gpt-cli 0.1.2 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b82b15bff40eaab0d8c15e2273b275841d3501e8c0ae085443f35782175d3ab8
-  data.tar.gz: de41d86f71219206252e937180099cbd07b1c77abef0b6e71271e3faf3d170d9
+  metadata.gz: e970f253447aaac501f343585e284d0b7254b8fc696f4a9ad74430b38861c833
+  data.tar.gz: f1f40e893b47c5bd66d47b8a7156b855156bcb8bda8334340e0a0659746f4c01
 SHA512:
-  metadata.gz: 26ff8b088978790eebdc85904dc3c994a96ffa20d854fa0ba5123f52d3c8ff86b96e271bf975bb4b585f544c79becb6447dae9dd10cabb8a5cb28e030fc42104
-  data.tar.gz: fb1d336d91b5efe7ebf7c48659dbb3bdf4e240c2f54b19e4001ec4806b730ad145686852ce1b5768cf75d29f92f39ac61393098cc9c3db5ba4601ed00e022404
+  metadata.gz: 3f0e9f58ee5f1f5a03fb20c217d25d3d6da505d3481e9fad56d53dcb465e759da3a48d524aff9e093ca3c69d3dac72fa688e6c9e4301c66d603e67a5bfd4d099
+  data.tar.gz: 20d1bc99c963c155bbd396890cf216d06a665983709a76d2bdeb5179842cef1b5f923b024c5f7ebe794477362156666bc60f67ba2b663564313de6736008e451

data/CHANGELOG.md

@@ -4,7 +4,11 @@
 
 - Initial release
 
-## [0.1.1] - 2023-03-23
+## [0.1.2] - 2023-03-23
 
 - Define open ai model in env var
-- Input context pompts
+- Input context pompts
+
+## [0.1.3] - 2023-03-23
+
+- Custom contexts prompts support

data/README.md

@@ -1,7 +1,7 @@
 # GPTCLI
 
 This library provides a UNIX-ey interface to OpenAI.
-It is a fork of [openai_pipe](https://github.com/Aesthetikx/openai_pipe), created by [Aesthetikx](https://github.com/Aesthetikx/openai_pipe), kudos to him for his awesome work!  
+It is a fork of [openai_pipe](https://github.com/Aesthetikx/openai_pipe), created by [Aesthetikx](https://github.com/Aesthetikx/), kudos to him for his awesome work!  
 The goal of this fork was to add the ability to choose which OpenAI model to use, as well as adding context prompts support. Thanks to these new features, you can have your own highly specialized GPT4 personal assistant, directly in your terminal! Productivity stonks 📈📈📈   
 
 See [Installation](#installation) and [Setup](#setup) below, but first, some examples.
@@ -185,7 +185,11 @@ Set the model you want to use in ENV:
 ```bash
 export OPENAI_MODEL="gpt-3.5-turbo"
 ```
-(Optional) set the default context prompt you want to use (for now, there's only 3 basic prompts available `python`, `fullstack` and `blockchain` in `lib/contexts.rb`):
+Copy `gpt_contexts.sample.json` somewhere, for example `~/Documents/gpt_contexts.json`, then put the file path in ENV:
+```bash
+export OPENAI_CONTEXTS_PATH="path to gpt_contexts.json"
+```
+(Optional) set the default context prompt you want to use (for now, there's only 3 basic prompts available `python`, `fullstack` and `blockchain` in `gpt_contexts.sample.json`):
 ```bash
 export OPENAI_DEFAULT_CONTEXT="python"
 ```
@@ -198,8 +202,11 @@ alias gpt="gpt-cli"
 
 There's two optional parameters you can set when running `gpt`:  
 `gpt -c <custom_context_prompt> -p <your prompt>`  
-`--context -c`: this will be the context prompt, see basic contexts in `lib/contexts.rb`. You can put a key ofrom the contexts hash of `lib/contexts.rb` or a custom context.  
+
+`--context -c`: this will be the context prompt, see basic contexts in `gpt_contexts.sample.json`. You can put a key from `gpt_contexts.json` or a custom context. Default to ENV `OPENAI_DEFAULT_CONTEXT` if not set. Add your own context prompts in `gpt_contexts.json`.      
+
 `--prompt -p`: your actual prompt.  
+
 You can also run gpt without any arguments, just your question. In this case, the context prompt will default to the one defined by ENV var `OPENAI_DEFAULT_CONTEXT` if it exists. If not, no context will be added.  
 See examples above for an overview of some usecases. Possibilities are endless.
 
@@ -207,7 +214,13 @@ See examples above for an overview of some usecases. Possibilities are endless.
 
 Be aware that there is a cost associated every time GPT3 is invoked, so be mindful of your account usage. Also be wary of sending sensitive data to OpenAI, and also wary of arbitrarily executing scripts or programs that GPT3 generates.
 Also, this is my very first time working in Ruby. So please be indulgent 🙏  
-A future release will replace `lib/contexts.rb` by a JSON file so user will be able to easily add/modify custom context prompts.
+
+## TODO
+
+- Add conversation history support  
+- Add internet search support to feed prompt more accurately  
+- Add dall-e support  
+- Add proper documentation  
 
 ## Development
 

data/gpt_contexts.sample.json

@@ -0,0 +1,5 @@
+{
+    "python": "Imagine you are a senior software developer specialized in Python, Django, SQL and Machine Learning with 20 years of experience. You are very proficient at writing high quality, clean, concise and highly optimized code that follows the PEP recommendations. You are my personal assistant. You are here to help me in various tasks and answer my questions.",
+    "fullstack": "Imagine you are an Senior Fullstack Engineer with 20 of experience in UNIX systems, bash, Python, Django, SQL, Javascript, ReactJS. You are very proficient at writing high quality, clean, concise and well optimized code that follows the PEP recommendations. You are my personal assistant. You are here to help me in various tasks and answer my questions.",
+    "blockchain": "Imagine you are Vitalik Buterin. You created Ethereum and you are the most famous blockchain developer in the world.You have a very deep knowledge about EVM, Solidity, and the whole blockchain ecosystem.You know everything about the latest trends in the blockchain space and you are very proficient at writing high quality, clean, concise and well optimized code that follows the good practices.You are my personal assistant. You are here to help me in various tasks and answer my questions."
+}

data/lib/gpt-cli/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module GPTCLI
-  VERSION = "0.1.2"
+  VERSION = "0.1.3"
 end

data/lib/gpt-cli.rb

@@ -1,15 +1,16 @@
 # frozen_string_literal: true
 
 require_relative "gpt-cli/version"
-require_relative "contexts"
 
+require "json"
 require "quick_openai"
 require "optparse"
 
 class ChatGPT
   def contexts
-    file_contents = File.read(File.join(File.dirname(__FILE__), 'contexts.rb'))
-    instance_eval(file_contents)
+    file_contents = File.read(ENV["OPENAI_CONTEXTS_PATH"])
+    contexts = JSON.parse(file_contents)
+    contexts.transform_keys(&:to_sym)
   end
 
   def gpt3(prompt, options)
@@ -44,7 +45,7 @@ module GPTCLI
     options = {}
     chatgpt = ChatGPT.new
     parser = OptionParser.new do |opts|
-      opts.on('-c', '--context CONTEXT_KEY', 'Context key from contexts.rb') do |context_input|
+      opts.on('-c', '--context CONTEXT_KEY', 'Context key from contexts.json') do |context_input|
         options[:context] = chatgpt.contexts.key?(context_input.to_sym) ? chatgpt.contexts[context_input.to_sym] : context_input
       end
       opts.on('-p', '--prompt PROMPT_TEXT', 'Prompt text to be passed to GPT-3') do |prompt_text|

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: gpt-cli
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
 platform: ruby
 authors:
 - John DeSilva
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-03-24 00:00:00.000000000 Z
+date: 2023-03-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: quick_openai
@@ -43,7 +43,7 @@ files:
 - README.md
 - Rakefile
 - exe/gpt-cli
-- lib/contexts.rb
+- gpt_contexts.sample.json
 - lib/gpt-cli.rb
 - lib/gpt-cli/version.rb
 - sig/gpt-cli.rbs
@@ -69,7 +69,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.26
+rubygems_version: 3.3.15
 signing_key:
 specification_version: 4
 summary: A UNIX-ey interface to OpenAI

data/lib/contexts.rb

@@ -1,14 +0,0 @@
-contexts = {
-  :python => %q(Imagine you are a senior software developer specialized in Python, Django, SQL and Machine Learning with 20 years of experience.
-                You are very proficient at writing high quality, clean, concise and highly optimized code that follows the PEP recommendations.
-                You are my personal assistant. You are here to help me in various tasks and answer my questions.),
-
-  :fullstack => %q(Imagine you are an Senior Fullstack Engineer with 20 of experience in UNIX systems, bash, Python, Django, SQL, Javascript, ReactJS, NextJS. 
-                   You are very proficient at writing high quality, clean, concise and well optimized code that follows the PEP recommendations. 
-                   You are my personal assistant. You are here to help me in various tasks and answer my questions.),
-
-  :blockchain => %q(Imagine you are Vitalik Buterin. You created Ethereum and you are the most famous blockchain developer in the world.
-                    You have a very deep knowledge about EVM, Solidity, and the whole blockchain ecosystem.
-                    You know everything about the latest trends in the blockchain space and you are very proficient at writing high quality, clean, concise and well optimized code that follows the good practices.
-                    You are my personal assistant. You are here to help me in various tasks and answer my questions.)
-}