Rename functions and improve documentation

README.md

@@ -8,7 +8,7 @@ WiseGPTEx is an Elixir library that utilizes OpenAI's GPT-3.5-turbo model and An
 ```elixir
 def deps do
   [
-    {:wise_gpt_ex, "~> 0.5.0"}
+    {:wise_gpt_ex, "~> 0.6.0"}
   ]
 end
 ```
@@ -19,7 +19,7 @@ config :wise_gpt_ex, :openai_api_key, "your_openai_api_key"
 config :wise_gpt_ex, :anthropic_api_key, "your_anthropic_api_key"
 ```
 
-## Usage (OpenAI API)
+## Usage (only with OpenAI API)
 
 To use WiseGPTEx, simply call the `get_best_completion/2` or `get_best_completion_with_resolver/2` function with a question and optional list of options:
 ```elixir
@@ -32,23 +32,32 @@ opts = [model: "gpt-4", temperature: 0.4, num_completions: 4, timeout: 3_600_000
 {:ok, response} = WiseGPTEx.get_best_completion_with_resolver("What is the capital of France?", opts)
 ```
 
-You can also make a raw call to the OpenAI API using the `get_raw_completion/2` function:
+You can also make a raw call to the OpenAI API using the `openai_completion/2` function:
 ```elixir
 messages = [
   %{"role" => "system", "content" => "You are High School Geography Teacher"},
   %{"role" => "user", "content" => "What was the capital of France in 15th century?"}
 ]
-{ok, response} = WiseGPTEx.get_raw_completion(messages, [model: "gpt-4", temperature: 0.75, timeout: 3_600])
+{ok, response} = WiseGPTEx.openai_completion(messages, [model: "gpt-4", temperature: 0.75, timeout: 3_600])
 ```
 
 Note that the `get_best_completion_with_resolver/2` function is similar to `get_best_completion/2`.
 This is because the difference between these two functions is in the method of how they select the best completion, not in their usage or the nature of their inputs or outputs.
 The `get_best_completion_with_resolver/2` function will perform an additional API call to get a more accurate completion, which can be beneficial for complex or ambiguous queries.
-The `get_raw_completion/2` function allows sending a custom conversation to the API without any additional prompting or setting the up the system role etc. This is useful when you want direct access to the model's system messages.
+The `openai_completion/2` function allows sending a custom conversation to the API without any additional prompting or setting the up the system role etc. This is useful when you want direct access to the model's system messages.
 
+## OpenAI API
+For interactions with the OpenAI API, use the `openai_completion/1` function:
+```elixir
+{:ok, response} = WiseGPTEx.openai_completion("What is the capital of France?")
+{:ok, "Paris"}
+```
 ## Anthropic API
-For interactions with the Anthropic API, use the get_anthropic_completion/2 function:
-{:ok, response} = WiseGPTEx.get_anthropic_completion("Why is the sky blue?")
+For interactions with the Anthropic API, use the `anthropic_completion/1` function:
+```elixir
+{:ok, response} = WiseGPTEx.anthropic_completion("Why is the sky blue?")
+{:ok, "The sky is blue because of the way sunlight interacts with Earth's atmosphere."}
+```
 
 ## Options
 

lib/wise_gpt_ex.ex

@@ -5,28 +5,6 @@ defmodule WiseGPTEx do
   This module provides functions to obtain the best completion from the OpenAI models (default: "gpt-3.5-turbo") using the OpenAI API completions endpoint (`https://api.openai.com/v1/chat/completions`).
   The `get_best_completion/2` and `get_best_completion_with_resolver/2` functions take a question and an optional list of options to configure the API request. `get_best_completion_with_resolver/2` also involves a secondary step to resolve the best completion among the options, which leads to an additional API call for a more accurate response.
 
-  ## Installation
-
-  1. Add `wise_gpt_ex` to your list of dependencies in `mix.exs`:
-  ```elixir
-  def deps do
-    [
-      {:wise_gpt_ex, "~> 0.5.0"}
-    ]
-  end
-  ```
-
-  2. Add the OpenAI API key to your configuration file (e.g., config/config.exs):
-  ```elixir
-  config :wise_gpt_ex, :openai_api_key, "your_openai_api_key"
-  ```
-
-  3. Add the Anthropic API key to your configuration file (e.g., config/config.exs):
-  ```elixir
-  config :wise_gpt_ex, :anthropic_api_key, "your_anthropic_api_key"
-  ```
-
-
   ## Examples
 
   Basic usage:
@@ -43,7 +21,7 @@ defmodule WiseGPTEx do
       ...>   %{"role" => "system", "content" => "You are High School Geography Teacher"},
       ...>   %{"role" => "user", "content" => "What was the capital of France in 15th century?"}
       ...> ]
-      ...> WiseGPTEx.get_raw_completion(messages)
+      ...> WiseGPTEx.openai_completion(messages)
       {:ok, "The capital of France in the 15th century was Paris."}
 
   Using all available options:
@@ -61,7 +39,7 @@ defmodule WiseGPTEx do
 
   Anthropic API usage:
 
-      iex> WiseGPTEx.get_anthropic_completion("Why is the sky blue?")
+      iex> WiseGPTEx.anthropic_completion("Why is the sky blue?")
       {:ok, "The sky is blue because... [detailed explanation]"}
 
   ## Options
@@ -73,7 +51,7 @@ defmodule WiseGPTEx do
     * `:num_completions` - The number of completions to generate (default: 3).
     * `:timeout` - The maximum time in milliseconds to wait for a response from the OpenAI API (default: 3_600_000 ms, or 60 minutes).
 
-  For `get_anthropic_completion/2`, the following options can be passed:
+  For `anthropic_completion/2`, the following options can be passed:
 
     * `:model` - The version of the Claude model to use (default: "claude-2").
     * `:temperature` - Controls the randomness of the model's output (default: 0.1).
@@ -111,13 +89,13 @@ defmodule WiseGPTEx do
       ...>   %{"role" => "system", "content" => "You are High School Geography Teacher"},
       ...>   %{"role" => "user", "content" => "What was the capital of France in 15th century?"}
       ...> ]
-      ...> WiseGPTEx.get_raw_completion(messages)
+      ...> WiseGPTEx.openai_completion(messages)
       {:ok, "The capital of France in the 15th century was Paris."}
   ```
   """
-  @spec get_raw_completion(list(map()), Keyword.t()) :: {:ok, binary()} | {:error, any()}
-  def get_raw_completion(messages, opts \\ []) do
-    OpenAIHTTPClient.get_raw_completion(messages, opts)
+  @spec openai_completion(list(map()), Keyword.t()) :: {:ok, binary()} | {:error, any()}
+  def openai_completion(messages, opts \\ []) do
+    OpenAIHTTPClient.completion(messages, opts)
   end
 
   @doc """
@@ -248,12 +226,12 @@ defmodule WiseGPTEx do
   ## Example:
 
   ```elixir
-  iex> WiseGPTEx.get_anthropic_completion("Why is the sky blue?")
+  iex> WiseGPTEx.anthropic_completion("Why is the sky blue?")
   {:ok, "The sky is blue because... [detailed explanation]"}
   ```
   """
-  @spec get_anthropic_completion(binary(), Keyword.t()) :: {:ok, binary()} | {:error, any()}
-  def get_anthropic_completion(message, opts \\ []) do
+  @spec anthropic_completion(binary(), Keyword.t()) :: {:ok, binary()} | {:error, any()}
+  def anthropic_completion(message, opts \\ []) do
     AnthropicHTTPClient.complete(message, opts)
   end
 end

lib/wise_gpt_ex/openai_http_client.ex

@@ -8,9 +8,9 @@ defmodule WiseGPTEx.OpenAIHTTPClient do
 
     * `get_completions_with_reasoning/2` - Retrieves completions with reasoning from the OpenAI API based on a given message and an optional list of options.
     * `get_best_completion/3` - Determines the best completion from a list of completions and an optional list of options.
-    * `get_raw_completion/2` - Gets a raw completion from the API based on given messages, without additional prompting.
+    * `completion/2` - Gets a raw completion from the API based on given messages, without additional prompting.
 
-    **NOTE:**  `get_raw_completion/2` allows sending custom conversations with both role and content to the API, while the other functions add extra prompting to request reasoning, disambiguation, etc.
+    **NOTE:**  `completion/2` allows sending custom conversations with both role and content to the API, while the other functions add extra prompting to request reasoning, disambiguation, etc.
   """
   alias WiseGPTEx.OpenAIUtils, as: Utils
 
@@ -21,8 +21,8 @@ defmodule WiseGPTEx.OpenAIHTTPClient do
   # 60 minutes
   @default_timeout_ms 3_600_000
 
-  @spec get_raw_completion(list(map()), Keyword.t()) :: {:ok, binary()} | {:error, any()}
-  def get_raw_completion(messages, opts \\ []) do
+  @spec completion(list(map()), Keyword.t()) :: {:ok, binary()} | {:error, any()}
+  def completion(messages, opts \\ []) do
     model = Keyword.get(opts, :model, @default_model)
     temperature = Keyword.get(opts, :temperature, @default_temperature)
     timeout = Keyword.get(opts, :timeout, @default_timeout_ms)

mix.exs

@@ -1,7 +1,7 @@
 defmodule WiseGPTEx.MixProject do
   use Mix.Project
 
-  @version "0.5.0"
+  @version "0.6.0"
   @docs_url "http://hexdocs.pm/wise_gpt_ex"
   @github_url "https://github.com/isavita/wise_gpt_ex"
 
@@ -15,7 +15,8 @@ defmodule WiseGPTEx.MixProject do
       package: package(),
       description: description(),
       name: "WiseGPTEx",
-      source_url: @github_url
+      source_url: @github_url,
+      docs: docs()
     ]
   end
 
@@ -52,4 +53,14 @@ defmodule WiseGPTEx.MixProject do
       }
     ]
   end
+
+  defp docs do
+    [
+      main: "readme",
+      logo: "logo.png",
+      source_url: @github_url,
+      source_ref: "v#{@version}",
+      extras: ["README.md"]
+    ]
+  end
 end

test/wise_gpt_ex/openai_http_client_test.exs

@@ -3,7 +3,7 @@ defmodule WiseGPTEx.OpenAIHTTPClientTest do
   import Mock
   alias WiseGPTEx.OpenAIHTTPClient
 
-  describe "get_raw_completion/1" do
+  describe "openai_completion/1" do
     @success_resp %{
       status_code: 200,
       body:
@@ -30,7 +30,7 @@ defmodule WiseGPTEx.OpenAIHTTPClientTest do
 
           @success_resp
         end do
-        assert {:ok, completion} = OpenAIHTTPClient.get_raw_completion(messages)
+        assert {:ok, completion} = OpenAIHTTPClient.completion(messages)
         assert completion == "The capital of France in the 15th century was Paris."
       end
     end

test/wise_gpt_ex_test.exs

@@ -88,7 +88,7 @@ defmodule WiseGPTExTest do
     end
   end
 
-  describe "get_anthropic_completion/2" do
+  describe "anthropic_completion/2" do
     @anthropic_success_resp %{
       status_code: 200,
       body:
@@ -102,7 +102,7 @@ defmodule WiseGPTExTest do
         end do
         assert {:ok,
                 "The sky is blue because of the way sunlight interacts with Earth's atmosphere."} =
-                 WiseGPTEx.get_anthropic_completion("Why is the sky blue?")
+                 WiseGPTEx.anthropic_completion("Why is the sky blue?")
       end
     end
 
@@ -122,7 +122,7 @@ defmodule WiseGPTExTest do
                     "message" => "Unauthorized access",
                     "type" => "authentication_error"
                   }
-                }} = WiseGPTEx.get_anthropic_completion("Why is the sky blue?")
+                }} = WiseGPTEx.anthropic_completion("Why is the sky blue?")
       end
     end
   end