Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: support to specify token limits #179

Merged
merged 1 commit into from
Oct 17, 2023
Merged

feat: support to specify token limits #179

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions .env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,10 @@
# # OpenAI API 模型名称，默认值为 `gpt-3.5-turbo`，这是目前可用的最好的模型。
# OPENAI_API_MODEL_NAME=

# # OpenAI token limit, used to calculate text split and truncation before calling Chat Completion API, usually set to the max token limit of the model and let insights-bot decide how to handle, default is `4096`
# # OpenAI Token 限制，用于在调用 Chat Completion API 之前计算文本的分割和截断，一般设置为模型的最大令牌限制，然后交由 insights-bot 决定如何处理，默认为 `4096`
# OPENAI_API_TOKEN_LIMIT=4096

# # PostgreSQL database URL. Such as `postgres://postgres:postgres@localhost:5432/postgres`.
# # You could also suffix with `?search_path=<schema name>` if you want to specify a schema
# # PostgreSQL 数据库 URL。例如 `postgres://postgres:postgres@localhost:5432/postgres`。
Expand Down
30 changes: 24 additions & 6 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,7 +139,7 @@ Arguments: None
```

```txt
[Forward a message]
<Forwarded messages>
```

```txt
Expand Down Expand Up @@ -183,20 +183,37 @@ $ ./insights-bot
docker run -it --rm -e TELEGRAM_BOT_TOKEN=<Telegram Bot API Token> -e OPENAI_API_SECRET=<OpenAI API Secret Key> -e DB_CONNECTION_STR="<PostgresSQL connection URL>" insights-bot ghcr.io/nekomeowww/insights-bot:latest
```

### Run with docker-compose
### Run with Docker Compose

Clone this project:

```shell
git clone github.com/nekomeowww/insights-bot
```

Or only copy or download the necessary `.env.example` and `docker-compose.yml` files (but you will only be able to run the bot with pre-bundled docker image):

```shell
curl -O https://raw.githubusercontent.com/nekomeowww/insights-bot/main/.env.example
curl -O https://raw.githubusercontent.com/nekomeowww/insights-bot/main/docker-compose.yml
```

Create your `.env` by making a copy of the contents from `.env.example` file. The .env file should be placed at the root of the project directory next to your `docker-compose.yml` file.

```shell
cp .env.example .env
```

Replace your OpenAI token and other environment variables in `.env`, and then run:

```shell
docker-compose --profile hub up -d
docker compose --profile hub up -d
```

If you prefer run docker image from local codes, then run:
If you prefer run docker image from local codes (which means build it manually, you will need the entire source code of this project), then run:

```shell
docker-compose --profile local up -d --build
docker compose --profile local up -d --build
```

### Build on your own
Expand Down Expand Up @@ -236,7 +253,8 @@ docker buildx build --platform linux/arm64,linux/amd64 -t <tag> -f Dockerfile .
| `OPENAI_API_SECRET` | `true` | | OpenAI API Secret Key that looks like `sk-************************************************`, you can obtain one by signing in to OpenAI platform and create one at [http://platform.openai.com/account/api-keys](http://platform.openai.com/account/api-keys). |
| `OPENAI_API_HOST` | `false` | `https://api.openai.com` | OpenAI API Host, you can specify one if you have a relay or reversed proxy configured. Such as `https://openai.example.workers.dev` |
| `OPENAI_API_MODEL_NAME` | `false` | `gpt-3.5-turbo` | OpenAI API model name, default is `gpt-3.5-turbo`, you can specify one if you want to use another model. Such as `gpt-4` |
| `DB_CONNECTION_STR` | `true` | | PostgreSQL database URL. Such as `postgres://postgres:postgres@localhost:5432/postgres`. You could also suffix with `?search_path=<schema name>` if you want to specify a schema |
| `OPENAI_API_TOKEN_LIMIT` | `false` | `4096` | OpenAI API token limit used to computed the splits and truncations of texts before calling Chat Completion API generally set to the maximum token limit of a model, and let insights-bot to determine how to process it, default is `4096` |
| `DB_CONNECTION_STR` | `true` | `postgresql://postgres:123456@db_local:5432/postgres?search_path=public&sslmode=disable` | PostgreSQL database URL. Such as `postgres://postgres:postgres@localhost:5432/postgres`. You could also suffix with `?search_path=<schema name>` if you want to specify a schema. |
| `SLACK_CLIENT_ID` | `false` | | Slack app client id, you can create a slack app and get it, see: [tutorial](https://api.slack.com/tutorials/slack-apps-and-postman) |
| `SLACK_CLIENT_SECRET` | `false` | | Slack app client secret, you can create a slack app and get it, see: [tutorial](https://api.slack.com/tutorials/slack-apps-and-postman) |
| `SLACK_WEBHOOK_PORT` | `false` | `7070` | Port for Slack Bot/App Webhook server, default is 7070 |
Expand Down
28 changes: 23 additions & 5 deletions README.zh-CN.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,20 +185,37 @@ $ ./insights-bot
docker run -it --rm -e TELEGRAM_BOT_TOKEN=<Telegram Bot API 令牌> -e OPENAI_API_SECRET=<OpenAI API 密钥y> -e DB_CONNECTION_STR="<PostgresSQL 连接 URL>" insights-bot ghcr.io/nekomeowww/insights-bot:latest
```

### 使用 docker-compose 运行
### 使用 Docker Compose 运行

克隆这个项目：

```shell
git clone github.com/nekomeowww/insights-bot
```

或者只复制或下载必要的`.env.example`和`docker-compose.yml`文件（但只能使用预构建的 Docker 镜像来运行 insights-bot）：

```shell
curl -O https://raw.githubusercontent.com/nekomeowww/insights-bot/main/.env.example
curl -O https://raw.githubusercontent.com/nekomeowww/insights-bot/main/docker-compose.yml
```

通过复制 `.env.example` 文件中的内容来创建 `.env` 文件。`.env` 文件应该放在项目根目录下，与 `docker-compose.yml` 文件同级。

```shell
cp .env.example .env
```

通过替换 `.env` 文件中的 OpenAI 令牌和其他环境变量，然后运行：

```shell
docker-compose --profile hub up -d
docker compose --profile hub up -d
```

如果你想从本地代码编译、构建并运行 Docker 镜像，那么运行：
如果你想从本地代码编译、构建并运行 Docker 镜像（也就是手动构建，你需要这个项目的全部源代码，可以选择先克隆下来），那么运行：

```shell
docker-compose --profile local up -d --build
docker compose --profile local up -d --build
```

### 亲自构建
Expand Down Expand Up @@ -238,7 +255,8 @@ docker buildx build --platform linux/arm64,linux/amd64 -t <tag> -f Dockerfile .
| `OPENAI_API_SECRET` | `true` | | OpenAI API 密钥，通常类似于 `sk-************************************************` 的结构，你可以登录到 Open AI 并在 [http://platform.openai.com/account/api-keys](http://platform.openai.com/account/api-keys) 上创建一个。 |
| `OPENAI_API_HOST` | `false` | `https://api.openai.com` | OpenAI API 的域名，如果配置了中继或反向代理，则可以指定一个。比如 `https://openai.example.workers.dev` |
| `OPENAI_API_MODEL_NAME` | `false` | `gpt-3.5-turbo` | OpenAI API 模型名称，默认为 `gpt-3.5-turbo`，如果你使用其他模型，比如 `gpt-4` 则可以制指定一个。 |
| `DB_CONNECTION_STR` | `true` | | PostgreSQL 数据库连接 URL。结构类似于 `postgres://postgres:postgres@localhost:5432/postgres`。如果你需要指定 schema，则可以通过在后缀加上 `?search_path=<schema name>` 来实现。 |
| `OPENAI_API_TOKEN_LIMIT` | `false` | `4096` | OpenAI API Token 限制，用于在调用 Chat Completion API 之前计算文本的分割和截断，一般设置为模型的最大令牌限制，然后交由 insights-bot 决定如何处理，默认为 `4096`。 |
| `DB_CONNECTION_STR` | `true` | `postgresql://postgres:123456@db_local:5432/postgres?search_path=public&sslmode=disable` | PostgreSQL 数据库连接 URL。结构类似于 `postgres://postgres:postgres@localhost:5432/postgres`。如果你需要指定 schema，则可以通过在后缀加上 `?search_path=<schema name>` 来实现。 |
| `SLACK_CLIENT_ID` | `false` | | Slack app client id，你可以参考[教程](https://api.slack.com/tutorials/slack-apps-and-postman)来创建一个。 |
| `SLACK_CLIENT_SECRET` | `false` | | Slack app client secret，你可以参考[教程](https://api.slack.com/tutorials/slack-apps-and-postman)来创建一个。 |
| `SLACK_WEBHOOK_PORT` | `false` | `7070` | Slack Bot/App Webhook 服务监听端口，默认为 7070。 |
Expand Down
36 changes: 28 additions & 8 deletions docker-compose.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,25 +4,35 @@ services:
# default insights-bot service that would pull the image from docker hub
# and runs on production environment with db_local service and redis_local
# service
#
# you need to use either docker compose up --profile hub -d or docker-compose --profile hub up -d
# to ask docker compose to run this service
insights_bot:
profiles:
- hub
image: ghcr.io/nekomeowww/insights-bot:latest
restart: always
environment:
- TIMEZONE_SHIFT_SECONDS
- TELEGRAM_BOT_TOKEN
- OPENAI_API_SECRET
- OPENAI_API_HOST
- OPENAI_API_MODEL_NAME
- SLACK_CLIENT_ID
- SLACK_CLIENT_SECRET
- DB_CONNECTION_STR=postgresql://postgres:123456@db_local:5432/postgres?search_path=public&sslmode=disable
- OPENAI_API_TOKEN_LIMIT
- DB_CONNECTION_STR
- REDIS_HOST=redis_local
- REDIS_PORT=6379
- REDIS_TLS_ENABLED=false
- REDIS_PASSWORD=123456
- LOG_LEVEL
# # uncomment the following lines if you want to enable discord bot webhook
# # uncomment the following lines if you configured telegram webhook in .env file
# - TELEGRAM_BOT_WEBHOOK_URL
# - TELEGRAM_BOT_WEBHOOK_PORT
# # uncomment the following lines if you configured slack and it's webhook options in .env file
# - SLACK_CLIENT_ID
# - SLACK_CLIENT_SECRET
# - SLACK_WEBHOOK_PORT
# # uncomment the following lines if you configured discord bot webhook in .env file
# - DISCORD_BOT_TOKEN
# - DISCORD_BOT_PUBLIC_KEY
# - DISCORD_BOT_WEBHOOK_PORT
Expand All @@ -45,6 +55,9 @@ services:
# On-demand build insights-bot service that would build the image from
# source code and runs on production environment with db_local service
# and redis_local service
#
# you need to use either docker compose up --profile local -d or docker-compose --profile local up -d
# to ask docker compose to run this service
insights_bot_local:
profiles:
- local
Expand All @@ -54,19 +67,26 @@ services:
image: insights-bot
restart: always
environment:
- TIMEZONE_SHIFT_SECONDS
- TELEGRAM_BOT_TOKEN
- OPENAI_API_SECRET
- OPENAI_API_HOST
- OPENAI_API_MODEL_NAME
- SLACK_CLIENT_ID
- SLACK_CLIENT_SECRET
- DB_CONNECTION_STR=postgresql://postgres:123456@db_local:5432/postgres?search_path=public&sslmode=disable
- OPENAI_API_TOKEN_LIMIT
- DB_CONNECTION_STR
- REDIS_HOST=redis_local
- REDIS_PORT=6379
- REDIS_TLS_ENABLED=false
- REDIS_PASSWORD=123456
- LOG_LEVEL
# # uncomment the following lines if you want to enable discord bot webhook
# # uncomment the following lines if you configured telegram webhook in .env file
# - TELEGRAM_BOT_WEBHOOK_URL
# - TELEGRAM_BOT_WEBHOOK_PORT
# # uncomment the following lines if you configured slack and it's webhook options in .env file
# - SLACK_CLIENT_ID
# - SLACK_CLIENT_SECRET
# - SLACK_WEBHOOK_PORT
# # uncomment the following lines if you configured discord bot webhook in .env file
# - DISCORD_BOT_TOKEN
# - DISCORD_BOT_PUBLIC_KEY
# - DISCORD_BOT_WEBHOOK_PORT
Expand Down
1 change: 0 additions & 1 deletion go.mod
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,6 @@ require (
go.uber.org/multierr v1.11.0
go.uber.org/ratelimit v0.3.0
go.uber.org/zap v1.26.0
gopkg.in/telebot.v3 v3.1.3
)

require (
Expand Down
Loading
Loading