.
@@ -329,6 +335,7 @@ function aigenerate(
         return_all::Bool = false, dry_run::Bool = false,
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
         streamcallback::Any = nothing,
+        no_system_message::Bool = false,
         aiprefill::Union{Nothing, AbstractString} = nothing,
         http_kwargs::NamedTuple = NamedTuple(), api_kwargs::NamedTuple = NamedTuple(),
         cache::Union{Nothing, Symbol} = nothing,
@@ -339,7 +346,8 @@ function aigenerate(
     @assert (isnothing(aiprefill)||!isempty(strip(aiprefill))) "`aiprefill` must not be empty`"
     ## Find the unique ID for the model alias provided
     model_id = get(MODEL_ALIASES, model, model)
-    conv_rendered = render(prompt_schema, prompt; aiprefill, conversation, cache, kwargs...)
+    conv_rendered = render(
+        prompt_schema, prompt; no_system_message, aiprefill, conversation, cache, kwargs...)
 
     if !dry_run
         @info conv_rendered.conversation
@@ -383,6 +391,7 @@ function aigenerate(
         conversation,
         return_all,
         dry_run,
+        no_system_message,
         kwargs...)
     return output
 end
diff --git a/src/llm_google.jl b/src/llm_google.jl
index 0a9f0fa20..e193b8d8f 100644
--- a/src/llm_google.jl
+++ b/src/llm_google.jl
@@ -10,21 +10,24 @@ end
     render(schema::AbstractGoogleSchema,
         messages::Vector{<:AbstractMessage};
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         kwargs...)
 
 Builds a history of the conversation to provide the prompt to the API. All unspecified kwargs are passed as replacements such that `{{key}}=>value` in the template.
 
 # Keyword Arguments
 - `conversation`: An optional vector of `AbstractMessage` objects representing the conversation history. If not provided, it is initialized as an empty vector.
-
+- `no_system_message::Bool=false`: If `true`, do not include the default system message in the conversation history OR convert any provided system message to a user message.
 """
 function render(schema::AbstractGoogleSchema,
         messages::Vector{<:AbstractMessage};
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         kwargs...)
     ##
     ## First pass: keep the message types but make the replacements provided in `kwargs`
-    messages_replaced = render(NoSchema(), messages; conversation, kwargs...)
+    messages_replaced = render(
+        NoSchema(), messages; conversation, no_system_message, kwargs...)
 
     ## Second pass: convert to the OpenAI schema
     conversation = Dict{Symbol, Any}[]
@@ -78,6 +81,8 @@ end
         verbose::Bool = true,
         api_key::String = GOOGLE_API_KEY,
         model::String = "gemini-pro", return_all::Bool = false, dry_run::Bool = false,
+        conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         http_kwargs::NamedTuple = (retry_non_idempotent = true,
             retries = 5,
             readtimeout = 120), api_kwargs::NamedTuple = NamedTuple(),
@@ -98,6 +103,7 @@ Note:
 - `return_all::Bool=false`: If `true`, returns the entire conversation history, otherwise returns only the last message (the `AIMessage`).
 - `dry_run::Bool=false`: If `true`, skips sending the messages to the model (for debugging, often used with `return_all=true`).
 - `conversation`: An optional vector of `AbstractMessage` objects representing the conversation history. If not provided, it is initialized as an empty vector.
+- `no_system_message::Bool=false`: If `true`, do not include the default system message in the conversation history OR convert any provided system message to a user message.
 - `http_kwargs`: A named tuple of HTTP keyword arguments.
 - `api_kwargs`: A named tuple of API keyword arguments.
 - `kwargs`: Prompt variables to be used to fill the prompt/template
@@ -151,6 +157,7 @@ function aigenerate(prompt_schema::AbstractGoogleSchema, prompt::ALLOWED_PROMPT_
         api_key::String = GOOGLE_API_KEY,
         model::String = "gemini-pro", return_all::Bool = false, dry_run::Bool = false,
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         http_kwargs::NamedTuple = (retry_non_idempotent = true,
             retries = 5,
             readtimeout = 120), api_kwargs::NamedTuple = NamedTuple(),
@@ -166,7 +173,8 @@ function aigenerate(prompt_schema::AbstractGoogleSchema, prompt::ALLOWED_PROMPT_
 
     ## Find the unique ID for the model alias provided
     model_id = get(MODEL_ALIASES, model, model)
-    conv_rendered = render(prompt_schema, prompt; conversation, kwargs...)
+    conv_rendered = render(
+        prompt_schema, prompt; conversation, no_system_message, kwargs...)
 
     if !dry_run
         time = @elapsed r = ggi_generate_content(prompt_schema, api_key,
@@ -195,6 +203,7 @@ function aigenerate(prompt_schema::AbstractGoogleSchema, prompt::ALLOWED_PROMPT_
         conversation,
         return_all,
         dry_run,
+        no_system_message,
         kwargs...)
 
     return output
diff --git a/src/llm_interface.jl b/src/llm_interface.jl
index a56e84e10..40669844e 100644
--- a/src/llm_interface.jl
+++ b/src/llm_interface.jl
@@ -207,6 +207,21 @@ Requires one environment variables to be set:
 """
 struct DeepSeekOpenAISchema <: AbstractOpenAISchema end
 
+"""
+    OpenRouterOpenAISchema
+
+Schema to call the [OpenRouter](https://openrouter.ai/) API.
+
+Links:
+- [Get your API key](https://openrouter.ai/keys)
+- [API Reference](https://openrouter.ai/docs)
+- [Available models](https://openrouter.ai/models)
+
+Requires one environment variable to be set:
+- `OPENROUTER_API_KEY`: Your API key
+"""
+struct OpenRouterOpenAISchema <: AbstractOpenAISchema end
+
 abstract type AbstractOllamaSchema <: AbstractPromptSchema end
 
 """
diff --git a/src/llm_ollama.jl b/src/llm_ollama.jl
index 5d6bdd240..0c80a539a 100644
--- a/src/llm_ollama.jl
+++ b/src/llm_ollama.jl
@@ -12,21 +12,24 @@
     render(schema::AbstractOllamaSchema,
         messages::Vector{<:AbstractMessage};
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         kwargs...)
 
 Builds a history of the conversation to provide the prompt to the API. All unspecified kwargs are passed as replacements such that `{{key}}=>value` in the template.
 
 # Keyword Arguments
 - `conversation`: An optional vector of `AbstractMessage` objects representing the conversation history. If not provided, it is initialized as an empty vector.
-
+- `no_system_message`: If `true`, do not include the default system message in the conversation history OR convert any provided system message to a user message.
 """
 function render(schema::AbstractOllamaSchema,
         messages::Vector{<:AbstractMessage};
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         kwargs...)
     ##
     ## First pass: keep the message types but make the replacements provided in `kwargs`
-    messages_replaced = render(NoSchema(), messages; conversation, kwargs...)
+    messages_replaced = render(
+        NoSchema(), messages; conversation, no_system_message, kwargs...)
 
     ## Second pass: convert to the OpenAI schema
     conversation = Dict{String, Any}[]
@@ -140,13 +143,15 @@ function aigenerate(prompt_schema::AbstractOllamaSchema, prompt::ALLOWED_PROMPT_
         model::String = MODEL_CHAT,
         return_all::Bool = false, dry_run::Bool = false,
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         http_kwargs::NamedTuple = NamedTuple(), api_kwargs::NamedTuple = NamedTuple(),
         kwargs...)
     ##
     global MODEL_ALIASES
     ## Find the unique ID for the model alias provided
     model_id = get(MODEL_ALIASES, model, model)
-    conv_rendered = render(prompt_schema, prompt; conversation, kwargs...)
+    conv_rendered = render(
+        prompt_schema, prompt; conversation, no_system_message, kwargs...)
 
     if !dry_run
         time = @elapsed resp = ollama_api(prompt_schema, nothing;
@@ -176,6 +181,7 @@ function aigenerate(prompt_schema::AbstractOllamaSchema, prompt::ALLOWED_PROMPT_
         conversation,
         return_all,
         dry_run,
+        no_system_message,
         kwargs...)
     return output
 end
diff --git a/src/llm_openai.jl b/src/llm_openai.jl
index 5fde45cf6..1b11fc063 100644
--- a/src/llm_openai.jl
+++ b/src/llm_openai.jl
@@ -4,6 +4,7 @@
         messages::Vector{<:AbstractMessage};
         image_detail::AbstractString = "auto",
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         kwargs...)
 
 Builds a history of the conversation to provide the prompt to the API. All unspecified kwargs are passed as replacements such that `{{key}}=>value` in the template.
@@ -11,17 +12,19 @@ Builds a history of the conversation to provide the prompt to the API. All unspe
 # Keyword Arguments
 - `image_detail`: Only for `UserMessageWithImages`. It represents the level of detail to include for images. Can be `"auto"`, `"high"`, or `"low"`.
 - `conversation`: An optional vector of `AbstractMessage` objects representing the conversation history. If not provided, it is initialized as an empty vector.
-
+- `no_system_message`: If `true`, do not include the default system message in the conversation history OR convert any provided system message to a user message.
 """
 function render(schema::AbstractOpenAISchema,
         messages::Vector{<:AbstractMessage};
         image_detail::AbstractString = "auto",
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         kwargs...)
     ##
     @assert image_detail in ["auto", "high", "low"] "Image detail must be one of: auto, high, low"
     ## First pass: keep the message types but make the replacements provided in `kwargs`
-    messages_replaced = render(NoSchema(), messages; conversation, kwargs...)
+    messages_replaced = render(
+        NoSchema(), messages; conversation, no_system_message, kwargs...)
 
     ## Second pass: convert to the OpenAI schema
     conversation = Dict{String, Any}[]
@@ -226,6 +229,19 @@ function OpenAI.create_chat(schema::DeepSeekOpenAISchema,
         base_url = url)
     OpenAI.create_chat(provider, model, conversation; kwargs...)
 end
+function OpenAI.create_chat(schema::OpenRouterOpenAISchema,
+        api_key::AbstractString,
+        model::AbstractString,
+        conversation;
+        url::String = "https://openrouter.ai/api/v1",
+        kwargs...)
+    # Build the corresponding provider object
+    # try to override provided api_key because the default is OpenAI key
+    provider = CustomProvider(;
+        api_key = isempty(OPENROUTER_API_KEY) ? api_key : OPENROUTER_API_KEY,
+        base_url = url)
+    OpenAI.create_chat(provider, model, conversation; kwargs...)
+end
 function OpenAI.create_chat(schema::DatabricksOpenAISchema,
         api_key::AbstractString,
         model::AbstractString,
@@ -443,6 +459,7 @@ end
         model::String = MODEL_CHAT, return_all::Bool = false, dry_run::Bool = false,
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
         streamcallback::Any = nothing,
+        no_system_message::Bool = false,
         http_kwargs::NamedTuple = (retry_non_idempotent = true,
             retries = 5,
             readtimeout = 120), api_kwargs::NamedTuple = NamedTuple(),
@@ -461,6 +478,7 @@ Generate an AI response based on a given prompt using the OpenAI API.
 - `conversation`: An optional vector of `AbstractMessage` objects representing the conversation history. If not provided, it is initialized as an empty vector.
 - `streamcallback`: A callback function to handle streaming responses. Can be simply `stdout` or a `StreamCallback` object. See `?StreamCallback` for details.
   Note: We configure the `StreamCallback` (and necessary `api_kwargs`) for you, unless you specify the `flavor`. See `?configure_callback!` for details.
+- `no_system_message::Bool=false`: If `true`, the default system message is not included in the conversation history. Any existing system message is converted to a `UserMessage`.
 - `http_kwargs`: A named tuple of HTTP keyword arguments.
 - `api_kwargs`: A named tuple of API keyword arguments. Useful parameters include:
     - `temperature`: A float representing the temperature for sampling (ie, the amount of "creativity"). Often defaults to `0.7`.
@@ -538,6 +556,7 @@ function aigenerate(prompt_schema::AbstractOpenAISchema, prompt::ALLOWED_PROMPT_
         model::String = MODEL_CHAT, return_all::Bool = false, dry_run::Bool = false,
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
         streamcallback::Any = nothing,
+        no_system_message::Bool = false,
         http_kwargs::NamedTuple = (retry_non_idempotent = true,
             retries = 5,
             readtimeout = 120), api_kwargs::NamedTuple = NamedTuple(),
@@ -546,7 +565,8 @@ function aigenerate(prompt_schema::AbstractOpenAISchema, prompt::ALLOWED_PROMPT_
     global MODEL_ALIASES
     ## Find the unique ID for the model alias provided
     model_id = get(MODEL_ALIASES, model, model)
-    conv_rendered = render(prompt_schema, prompt; conversation, kwargs...)
+    conv_rendered = render(
+        prompt_schema, prompt; conversation, no_system_message, kwargs...)
 
     if !dry_run
         time = @elapsed r = create_chat(prompt_schema, api_key,
@@ -587,6 +607,7 @@ function aigenerate(prompt_schema::AbstractOpenAISchema, prompt::ALLOWED_PROMPT_
         conversation,
         return_all,
         dry_run,
+        no_system_message,
         kwargs...)
 
     return output
diff --git a/src/llm_shared.jl b/src/llm_shared.jl
index 38682fde8..42cfceea9 100644
--- a/src/llm_shared.jl
+++ b/src/llm_shared.jl
@@ -11,6 +11,7 @@ role4render(schema::AbstractPromptSchema, msg::AIMessage) = "assistant"
     render(schema::NoSchema,
         messages::Vector{<:AbstractMessage};
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         replacement_kwargs...)
 
 Renders a conversation history from a vector of messages with all replacement variables specified in `replacement_kwargs`.
@@ -20,6 +21,7 @@ It is the first pass of the prompt rendering system, and is used by all other sc
 # Keyword Arguments
 - `image_detail`: Only for `UserMessageWithImages`. It represents the level of detail to include for images. Can be `"auto"`, `"high"`, or `"low"`.
 - `conversation`: An optional vector of `AbstractMessage` objects representing the conversation history. If not provided, it is initialized as an empty vector.
+- `no_system_message`: If `true`, do not include the default system message in the conversation history OR convert any provided system message to a user message.
 
 # Notes
 - All unspecified kwargs are passed as replacements such that `{{key}}=>value` in the template.
@@ -29,6 +31,7 @@ It is the first pass of the prompt rendering system, and is used by all other sc
 function render(schema::NoSchema,
         messages::Vector{<:AbstractMessage};
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         replacement_kwargs...)
     ## copy the conversation to avoid mutating the original
     conversation = copy(conversation)
@@ -41,8 +44,9 @@ function render(schema::NoSchema,
             replacements = ["{{$(key)}}" => value
                             for (key, value) in pairs(replacement_kwargs)
                             if key in msg.variables]
+            ## Force System message to UserMessage if no_system_message=true
+            MSGTYPE = no_system_message && issystemmessage(msg) ? UserMessage : typeof(msg)
             # Rebuild the message with the replaced content
-            MSGTYPE = typeof(msg)
             new_msg = MSGTYPE(;
                 # unpack the type to replace only the content field
                 [(field, getfield(msg, field)) for field in fieldnames(typeof(msg))]...,
@@ -70,8 +74,10 @@ function render(schema::NoSchema,
     ## Multiple system prompts are not allowed
     (count_system_msg > 1) && throw(ArgumentError("Only one system message is allowed."))
     ## Add default system prompt if not provided
-    (count_system_msg == 0) && pushfirst!(conversation,
-        SystemMessage("Act as a helpful AI assistant"))
+    if (count_system_msg == 0) && !no_system_message
+        pushfirst!(conversation,
+            SystemMessage("Act as a helpful AI assistant"))
+    end
 
     return conversation
 end
@@ -82,6 +88,7 @@ end
         return_all::Bool = false,
         dry_run::Bool = false,
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         kwargs...)
 
 Finalizes the outputs of the ai* functions by either returning the conversation history or the last message.
@@ -92,19 +99,21 @@ Finalizes the outputs of the ai* functions by either returning the conversation
   Useful for debugging when you want to check the specific schema rendering. 
 - `conversation::AbstractVector{<:AbstractMessage}=[]`: An optional vector of `AbstractMessage` objects representing the conversation history. If not provided, it is initialized as an empty vector.
 - `kwargs...`: Variables to replace in the prompt template.
+- `no_system_message::Bool=false`: If true, the default system message is not included in the conversation history. Any existing system message is converted to a `UserMessage`.
 """
 function finalize_outputs(prompt::ALLOWED_PROMPT_TYPE, conv_rendered::Any,
         msg::Union{Nothing, AbstractMessage, AbstractVector{<:AbstractMessage}};
         return_all::Bool = false,
         dry_run::Bool = false,
         conversation::AbstractVector{<:AbstractMessage} = AbstractMessage[],
+        no_system_message::Bool = false,
         kwargs...)
     if return_all
         if !dry_run
             # If not a dry_run, re-create the messages sent to the model before schema application
             # This is a duplication of work, as we already have the rendered messages in conv_rendered,
             # but we prioritize the user's experience over performance here (ie, render(OpenAISchema,msgs) does everything under the hood)
-            output = render(NoSchema(), prompt; conversation, kwargs...)
+            output = render(NoSchema(), prompt; conversation, no_system_message, kwargs...)
             if msg isa AbstractVector
                 ## handle multiple messages (multi-sample)
                 append!(output, msg)
diff --git a/src/user_preferences.jl b/src/user_preferences.jl
index 935fe1b95..e8a6ed10e 100644
--- a/src/user_preferences.jl
+++ b/src/user_preferences.jl
@@ -21,6 +21,7 @@ Check your preferences by calling `get_preferences(key::String)`.
 - `VOYAGE_API_KEY`: The API key for the Voyage API. Free tier is upto 50M tokens! Get yours from [here](https://dash.voyageai.com/api-keys).
 - `GROQ_API_KEY`: The API key for the Groq API. Free in beta! Get yours from [here](https://console.groq.com/keys).
 - `DEEPSEEK_API_KEY`: The API key for the DeepSeek API. Get \$5 credit when you join. Get yours from [here](https://platform.deepseek.com/api_keys).
+- `OPENROUTER_API_KEY`: The API key for the OpenRouter API. Get yours from [here](https://openrouter.ai/keys).
 - `MODEL_CHAT`: The default model to use for aigenerate and most ai* calls. See `MODEL_REGISTRY` for a list of available models or define your own.
 - `MODEL_EMBEDDING`: The default model to use for aiembed (embedding documents). See `MODEL_REGISTRY` for a list of available models or define your own.
 - `PROMPT_SCHEMA`: The default prompt schema to use for aigenerate and most ai* calls (if not specified in `MODEL_REGISTRY`). Set as a string, eg, `"OpenAISchema"`.
@@ -49,6 +50,7 @@ Define your `register_model!()` calls in your `startup.jl` file to make them ava
 - `VOYAGE_API_KEY`: The API key for the Voyage API. Free tier is upto 50M tokens! Get yours from [here](https://dash.voyageai.com/api-keys).
 - `GROQ_API_KEY`: The API key for the Groq API. Free in beta! Get yours from [here](https://console.groq.com/keys).
 - `DEEPSEEK_API_KEY`: The API key for the DeepSeek API. Get \$5 credit when you join. Get yours from [here](https://platform.deepseek.com/api_keys).
+- `OPENROUTER_API_KEY`: The API key for the OpenRouter API. Get yours from [here](https://openrouter.ai/keys).
 - `LOG_DIR`: The directory to save the logs to, eg, when using `SaverSchema <: AbstractTracerSchema`. Defaults to `joinpath(pwd(), "log")`. Refer to `?SaverSchema` for more information on how it works and examples.
 
 Preferences.jl takes priority over ENV variables, so if you set a preference, it will take precedence over the ENV variable.
@@ -69,6 +71,7 @@ const ALLOWED_PREFERENCES = ["MISTRALAI_API_KEY",
     "VOYAGE_API_KEY",
     "GROQ_API_KEY",
     "DEEPSEEK_API_KEY",
+    "OPENROUTER_API_KEY",  # Added OPENROUTER_API_KEY
     "MODEL_CHAT",
     "MODEL_EMBEDDING",
     "MODEL_ALIASES",
@@ -147,6 +150,7 @@ global ANTHROPIC_API_KEY::String = ""
 global VOYAGE_API_KEY::String = ""
 global GROQ_API_KEY::String = ""
 global DEEPSEEK_API_KEY::String = ""
+global OPENROUTER_API_KEY::String = ""
 global LOCAL_SERVER::String = ""
 global LOG_DIR::String = ""
 
@@ -196,6 +200,9 @@ function load_api_keys!()
     global DEEPSEEK_API_KEY
     DEEPSEEK_API_KEY = @load_preference("DEEPSEEK_API_KEY",
         default=get(ENV, "DEEPSEEK_API_KEY", ""))
+    global OPENROUTER_API_KEY  # Added OPENROUTER_API_KEY
+    OPENROUTER_API_KEY = @load_preference("OPENROUTER_API_KEY",
+        default=get(ENV, "OPENROUTER_API_KEY", ""))
     global LOCAL_SERVER
     LOCAL_SERVER = @load_preference("LOCAL_SERVER",
         default=get(ENV, "LOCAL_SERVER", ""))
@@ -392,7 +399,12 @@ aliases = merge(
         "ggemma9" => "gemma2-9b-it",
         ## DeepSeek
         "dschat" => "deepseek-chat",
-        "dscode" => "deepseek-coder"
+        "dscode" => "deepseek-coder",
+        ## OpenRouter
+        "oro1" => "openai/o1-preview",
+        "oro1m" => "openai/o1-mini",
+        "orcop" => "cohere/command-r-plus-08-2024",
+        "orco" => "cohere/command-r-08-2024"
     ),
     ## Load aliases from preferences as well
     @load_preference("MODEL_ALIASES", default=Dict{String, String}()))
@@ -824,7 +836,43 @@ registry = Dict{String, ModelSpec}(
         DeepSeekOpenAISchema(),
         1.4e-7,
         2.8e-7,
-        "Deepseek.com-hosted coding model. Max 16K context. See details [here](https://platform.deepseek.com/docs)")
+        "Deepseek.com-hosted coding model. Max 16K context. See details [here](https://platform.deepseek.com/docs)"),
+    ## OpenRouter models
+    "openai/o1-preview" => ModelSpec("openai/o1-preview",
+        OpenRouterOpenAISchema(),
+        15e-6,
+        60e-6,
+        "OpenRouter's hosted version of OpenAI's latest reasoning model o1-preview. 128K context, max output 32K tokens. Details unknown."),
+    "openai/o1-preview-2024-09-12" => ModelSpec("openai/o1-preview-2024-09-12",
+        OpenRouterOpenAISchema(),
+        15e-6,
+        60e-6,
+        "OpenRouter's hosted version of OpenAI's latest reasoning model o1-preview, version 2024-09-12. 128K context, max output 32K tokens. Details unknown."),
+    "openai/o1-mini" => ModelSpec("openai/o1-mini",
+        OpenRouterOpenAISchema(),
+        3e-6,
+        12e-6,
+        "OpenRouter's hosted version of OpenAI's latest and smallest reasoning model o1-mini. 128K context, max output 65K tokens. Details unknown."),
+    "openai/o1-mini-2024-09-12" => ModelSpec("openai/o1-mini-2024-09-12",
+        OpenRouterOpenAISchema(),
+        3e-6,
+        12e-6,
+        "OpenRouter's hosted version of OpenAI's latest and smallest reasoning model o1-mini, version 2024-09-12. 128K context, max output 65K tokens. Details unknown."),
+    "cohere/command-r-plus-08-2024" => ModelSpec("cohere/command-r-plus-08-2024",
+        OpenRouterOpenAISchema(),
+        2.5e-6,
+        10e-6,
+        "OpenRouter's hosted version of Cohere's latest and strongest model Command R Plus. 128K context, max output 4K tokens."),
+    "cohere/command-r-08-2024" => ModelSpec("cohere/command-r-08-2024",
+        OpenRouterOpenAISchema(),
+        1.5e-7,
+        6e-7,
+        "OpenRouter's hosted version of Cohere's latest smaller model Command R. 128K context, max output 4K tokens."),
+    "meta-llama/llama-3.1-405b" => ModelSpec("meta-llama/llama-3.1-405b",
+        OpenRouterOpenAISchema(),
+        2e-6,
+        2e-6,
+        "Meta's Llama3.1 405b, hosted by OpenRouter. This is a BASE model!! Max output 32K tokens, 131K context. See details [here](https://openrouter.ai/models/meta-llama/llama-3.1-405b)")
 )
 
 """
diff --git a/test/llm_shared.jl b/test/llm_shared.jl
index 82df905a5..d5451d84e 100644
--- a/test/llm_shared.jl
+++ b/test/llm_shared.jl
@@ -1,6 +1,6 @@
 using PromptingTools: render, NoSchema
 using PromptingTools: AIMessage, SystemMessage, AbstractMessage, AbstractChatMessage
-using PromptingTools: UserMessage, UserMessageWithImages
+using PromptingTools: UserMessage, UserMessageWithImages, DataMessage
 using PromptingTools: finalize_outputs, role4render
 
 @testset "render-NoSchema" begin
@@ -179,9 +179,34 @@ using PromptingTools: finalize_outputs, role4render
     ]
     conversation = render(schema, messages)
     @test conversation == expected_output
+
+    # Test no_system_message
+    messages = [
+        SystemMessage("System message 1"),
+        UserMessage("User message")
+    ]
+    expected_output = [
+        UserMessage("System message 1"),
+        UserMessage("User message")
+    ]
+    conversation = render(schema, messages; no_system_message = true)
+    @test conversation[1] isa UserMessage
+    @test conversation[2] isa UserMessage
+    @test conversation[1].content == "System message 1"
+    @test conversation[2].content == "User message"
+
+    ## No default message 
+    messages = [
+        UserMessage("User message")
+    ]
+    expected_output = [
+        UserMessage("User message")
+    ]
+    conversation = render(schema, messages; no_system_message = true)
+    @test conversation[1] isa UserMessage
+    @test conversation[1].content == "User message"
 end
 
-# Write 5 unit tests for finalize_outputs for various combinations of inputs. Use @test calls
 @testset "finalize_outputs" begin
     # Given a vector of messages and a single message, it should return the last message.
     messages = [