Merge pull request #35 from barakplasma/change-openai-base-url

feat: allow user to change openai base url and model for LocalAI support

README.md

@@ -20,7 +20,7 @@ Matcha is a daily digest generator for your RSS feeds and interested topics/keyw
 ### In Obsidian
 <img width="900" alt="image" src="https://user-images.githubusercontent.com/3144671/219786799-55db70c1-5860-4d4b-9df4-b81a89f8161d.png">
 
-### On the terminal 
+### On the terminal
 
 <img width="596" alt="image" src="https://user-images.githubusercontent.com/3144671/208323296-af2d6a51-7d33-42a9-a827-0e96a4a383fd.png">
 
@@ -31,47 +31,77 @@ Matcha is a daily digest generator for your RSS feeds and interested topics/keyw
  - Quick bookmarking of articles to Instapaper
  - Interested Topics/Keywords to follow (through [Google News](https://news.google.com/))
  - Hacker News comments direct link and distinguishing mostly dicussed posts 🔥
- - Terminal Mode by calling `./matcha -t` 
+ - Terminal Mode by calling `./matcha -t`
+
 
-
 ## Installation / Usage
-1. Since Matcha generates markdown, any markdown reader should do the job. Currently it has been tested on [Obsidian](https://obsidian.md/) so you need a markdown reader before moving on, unless you will use terminal mode (-t option), then a markdown reader is not needed. 
-2. **Download the [corresponding binary](https://github.com/piqoni/matcha/releases)** based on your OS and after executing (if on mac/linux run `chmod +x matcha-darwin-amd64` to make it executable), a sample `config.yml` will be generated, which you can add in your rss feeds, keywords and the `markdown_dir_path` where you want the markdown files to be generated (if left empty, it will generate the daily digest on current dir). 
-3. You can either execute matcha on-demand (a terminal alias) or set a cron to run matcha as often as you want. Even if you set it to execute every hour, matcha will still generate daily digests, one file per day, and will add more articles to it if new articles are published throughout the day. 
+1. Since Matcha generates markdown, any markdown reader should do the job. Currently it has been tested on [Obsidian](https://obsidian.md/) so you need a markdown reader before moving on, unless you will use terminal mode (-t option), then a markdown reader is not needed.
+2. **Download the [corresponding binary](https://github.com/piqoni/matcha/releases)** based on your OS and after executing (if on mac/linux run `chmod +x matcha-darwin-amd64` to make it executable), a sample `config.yml` will be generated, which you can add in your rss feeds, keywords and the `markdown_dir_path` where you want the markdown files to be generated (if left empty, it will generate the daily digest on current dir).
+3. You can either execute matcha on-demand (a terminal alias) or set a cron to run matcha as often as you want. Even if you set it to execute every hour, matcha will still generate daily digests, one file per day, and will add more articles to it if new articles are published throughout the day.
 
 Note to Go developers: You can also install matcha using `go install github.com/piqoni/matcha@latest`
 ## Configuration
-On first execution, Matcha will generate the following config.yaml and a markdown file on the same directory as the application. Change the 'feeds' to your actual RSS feeds, and google_news_keywords to the keywords you are interested in. And if you want to change where the markdown files are generated, set the full directory path in `markdown_dir_path`. 
+On first execution, Matcha will generate the following config.yaml and a markdown file on the same directory as the application. Change the 'feeds' to your actual RSS feeds, and google_news_keywords to the keywords you are interested in. And if you want to change where the markdown files are generated, set the full directory path in `markdown_dir_path`.
 
-```yaml 
-markdown_dir_path: 
+```yaml
+markdown_dir_path:
 feeds:
   - http://hnrss.org/best 10
   - https://waitbutwhy.com/feed
   - http://tonsky.me/blog/atom.xml
   - http://www.joelonsoftware.com/rss.xml
   - https://www.youtube.com/feeds/videos.xml?channel_id=UCHnyfMqiRRG1u-2MsSQLbXA
-google_news_keywords: George Hotz,ChatGPT,Copenhagen 
-instapaper: true 
+google_news_keywords: George Hotz,ChatGPT,Copenhagen
+instapaper: true
 weather_latitude: 37.77
 weather_longitude: 122.41
 terminal_mode: false
-opml_file_path: 
-markdown_file_prefix: 
-markdown_file_suffix: 
+opml_file_path:
+markdown_file_prefix:
+markdown_file_suffix:
 reading_time: false
-openai_api_key: 
-summary_feeds: 
+openai_api_key:
+openai_base_url:
+openai_model:
+summary_feeds:
 ```
-### Summary of Articles using ChatGPT
-To use the summary feature, you need to an OpanAI account ([sign up here](https://openai.com/api/)) then get your API key [here](https://openai.com/api/).
 
-Then update the configuration with the feeds you want to be summarized under "summary_feeds" setting, example:
-```
-openai_api_key: xxxxxxxxxxxxxxxxx
+### Summarization of Articles using ChatGPT
+
+In order to use the summarization feature, you'll first need to set up an OpenAI account. If you haven't already done so, you can sign up [here](https://platform.openai.com/login?launch). Once registered, you'll need to acquire an OpenAI API key which can be found [here](https://platform.openai.com/account/api-keys).
+
+Alternatively, you may use LocalAI (see the "LocalAI Support" section below for more information).
+
+Next, update the configuration file with the desired feeds you want to summarize. This can be done under the "summary_feeds" section. Here is an example configuration:
+
+```yaml
+openai_api_key: sk-xxxxxxxxxxxxxxxxx
 summary_feeds:
-    - http://hnrss.org/best
+    - http://hnrss.org/best 10
 ```
+
+Replace `sk-xxxxxxxxxxxxxxxxx` with your OpenAI API key and include the RSS feeds under `summary_feeds` for articles you're interested in summarizing.
+
+You can also customize which model you use for summarization by changing the openai_model to one of the values [here](https://github.com/sashabaranov/go-openai/blob/a14bc103f4bc2b3ac40c844079fdf59dfdf62b0b/completion.go#L30) which defaults to 'gpt-3.5-turbo' for now. 'gpt-4' is also a valid model name.
+
+```yaml
+openai_model: gpt-3.5-turbo
+```
+
+#### LocalAI Support
+
+For those interested in using LocalAI for summarization, whether for cost-efficiency or privacy reasons, you'll first need to set it up and run it. For setup instructions, please visit the LocalAI repository on GitHub [here](https://github.com/go-skynet/LocalAI).
+
+After setting up LocalAI, you'll need to direct Matcha to the openai-compatible base URL of LocalAI. This is done by updating the "openai_base_url" in the configuration file. For instance, if your LocalAI server is running locally on port 8080, your configuration would look like this:
+
+```yaml
+openai_base_url: http://localhost:8080/v1
+openai_model: openllama-3b
+```
+
+In this case, 'http://localhost:8080/v1' represents the base URL where your LocalAI server is running. 'openai_model' could be any model compatible with LocalAI. You can also replace the openai_base_url with another hosted url like the Azure openai endpoint.
+Please note in case of errors that you may need to change the openai_model to match the model you downloaded in LocalAI.
+
 ### Command line Options
 Run matcha with --help option to see current cli options:
 ```
@@ -80,10 +110,10 @@ Run matcha with --help option to see current cli options:
   -o filepath
     	OPML file path to append feeds from opml files
   -t	Run Matcha in Terminal Mode, no markdown files will be created
-```  
+```
 
 #### OPML Import
-To use OPML files (exported from other services), rename your file to `config.opml` and leave it in the directory where matcha is located. The other option is to run the command with -o option pointing to the opml filepath. 
+To use OPML files (exported from other services), rename your file to `config.opml` and leave it in the directory where matcha is located. The other option is to run the command with -o option pointing to the opml filepath.
 
 <div align="center">
 <a href="https://www.buymeacoffee.com/matchaRSS" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/default-orange.png" alt="Buy Me A Coffee" height="41" width="174"></a>

config.go

@@ -16,24 +16,26 @@ import (
 	"github.com/spf13/viper"
 )
 
-var config string = `markdown_dir_path: 
+var config string = `markdown_dir_path:
 feeds:
   - http://hnrss.org/best 10
   - https://waitbutwhy.com/feed
   - http://tonsky.me/blog/atom.xml
   - http://www.joelonsoftware.com/rss.xml
   - https://www.youtube.com/feeds/videos.xml?channel_id=UCHnyfMqiRRG1u-2MsSQLbXA
-google_news_keywords: George Hotz,ChatGPT,Copenhagen 
-instapaper: true 
+google_news_keywords: George Hotz,ChatGPT,Copenhagen
+instapaper: true
 weather_latitude: 37.77
 weather_longitude: 122.41
 terminal_mode: false
-opml_file_path: 
-markdown_file_prefix: 
+opml_file_path:
+markdown_file_prefix:
 markdown_file_suffix:
-reading_time: false 
-openai_api_key: 
-summary_feeds: 
+reading_time: false
+openai_api_key:
+openai_base_url:
+openai_model:
+summary_feeds:
 show_images: false`
 
 func parseOPML(xmlContent []byte) []RSS {
@@ -124,6 +126,12 @@ func bootstrapConfig() {
 	if viper.IsSet("openai_api_key") {
 		openaiApiKey = viper.Get("openai_api_key").(string)
 	}
+	if viper.IsSet("openai_base_url") {
+		openaiBaseURL = viper.Get("openai_base_url").(string)
+	}
+	if viper.IsSet("openai_model") {
+		openaiModel = viper.Get("openai_model").(string)
+	}
 
 	if viper.IsSet("summary_feeds") {
 		summaryFeeds := viper.Get("summary_feeds")

feeds_writer.go

@@ -24,6 +24,8 @@ var currentDate = time.Now().Format("2006-01-02")
 var lat, lon float64
 var instapaper bool
 var openaiApiKey string
+var openaiBaseURL string
+var openaiModel string
 var reading_time bool
 var show_images bool
 var myFeeds []RSS

go.mod

@@ -4,8 +4,8 @@ go 1.18
 
 require (
 	github.com/mmcdole/gofeed v1.1.3
-	github.com/sashabaranov/go-openai v1.9.0
-	github.com/spf13/viper v1.12.0
+	github.com/sashabaranov/go-openai v1.14.2
+	github.com/spf13/viper v1.16.0
 	modernc.org/sqlite v1.20.0
 )
 
@@ -18,38 +18,38 @@ require (
 require (
 	github.com/PuerkitoBio/goquery v1.5.1 // indirect
 	github.com/andybalholm/cascadia v1.2.0 // indirect
-	github.com/fsnotify/fsnotify v1.5.4 // indirect
+	github.com/fsnotify/fsnotify v1.6.0 // indirect
 	github.com/go-shiori/go-readability v0.0.0-20220215145315-dd6828d2f09b
 	github.com/google/uuid v1.3.0 // indirect
 	github.com/hashicorp/hcl v1.0.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/jwalton/go-supportscolor v1.1.0 // indirect
 	github.com/kballard/go-shellquote v0.0.0-20180428030007-95032a82bc51 // indirect
-	github.com/magiconair/properties v1.8.6 // indirect
+	github.com/magiconair/properties v1.8.7 // indirect
 	github.com/mattn/go-isatty v0.0.16 // indirect
 	github.com/mitchellh/mapstructure v1.5.0 // indirect
 	github.com/mmcdole/goxpp v0.0.0-20181012175147-0068e33feabf // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/pelletier/go-toml v1.9.5 // indirect
-	github.com/pelletier/go-toml/v2 v2.0.1 // indirect
+	github.com/pelletier/go-toml/v2 v2.0.8 // indirect
 	github.com/remyoudompheng/bigfft v0.0.0-20200410134404-eec4a21b6bb0 // indirect
 	github.com/savioxavier/termlink v1.2.1
-	github.com/spf13/afero v1.8.2 // indirect
-	github.com/spf13/cast v1.5.0 // indirect
+	github.com/spf13/afero v1.9.5 // indirect
+	github.com/spf13/cast v1.5.1 // indirect
 	github.com/spf13/jwalterweatherman v1.1.0 // indirect
 	github.com/spf13/pflag v1.0.5 // indirect
-	github.com/subosito/gotenv v1.3.0 // indirect
-	golang.org/x/mod v0.4.1 // indirect
-	golang.org/x/net v0.0.0-20220520000938-2e3eb7b945c2 // indirect
-	golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab // indirect
-	golang.org/x/term v0.0.0-20210927222741-03fcf44c2211 // indirect
-	golang.org/x/text v0.3.7 // indirect
-	golang.org/x/tools v0.1.0 // indirect
-	golang.org/x/xerrors v0.0.0-20220517211312-f3a8303e98df // indirect
-	gopkg.in/ini.v1 v1.66.4 // indirect
+	github.com/subosito/gotenv v1.4.2 // indirect
+	golang.org/x/mod v0.8.0 // indirect
+	golang.org/x/net v0.10.0 // indirect
+	golang.org/x/sys v0.8.0 // indirect
+	golang.org/x/term v0.8.0 // indirect
+	golang.org/x/text v0.9.0 // indirect
+	golang.org/x/tools v0.6.0 // indirect
+	golang.org/x/xerrors v0.0.0-20220907171357-04be3eba64a2 // indirect
+	gopkg.in/ini.v1 v1.67.0 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
-	gopkg.in/yaml.v3 v3.0.0 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
 	lukechampine.com/uint128 v1.2.0 // indirect
 	modernc.org/cc/v3 v3.40.0 // indirect
 	modernc.org/ccgo/v3 v3.16.13 // indirect