prompt_manager 0.1.0 → 0.1.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 2772d50f835a71c26631b2109af906008fec84b62e7ccf435a188fb856415268
4
- data.tar.gz: c1aa3889826246a79df35ad74cd221c1374af161083a34f50d64ef09f5606ade
3
+ metadata.gz: 8b3b9572e08d0f90b7857d9451a13e0ed5d3b089761a1ce820d3b4cf9a47b805
4
+ data.tar.gz: aa374359e5200177d631ce9607bac8559529bdc968a661820110017021414605
5
5
  SHA512:
6
- metadata.gz: c43cc115f2dfa8e847c499386b482d29f3454ca068b0d161d8c14350002d955461962e1009af0a932a92388eef39b134515bca6f694dabd41110150301339b56
7
- data.tar.gz: 55b0e4f827d1950f39ad87909954660cb5ae0f6da44a4de0b43aad637dc1d99d878d2cb1876ac4a001cd42c190e1160a76593c6f4cba3b8411c250bd42e97e35
6
+ metadata.gz: 992bc7f9e337d3fadbc99d0d192a325640bc113f244dd0bf448273398717e9e0d60d0e2a2ee02d18f617e3c9687efaee8fc36c6594f0a3819ca9e877140d6164
7
+ data.tar.gz: a7d7891c715aa4beea562a82135e2f945d36d4e2132eb39efaf71a8795572dc804ef55bd253a34734a4d84bfb1e516fd6f973dc0c62da0b63fb4ad59cd18f5c2
data/README.md CHANGED
@@ -14,31 +14,31 @@ If bundler is not being used to manage dependencies, install the gem by executin
14
14
 
15
15
  ## Usage
16
16
 
17
- See [examples/simple.rb](examples.simple.rb)
17
+ See [examples/simple.rb](examples/simple.rb)
18
18
 
19
19
  ## Overview
20
20
 
21
21
  ### Generative AI (gen-AI)
22
22
 
23
- Gen-AI deals with the conversion (some would say execution) of a human natural language text (the "prompt") into somthing else using what are known as large language models (LLM) such as those available from OpenAI. A parameterized prompt is one in whcih there are embedded keywords (parameters) which are place holders for other text to be inserted into the prompt.
23
+ Gen-AI deals with the conversion (some would say execution) of a human natural language text (the "prompt") into somthing else using what are known as large language models (LLM) such as those available from OpenAI. A parameterized prompt is one in which there are embedded keywords (parameters) which are place holders for other text to be inserted into the prompt.
24
24
 
25
- The prompt_manager uses a regurlar expression to identify these keywords within the prompt. It uses the keywords as keys in a `parameters` Hash which is stored with the prompt text in a serialized form - for example as JSON.
25
+ The prompt_manager uses a regular expression to identify these keywords within the prompt. It uses the keywords as keys in a `parameters` Hash which is stored with the prompt text in a serialized form - for example as JSON.
26
26
 
27
27
  #### What does a keyword look like?
28
28
 
29
- The current hard-coded REGEX for a [KEYWORD] identifies any all [UPPERCASE_TEXT] enclosed in squal brackes as a keyword. [KEY WORDS CAN ALSO HAVE SPACES] as well as the underscore character.
29
+ The current hard-coded REGEX for a [KEYWORD] identifies any all [UPPERCASE_TEXT] enclosed in square brackets as a keyword. [KEYWORDS CAN ALSO HAVE SPACES] as well as the underscore character.
30
30
 
31
- This is just the initial convention adopted by prompt_manager. It is intended that this REGEX be configurable so that the promp_manager can be used with other conventions.
31
+ This is just the initial convention adopted by prompt_manager. It is intended that this REGEX be configurable so that the prompt_manager can be used with other conventions.
32
32
 
33
33
  ### Storage Adapters
34
34
 
35
- A storage adapter is a class instance that ties the `PromptManager::Prompt` class to a storage facility that holds the actual prompts. Currentlyt there are 3 storage adapters planned for implementation.
35
+ A storage adapter is a class instance that ties the `PromptManager::Prompt` class to a storage facility that holds the actual prompts. Currently there are 3 storage adapters planned for implementation.
36
36
 
37
37
  #### FileSystemAdapter
38
38
 
39
- This is the first storage adapter developed. It saves prompts as text files within the file system inside a designated `prompts_dir` (directory) such as `~/,prompts` or where it makes the most sense to you. Another example would be to have your directory on a shared file system so that others can use the same prompts.
39
+ This is the first storage adapter developed. It saves prompts as text files within the file system inside a designated `prompts_dir` (directory) such as `~/.prompts` or where it makes the most sense to you. Another example would be to have your directory on a shared file system so that others can use the same prompts.
40
40
 
41
- The `promp ID` is the basename of the text file. For example `todo.txt` is the file for the prompt ID `todo` (see the examples directory.)
41
+ The `prompt ID` is the basename of the text file. For example `todo.txt` is the file for the prompt ID `todo` (see the examples directory.)
42
42
 
43
43
  The parameters for the `todo` prompt ID are saved in the same directory as `todo.txt` in a JSON file named `todo.json` (also in the examples directory.)
44
44
 
@@ -1,5 +1,5 @@
1
1
  # frozen_string_literal: true
2
2
 
3
3
  module PromptManager
4
- VERSION = "0.1.0"
4
+ VERSION = "0.1.1"
5
5
  end
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: prompt_manager
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.1.0
4
+ version: 0.1.1
5
5
  platform: ruby
6
6
  authors:
7
7
  - Dewayne VanHoozer
@@ -53,7 +53,7 @@ dependencies:
53
53
  - !ruby/object:Gem::Version
54
54
  version: '0'
55
55
  description: "Manage the parameterized prompts (text) used in generative AI (aka chatGPT,
56
- \npen AI, et.al.) using storage adapters such as FileSystemAdapter, \nSqliteAdapter
56
+ \nOpenAI, et.al.) using storage adapters such as FileSystemAdapter, \nSqliteAdapter
57
57
  and ActiveRecordAdapter.\n"
58
58
  email:
59
59
  - dvanhoozer@gmail.com