stdin and disable spinner

CHANGELOG.md

@@ -2,7 +2,11 @@
 
 ## Unreleased
 
+## 2023-04-16 0.1.7
+
 - Disable spinners with env `DISABLE_SPINNER`
+- Disable spinners with flag `x`
+- `prompt` also accepts text from stdin
 
 ## 2023-04-05 0.1.6
 

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "gpto"
-version = "0.1.6"
+version = "0.1.7"
 authors = ["Alan Vardy <[email protected]>"]
 edition = "2021"
 license = "MIT"

PUBLISH_CHECKLIST.md

@@ -14,57 +14,31 @@ This checklist is just here for me to reduce the friction of publishing new vers
 
 Code changes
 
-1. Update dependencies and make sure nothing broke
+1. Update dependencies and make sure nothing broke with `./update_test.sh`
+2. Change the version in `Cargo.toml` and in this document (do a global find and replace)
+3. Update CHANGELOG.md with the version number
+4. Update README.md with help text `cargo run -- -h`
+5. Add any new examples to README.md
+6. Open PR for the version and wait for it to pass
+7. Commit and merge PR
 
-```bash
-cargo update && \
-./test.sh && \
-./manual_test.sh
-```
-
-2. Revert the change to the test `gpto.cfg`
-3. Change the version in `Cargo.toml` and in this document (do a global find and replace)
-4. Update CHANGELOG.md with the version number
-5. Update README.md with help text `cargo run -- -h`
-6. Add any new examples to README.md
-7. Open PR for the version and wait for it to pass
-8. Commit and merge PR
-
-9. Build release
+8. Build release
 
 ```bash
 git checkout main
 git pull
 cargo aur
 ```
 
-10. [Create a new release](https://github.com/alanvardy/gpto/releases/new)
+9. [Create a new release](https://github.com/alanvardy/gpto/releases/new)
 
 - Make sure to use the label and title in format `v0.1.6`
 - Add binary from gpto directory
 
-11. Publish to Cargo
+10. Publish to Cargo
 
 ```bash
 cargo publish
 ```
 
-12. Make sure we have the latest AUR git history
-
-```bash
-cd ../gpto-bin/
-git pull
-cd ../gpto/
-```
-
-13. Push to AUR
-
-```bash
-makepkg --printsrcinfo > ../gpto-bin/.SRCINFO
-mv PKGBUILD ../gpto-bin/
-rm *.tar.gz
-cd ../gpto-bin/
-git add .
-git commit -m v0.1.6
-git push aur
-```
+11. Push to aur with `./push_aur`

README.md

@@ -12,31 +12,22 @@ A tiny unofficial OpenAI client
 Usage: gpto [OPTIONS]
 
 Options:
-  -p, --prompt <Prompt text>...
-          The prompt(s) to generate completions for
+  -p, --prompt [<Prompt text>...]
+          The prompt(s) to generate completions for. Also accepts text from stdin
+  -x, --disable spinner
+          Disable the spinner and message when querying
   -c, --conversation [<Instructions to bot>...]
           Start a conversation with an optional description of the bot's role
   -s, --suffix <Text to be appended to end of response>...
           The suffix that comes after a completion of inserted text. Defaults to an empty string
   -t, --temperature <float>
-          What sampling temperature to use. 
-               Higher values means the model will take more risks. 
-               Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer. 
-               Defaults to 1.0
+          What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling)    for ones with a well-defined answer. Defaults to 1.0
   -n, --number <integer>
           How many completions to generate for each prompt. Defaults to 1
   -k, --top_p <float>
-          An alternative to sampling with temperature, called nucleus sampling,
-               where the model considers the results of the tokens with top_p probability mass.
-               So 0.1 means only the tokens comprising the top 10% probability mass are considered.
-               We generally recommend altering this or temperature but not both.
-               Defaults to 1.0
+          An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. Defaults to 1.0
   -m, --model <model name>
-          
-              Model to use for completion. Defaults to gpt-3.5-turbo.
-              This CLI uses the /v1/chat/completions endpoint,
-              see https://platform.openai.com/docs/models/gpt-3 for models available
-              
+          Model to use for completion. Defaults to gpt-3.5-turbo. This CLI uses the /v1/chat/completions endpoint, see https://platform.openai.com/docs/models/gpt-3 for models available
   -o, --config <path to config file>
           Absolute path of configuration. Defaults to $XDG_CONFIG_HOME/gpto.cfg
   -h, --help
@@ -95,6 +86,14 @@ Q: What did the fish say when it hit the wall?
 A: Dam!
 ```
 
+Get completions using text from stdin (without displaying the spinner)
+
+```bash
+> echo "what is one plus one" | gpto -xp
+
+Two
+```
+
 Get a completion with a different model (this example uses the leading code completion model). And yes, the generated code is not idiomatic!
 
 Read more about models [here](https://platform.openai.com/docs/models/gpt-3). This CLI app uses the `/v1/chat/completions` endpoint.

manual_test.sh

@@ -8,6 +8,8 @@ echo "== TESTING -p tell a great joke -t 0 ==" && \
 cargo run -- -p tell a great joke -t 0 && \
 echo "== TESTING -m gpt-3.5-turbo-0301 ==" && \
 cargo run -- -m gpt-3.5-turbo-0301 -p language is elixir create a function that adds two numbers && \
+echo "== TESTING -p with stdin ==" && \
+echo "what is one plus one" | cargo run -- -xp && \
 echo "== TESTING -c ==" && \
 cargo run -- -c && \
 echo "== TESTING -c Roleplay as Shakespeare ==" && \

push_aur.sh

@@ -0,0 +1,12 @@
+#!/bin/sh
+cd ../gpto-bin/
+git pull
+cd ../gpto/
+makepkg --printsrcinfo > ../gpto-bin/.SRCINFO
+mv PKGBUILD ../gpto-bin/
+rm *.tar.gz
+cd ../gpto-bin/
+git add .
+git commit -m "new version"
+git push aur
+cd ../gpto