yt-briefing 0.9.1 → 0.9.2
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.
- package/README.md +19 -9
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -55,9 +55,9 @@ YT_BRIEFING_LLM_MODEL=gemini-2.5-flash
|
|
|
55
55
|
YT_BRIEFING_YOUTUBE_API_KEY=<key> # console.cloud.google.com → enable "YouTube Data API v3"
|
|
56
56
|
```
|
|
57
57
|
|
|
58
|
-
Any OpenAI-compatible endpoint works — see [Providers](#providers) to use OpenRouter, OpenAI,
|
|
59
|
-
local Ollama instead of Gemini.
|
|
60
|
-
|
|
58
|
+
Any OpenAI-compatible endpoint works — see [Providers](#providers) to use OpenRouter, OpenAI,
|
|
59
|
+
Anthropic, or a local Ollama instead of Gemini. `YT_BRIEFING_PROXY` (datacenter/VPS IPs) is the
|
|
60
|
+
only optional extra.
|
|
61
61
|
|
|
62
62
|
4. Onboard:
|
|
63
63
|
|
|
@@ -84,23 +84,32 @@ another language? Just say so when you run it (e.g. `/yt-transcribe <url> in Ger
|
|
|
84
84
|
won't change your setup. `--lang pl|en` is separate — it picks which caption track to fetch,
|
|
85
85
|
not the summary language.
|
|
86
86
|
|
|
87
|
-
|
|
87
|
+
For example:
|
|
88
88
|
|
|
89
|
-
```
|
|
90
|
-
|
|
89
|
+
```
|
|
90
|
+
/yt-transcribe https://www.youtube.com/watch?v=dQw4w9WgXcQ
|
|
91
91
|
```
|
|
92
92
|
|
|
93
93
|
## Search within a channel
|
|
94
94
|
|
|
95
95
|
Mine one channel's videos for a topic and get a comparison. Run `/yt-search` with a channel and
|
|
96
|
-
an intent —
|
|
96
|
+
an intent — for example:
|
|
97
|
+
|
|
98
|
+
```
|
|
99
|
+
/yt-search @betterstack which terminal for AI coding
|
|
100
|
+
```
|
|
97
101
|
|
|
98
102
|
It covers the channel's **whole history** (not just recent uploads), re-ranks every upload against
|
|
99
103
|
your intent, then lazily yields one matching video at a time to keep or skip — and synthesizes a
|
|
100
104
|
comparison from everything you kept.
|
|
101
105
|
|
|
102
106
|
The one flag is `--top N` — how many of the top re-ranked matches to triage (**default 10**). Raise
|
|
103
|
-
it to go deeper, lower it for a quicker pass:
|
|
107
|
+
it to go deeper, lower it for a quicker pass:
|
|
108
|
+
|
|
109
|
+
```
|
|
110
|
+
/yt-search @betterstack which terminal
|
|
111
|
+
/yt-search @betterstack which terminal --top 5
|
|
112
|
+
```
|
|
104
113
|
|
|
105
114
|
## Run it
|
|
106
115
|
|
|
@@ -123,7 +132,8 @@ YT_BRIEFING_LLM_MODEL=gemini-2.5-flash
|
|
|
123
132
|
> or switch to a paid key (enable billing, same model) to avoid it.
|
|
124
133
|
|
|
125
134
|
Want something else? Change those three lines for OpenRouter (`https://openrouter.ai/api/v1`),
|
|
126
|
-
OpenAI (`https://api.openai.com/v1`),
|
|
135
|
+
OpenAI (`https://api.openai.com/v1`), Anthropic (`https://api.anthropic.com/v1/`,
|
|
136
|
+
e.g. `claude-sonnet-4-6`), or a local Ollama (`http://localhost:11434/v1`). Set
|
|
127
137
|
`YT_BRIEFING_LLM_BASE_URL`, `_API_KEY`, and `_MODEL` in your root `.env` (see [Setup](#setup)).
|
|
128
138
|
|
|
129
139
|
## Why an API, not the agent's native model
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "yt-briefing",
|
|
3
|
-
"version": "0.9.
|
|
3
|
+
"version": "0.9.2",
|
|
4
4
|
"description": "A self-learning YouTube briefing engine: it sweeps the channels you follow, filters noise in two stages (title, then transcript), summarizes the rest in your language, and adapts to your ratings — one video at a time.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"bin": {
|