Compare commits
18 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
cb29419d75 | ||
|
|
51ca8c9948 | ||
|
|
12b938d2d1 | ||
|
|
f3d1b32ad7 | ||
|
|
3d3bd3c9f9 | ||
|
|
a25845e89e | ||
|
|
479f54b93d | ||
|
|
90ab6807ac | ||
|
|
5022f79bf5 | ||
|
|
2ba3b5a437 | ||
|
|
2819011b9d | ||
|
|
ede9065f77 | ||
|
|
5e61f5b3a3 | ||
|
|
8633e82f62 | ||
|
|
6aa3d70d57 | ||
|
|
75e29ee3fb | ||
|
|
eab7978b9f | ||
|
|
765e7c17b2 |
@@ -1,3 +1,11 @@
|
||||
# (2026-03-20) Version 1.16.0
|
||||
|
||||
- (**Feature**) Add support for file attachments (`m.file` Matrix messages) in conversations. Files like PDFs, text documents, spreadsheets, code files, etc. are now downloaded and forwarded to the LLM alongside the conversation context, similar to how images (`m.image`) are already handled. See the [💬 Text Generation](./docs/features.md#-text-generation) documentation for details and known limitations.
|
||||
|
||||
- (**Improvement**) Use the [mime_guess](https://crates.io/crates/mime_guess) crate for MIME type detection from file extensions, replacing a hand-maintained mapping. This covers hundreds of file extensions out of the box.
|
||||
|
||||
|
||||
|
||||
# (2026-03-07) Version 1.15.0
|
||||
|
||||
- (**Feature**) Add support for authentication via access tokens (for [Matrix Authentication Service](https://github.com/element-hq/matrix-authentication-service)/OIDC-enabled homeservers) as an alternative to password authentication. See [🔐 Authentication](./docs/configuration/authentication.md) for setup details. Thanks to [Taylor Southwick](https://github.com/twsouthwick) for the contribution in [#83](https://github.com/etkecc/baibot/pull/83)!
|
||||
|
||||
88
Cargo.lock
generated
88
Cargo.lock
generated
@@ -178,9 +178,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "async-openai"
|
||||
version = "0.33.0"
|
||||
version = "0.33.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b3ef6d66e53b3ec8ed4bae8e6dcdda75c0f5b4f67faba78fac1b09434cb4f2fc"
|
||||
checksum = "cc48c3deb4ad9a2ee8c8e364c79eb0f74e69e17ed7e883d55988b90ea44fe986"
|
||||
dependencies = [
|
||||
"async-openai-macros",
|
||||
"backoff",
|
||||
@@ -288,7 +288,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "baibot"
|
||||
version = "1.15.0"
|
||||
version = "1.16.0"
|
||||
dependencies = [
|
||||
"anthropic",
|
||||
"anyhow",
|
||||
@@ -460,9 +460,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "cc"
|
||||
version = "1.2.56"
|
||||
version = "1.2.57"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "aebf35691d1bfb0ac386a69bac2fde4dd276fb618cf8bf4f5318fe285e821bb2"
|
||||
checksum = "7a0dd1ca384932ff3641c8718a02769f1698e7563dc6974ffd03346116310423"
|
||||
dependencies = [
|
||||
"find-msvc-tools",
|
||||
"shlex",
|
||||
@@ -1998,9 +1998,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "itoa"
|
||||
version = "1.0.17"
|
||||
version = "1.0.18"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "92ecc6618181def0457392ccd0ee51198e065e016d1d527a7ac1b6dc7c1f09d2"
|
||||
checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
|
||||
|
||||
[[package]]
|
||||
name = "js-sys"
|
||||
@@ -2070,9 +2070,9 @@ checksum = "09edd9e8b54e49e587e4f6295a7d29c3ea94d469cb40ab8ca70b288248a81db2"
|
||||
|
||||
[[package]]
|
||||
name = "libc"
|
||||
version = "0.2.182"
|
||||
version = "0.2.183"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6800badb6cb2082ffd7b6a67e6125bb39f18782f793520caee8cb8846be06112"
|
||||
checksum = "b5b646652bf6661599e1da8901b3b9522896f01e736bad5f723fe7a3a27f899d"
|
||||
|
||||
[[package]]
|
||||
name = "libsqlite3-sys"
|
||||
@@ -2673,9 +2673,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "once_cell"
|
||||
version = "1.21.3"
|
||||
version = "1.21.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
|
||||
checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
|
||||
|
||||
[[package]]
|
||||
name = "opaque-debug"
|
||||
@@ -2685,9 +2685,9 @@ checksum = "c08d65885ee38876c4f86fa503fb49d7b507c2b62552df7c70b2fce627e06381"
|
||||
|
||||
[[package]]
|
||||
name = "openssl"
|
||||
version = "0.10.75"
|
||||
version = "0.10.76"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "08838db121398ad17ab8531ce9de97b244589089e290a384c900cb9ff7434328"
|
||||
checksum = "951c002c75e16ea2c65b8c7e4d3d51d5530d8dfa7d060b4776828c88cfb18ecf"
|
||||
dependencies = [
|
||||
"bitflags 2.11.0",
|
||||
"cfg-if",
|
||||
@@ -2723,9 +2723,9 @@ checksum = "7c87def4c32ab89d880effc9e097653c8da5d6ef28e6b539d313baaacfbafcbe"
|
||||
|
||||
[[package]]
|
||||
name = "openssl-sys"
|
||||
version = "0.9.111"
|
||||
version = "0.9.112"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "82cab2d520aa75e3c58898289429321eb788c3106963d0dc886ec7a5f4adc321"
|
||||
checksum = "57d55af3b3e226502be1526dfdba67ab0e9c96fc293004e79576b2b9edb0dbdb"
|
||||
dependencies = [
|
||||
"cc",
|
||||
"libc",
|
||||
@@ -2983,9 +2983,9 @@ checksum = "007d8adb5ddab6f8e3f491ac63566a7d5002cc7ed73901f72057943fa71ae1ae"
|
||||
|
||||
[[package]]
|
||||
name = "quick_cache"
|
||||
version = "0.6.18"
|
||||
version = "0.6.21"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7ada44a88ef953a3294f6eb55d2007ba44646015e18613d2f213016379203ef3"
|
||||
checksum = "5a70b1b8b47e31d0498ecbc3c5470bb931399a8bfed1fd79d1717a61ce7f96e3"
|
||||
dependencies = [
|
||||
"ahash",
|
||||
"equivalent",
|
||||
@@ -3015,9 +3015,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "quinn-proto"
|
||||
version = "0.11.13"
|
||||
version = "0.11.14"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f1906b49b0c3bc04b5fe5d86a77925ae6524a19b816ae38ce1e426255f1d8a31"
|
||||
checksum = "434b42fec591c96ef50e21e886936e66d3cc3f737104fdb9b737c40ffb94c098"
|
||||
dependencies = [
|
||||
"bytes",
|
||||
"getrandom 0.3.4",
|
||||
@@ -3701,9 +3701,9 @@ checksum = "9774ba4a74de5f7b1c1451ed6cd5285a32eddb5cccb8cc655a4e50009e06477f"
|
||||
|
||||
[[package]]
|
||||
name = "schannel"
|
||||
version = "0.1.28"
|
||||
version = "0.1.29"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "891d81b926048e76efe18581bf793546b4c0eaf8448d72be8de2bbee5fd166e1"
|
||||
checksum = "91c1b7e4904c873ef0710c1f407dde2e6287de2bebc1bbbf7d430bb7cbffd939"
|
||||
dependencies = [
|
||||
"windows-sys 0.61.2",
|
||||
]
|
||||
@@ -4132,9 +4132,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "tempfile"
|
||||
version = "3.26.0"
|
||||
version = "3.27.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "82a72c767771b47409d2345987fda8628641887d5466101319899796367354a0"
|
||||
checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
|
||||
dependencies = [
|
||||
"fastrand",
|
||||
"getrandom 0.4.2",
|
||||
@@ -4261,9 +4261,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "tinyvec"
|
||||
version = "1.10.0"
|
||||
version = "1.11.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "bfa5fdc3bce6191a1dbc8c02d5c8bffcf557bafa17c124c5264a458f1b0613fa"
|
||||
checksum = "3e61e67053d25a4e82c844e8424039d9745781b3fc4f32b8d55ed50f5f667ef3"
|
||||
dependencies = [
|
||||
"tinyvec_macros",
|
||||
]
|
||||
@@ -4365,7 +4365,7 @@ dependencies = [
|
||||
"serde_spanned",
|
||||
"toml_datetime 0.7.5+spec-1.1.0",
|
||||
"toml_parser",
|
||||
"winnow",
|
||||
"winnow 0.7.15",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -4379,32 +4379,32 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "toml_datetime"
|
||||
version = "1.0.0+spec-1.1.0"
|
||||
version = "1.0.1+spec-1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "32c2555c699578a4f59f0cc68e5116c8d7cabbd45e1409b989d4be085b53f13e"
|
||||
checksum = "9b320e741db58cac564e26c607d3cc1fdc4a88fd36c879568c07856ed83ff3e9"
|
||||
dependencies = [
|
||||
"serde_core",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "toml_edit"
|
||||
version = "0.25.4+spec-1.1.0"
|
||||
version = "0.25.5+spec-1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7193cbd0ce53dc966037f54351dbbcf0d5a642c7f0038c382ef9e677ce8c13f2"
|
||||
checksum = "8ca1a40644a28bce036923f6a431df0b34236949d111cc07cb6dca830c9ef2e1"
|
||||
dependencies = [
|
||||
"indexmap",
|
||||
"toml_datetime 1.0.0+spec-1.1.0",
|
||||
"toml_datetime 1.0.1+spec-1.1.0",
|
||||
"toml_parser",
|
||||
"winnow",
|
||||
"winnow 1.0.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "toml_parser"
|
||||
version = "1.0.9+spec-1.1.0"
|
||||
version = "1.0.10+spec-1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "702d4415e08923e7e1ef96cd5727c0dfed80b4d2fa25db9647fe5eb6f7c5a4c4"
|
||||
checksum = "7df25b4befd31c4816df190124375d5a20c6b6921e2cad937316de3fccd63420"
|
||||
dependencies = [
|
||||
"winnow",
|
||||
"winnow 1.0.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -4502,9 +4502,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "tracing-subscriber"
|
||||
version = "0.3.22"
|
||||
version = "0.3.23"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "2f30143827ddab0d256fd843b7a66d164e9f271cfa0dde49142c5ca0ca291f1e"
|
||||
checksum = "cb7f578e5945fb242538965c2d0b04418d38ec25c79d160cd279bf0731c8d319"
|
||||
dependencies = [
|
||||
"matchers",
|
||||
"nu-ansi-term",
|
||||
@@ -5213,6 +5213,12 @@ name = "winnow"
|
||||
version = "0.7.15"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "df79d97927682d2fd8adb29682d1140b343be4ac0f08fd68b7765d9c059d3945"
|
||||
|
||||
[[package]]
|
||||
name = "winnow"
|
||||
version = "1.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a90e88e4667264a994d34e6d1ab2d26d398dcdca8b7f52bec8668957517fc7d8"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
]
|
||||
@@ -5364,18 +5370,18 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "zerocopy"
|
||||
version = "0.8.40"
|
||||
version = "0.8.47"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a789c6e490b576db9f7e6b6d661bcc9799f7c0ac8352f56ea20193b2681532e5"
|
||||
checksum = "efbb2a062be311f2ba113ce66f697a4dc589f85e78a4aea276200804cea0ed87"
|
||||
dependencies = [
|
||||
"zerocopy-derive",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zerocopy-derive"
|
||||
version = "0.8.40"
|
||||
version = "0.8.47"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f65c489a7071a749c849713807783f70672b28094011623e200cb86dcb835953"
|
||||
checksum = "0e8bc7269b54418e7aeeef514aa68f8690b8c0489a06b0136e5f57c4c5ccab89"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
|
||||
@@ -7,7 +7,7 @@ license = "AGPL-3.0-or-later"
|
||||
readme = "README.md"
|
||||
keywords = ["matrix", "chat", "bot", "AI", "LLM"]
|
||||
include = ["/etc/assets/baibot-torso-768.png", "/src", "/README.md", "/CHANGELOG.md", "/LICENSE"]
|
||||
version = "1.15.0"
|
||||
version = "1.16.0"
|
||||
edition = "2024"
|
||||
|
||||
[lib]
|
||||
@@ -32,7 +32,7 @@ regex = "1.12.*"
|
||||
serde = { version = "1.0.*", features = ["derive"], default-features = false }
|
||||
serde_json = "1.0.*"
|
||||
serde_yaml_ng = "0.10.*"
|
||||
tempfile = "3.26.*"
|
||||
tempfile = "3.27.*"
|
||||
tiktoken-rs = { version = "0.9.*", default-features = false }
|
||||
tokio = { version = "1.50.*", features = ["rt", "rt-multi-thread", "macros"] }
|
||||
tracing = "0.1.*"
|
||||
|
||||
@@ -8,7 +8,7 @@ You can also use **different models within the same room** (e.g. [💬 text-gene
|
||||
|
||||
The bot supports the following use-purposes:
|
||||
|
||||
- [💬 text-generation](../features.md#-text-generation): communicating with you via text (though certain models may "see" images as well)
|
||||
- [💬 text-generation](../features.md#-text-generation): communicating with you via text (though certain models may also process images and files)
|
||||
- [🦻 speech-to-text](../features.md#-speech-to-text): turning your voice messages into text
|
||||
- [🗣️ text-to-speech](../features.md#️-text-to-speech): turning bot or users text messages into voice messages
|
||||
- [🖌️ image-generation](../features.md#image-generation): generating images based on instructions
|
||||
|
||||
@@ -8,7 +8,7 @@ You can also use **different models within the same room** (e.g. [💬 text-gene
|
||||
|
||||
The bot supports the following use-purposes:
|
||||
|
||||
- [💬 text-generation](#-text-generation): communicating with you via text (though certain models may "see" images as well)
|
||||
- [💬 text-generation](#-text-generation): communicating with you via text (though certain models may also process images and files)
|
||||
- [🦻 speech-to-text](#-speech-to-text): turning your voice messages into text
|
||||
- [🗣️ text-to-speech](#%EF%B8%8F-text-to-speech): turning bot or users text messages into voice messages
|
||||
- [🖌️ image-generation](#%EF%B8%8F-image-generation): generating images based on instructions
|
||||
@@ -26,7 +26,7 @@ Text Generation is the bot's ability to **respond to users' messages with text**
|
||||
|
||||

|
||||
|
||||
Some models also support vision, so you may be able to mix text and images in the same conversation.
|
||||
Some models also support vision and document understanding, so you may be able to mix text, images, and files (PDFs, text documents, etc.) in the same conversation. Note that certain providers may not support all file types or may have issues with specific files (e.g. scanned/image-based PDFs). If a file is rejected by the provider, the conversation thread may become unusable — start a new thread to work around this.
|
||||
|
||||
In multi-user (group) rooms, to avoid disturbing the normal conversation between people, the bot is auto-configured to only respond to messages starting with the command prefix (`!bai`) or direct mentions via the [💬 Text Generation / 🗟 Prefix Requirement Type](./configuration/text-generation.md#-prefix-requirement-type) setting.
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
base_url: https://api.openai.com/v1
|
||||
api_key: YOUR_API_KEY_HERE
|
||||
text_generation:
|
||||
model_id: gpt-5.2
|
||||
model_id: gpt-5.4
|
||||
prompt: "You are a brief, but helpful bot called {{ baibot_name }} powered by the {{ baibot_model_id }} model. The date/time of this conversation's start is: {{ baibot_conversation_start_time_utc }}."
|
||||
temperature: 1.0
|
||||
# Reasoning models need to use `max_completion_tokens` instead of `max_response_tokens`.
|
||||
|
||||
@@ -11,7 +11,7 @@ This is related to the [💬 Text Generation](./features.md#-text-generation) fe
|
||||
|
||||
If there's a text-generation handler agent configured, the bot **may** respond to messages sent in the room.
|
||||
|
||||
Some models also support vision, so you may be able to mix text and images in the same conversation.
|
||||
Some models also support vision and document understanding, so you may be able to mix text, images, and files (PDFs, text documents, etc.) in the same conversation.
|
||||
|
||||
See screenshots of:
|
||||
|
||||
|
||||
@@ -91,7 +91,7 @@ agents:
|
||||
# base_url: https://api.openai.com/v1
|
||||
# api_key: ""
|
||||
# text_generation:
|
||||
# model_id: gpt-5.2
|
||||
# model_id: gpt-5.4
|
||||
# prompt: "You are a brief, but helpful bot called {{ baibot_name }} powered by the {{ baibot_model_id }} model. The date/time of this conversation's start is: {{ baibot_conversation_start_time_utc }}."
|
||||
# temperature: 1.0
|
||||
# # Reasoning models need to use `max_completion_tokens` instead of `max_response_tokens`.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
services:
|
||||
element-web:
|
||||
image: ghcr.io/element-hq/element-web:v1.12.11
|
||||
image: ghcr.io/element-hq/element-web:v1.12.12
|
||||
user: "${UID}:${GID}"
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
services:
|
||||
ollama:
|
||||
image: docker.io/ollama/ollama:0.17.7
|
||||
image: docker.io/ollama/ollama:0.18.2
|
||||
restart: unless-stopped
|
||||
ports:
|
||||
- "${SERVICE_OLLAMA_BIND_PORT_HTTP}:11434"
|
||||
|
||||
@@ -14,7 +14,7 @@ services:
|
||||
- /etc/passwd:/etc/passwd:ro
|
||||
|
||||
synapse:
|
||||
image: ghcr.io/element-hq/synapse:v1.148.0
|
||||
image: ghcr.io/element-hq/synapse:v1.149.1
|
||||
user: "${UID}:${GID}"
|
||||
restart: unless-stopped
|
||||
entrypoint: python
|
||||
|
||||
@@ -28,6 +28,13 @@ pub(super) fn create_anthropic_message_request(llm_messages: Vec<LLMMessage>) ->
|
||||
},
|
||||
}]
|
||||
}
|
||||
LLMMessageContent::File(file_details) => {
|
||||
tracing::warn!(
|
||||
"The Anthropic provider's library does not support file/document content. This file message ({}) will be skipped.",
|
||||
file_details.filename(),
|
||||
);
|
||||
continue;
|
||||
}
|
||||
};
|
||||
|
||||
let message = Message { role, content };
|
||||
|
||||
@@ -84,7 +84,7 @@ impl Default for TextGenerationConfig {
|
||||
}
|
||||
|
||||
fn default_text_model_id() -> String {
|
||||
"gpt-5.2".to_owned()
|
||||
"gpt-5.4".to_owned()
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
use async_openai::types::responses::{
|
||||
EasyInputContent, EasyInputMessage, ImageDetail, InputContent, InputImageContent, InputItem,
|
||||
InputParam, MessageType, Role,
|
||||
EasyInputContent, EasyInputMessage, ImageDetail, InputContent, InputFileArgs,
|
||||
InputImageContent, InputItem, InputParam, MessageType, Role,
|
||||
};
|
||||
|
||||
use crate::conversation::llm::{
|
||||
@@ -35,6 +35,21 @@ pub fn convert_llm_messages_to_openai_response_input(
|
||||
file_id: None,
|
||||
})])
|
||||
}
|
||||
LLMMessageContent::File(file_details) => {
|
||||
let file_data = format!(
|
||||
"data:{};base64,{}",
|
||||
file_details.mime,
|
||||
base64_encode(&file_details.data)
|
||||
);
|
||||
|
||||
let file_content = InputFileArgs::default()
|
||||
.file_data(file_data)
|
||||
.filename(file_details.filename())
|
||||
.build()
|
||||
.expect("Failed to build InputFileContent");
|
||||
|
||||
EasyInputContent::ContentList(vec![InputContent::InputFile(file_content)])
|
||||
}
|
||||
};
|
||||
|
||||
items.push(InputItem::EasyMessage(EasyInputMessage {
|
||||
|
||||
@@ -40,6 +40,12 @@ fn convert_llm_message_to_openai_message(llm_message: LLMMessage) -> Option<Mess
|
||||
);
|
||||
None
|
||||
}
|
||||
LLMMessageContent::File(_file_details) => {
|
||||
tracing::warn!(
|
||||
"The OpenAI-compat provider's library does not support file content. This file message will be skipped."
|
||||
);
|
||||
None
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -41,6 +41,8 @@ pub enum ChatCompletionControllerType {
|
||||
|
||||
Image,
|
||||
|
||||
File,
|
||||
|
||||
ThreadMention,
|
||||
ReplyMention,
|
||||
}
|
||||
@@ -419,7 +421,8 @@ async fn handle_stage_text_generation(
|
||||
| ChatCompletionControllerType::TextMention
|
||||
| ChatCompletionControllerType::TextDirect
|
||||
| ChatCompletionControllerType::Audio
|
||||
| ChatCompletionControllerType::Image => {
|
||||
| ChatCompletionControllerType::Image
|
||||
| ChatCompletionControllerType::File => {
|
||||
Some(message_context.combined_admin_and_user_regexes())
|
||||
}
|
||||
|
||||
|
||||
@@ -58,6 +58,18 @@ pub fn determine_controller(
|
||||
)
|
||||
}
|
||||
}
|
||||
MessagePayload::File(_file_message_content) => {
|
||||
let prefix_requirement_type = message_context
|
||||
.room_config_context()
|
||||
.text_generation_prefix_requirement_type();
|
||||
|
||||
match prefix_requirement_type {
|
||||
TextGenerationPrefixRequirementType::CommandPrefix => ControllerType::Ignore,
|
||||
TextGenerationPrefixRequirementType::No => {
|
||||
ControllerType::ChatCompletion(ChatCompletionControllerType::File)
|
||||
}
|
||||
}
|
||||
}
|
||||
MessagePayload::Audio(_) => {
|
||||
ControllerType::ChatCompletion(ChatCompletionControllerType::Audio)
|
||||
}
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
use chrono::{DateTime, Utc};
|
||||
use mxlink::matrix_sdk::ruma::events::room::message::ImageMessageEventContent;
|
||||
use mxlink::matrix_sdk::ruma::events::room::message::{
|
||||
FileMessageEventContent, ImageMessageEventContent,
|
||||
};
|
||||
use mxlink::mime::Mime;
|
||||
|
||||
use crate::agent::provider::ImageSource;
|
||||
@@ -48,10 +50,35 @@ impl From<ImageDetails> for ImageSource {
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct FileDetails {
|
||||
pub event_content: FileMessageEventContent,
|
||||
pub mime: Mime,
|
||||
pub data: Vec<u8>,
|
||||
}
|
||||
|
||||
impl FileDetails {
|
||||
pub fn new(event_content: FileMessageEventContent, mime: Mime, data: Vec<u8>) -> Self {
|
||||
Self {
|
||||
event_content,
|
||||
mime,
|
||||
data,
|
||||
}
|
||||
}
|
||||
|
||||
pub fn filename(&self) -> String {
|
||||
self.event_content
|
||||
.filename
|
||||
.clone()
|
||||
.unwrap_or(self.event_content.body.clone())
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub enum MessageContent {
|
||||
Text(String),
|
||||
Image(ImageDetails),
|
||||
File(FileDetails),
|
||||
}
|
||||
|
||||
impl PartialEq for MessageContent {
|
||||
@@ -62,6 +89,7 @@ impl PartialEq for MessageContent {
|
||||
// We can probably do better than this by inspecting `.event_conten1t.source`, but for now this is good enough.
|
||||
a.filename() == b.filename()
|
||||
}
|
||||
(MessageContent::File(a), MessageContent::File(b)) => a.filename() == b.filename(),
|
||||
_ => false,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -74,6 +74,7 @@ fn calculate_token_size_for_message(bpe: &CoreBPE, model: &str, message: &Messag
|
||||
let text_length = match &message.content {
|
||||
MessageContent::Text(text) => bpe.encode_with_special_tokens(text).len() as i32,
|
||||
MessageContent::Image(..) => 0,
|
||||
MessageContent::File(..) => 0,
|
||||
};
|
||||
|
||||
(text_length + role_length + tokens_per_message + tokens_per_name) as u32
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
use mxlink::matrix_sdk::ruma::OwnedUserId;
|
||||
|
||||
use super::entity::{Author, ImageDetails, Message, MessageContent};
|
||||
use super::entity::{Author, FileDetails, ImageDetails, Message, MessageContent};
|
||||
use crate::conversation::matrix::{MatrixMessage, MatrixMessageContent};
|
||||
use crate::utils::text_to_speech as text_to_speech_utils;
|
||||
|
||||
@@ -32,6 +32,15 @@ fn convert_bot_message(matrix_message: &MatrixMessage) -> Option<Message> {
|
||||
)),
|
||||
timestamp: matrix_message.timestamp.to_owned(),
|
||||
}),
|
||||
MatrixMessageContent::File(file_content, mime_type, media_bytes) => Some(Message {
|
||||
author: Author::Assistant,
|
||||
content: MessageContent::File(FileDetails::new(
|
||||
file_content.clone(),
|
||||
mime_type.clone(),
|
||||
media_bytes.clone(),
|
||||
)),
|
||||
timestamp: matrix_message.timestamp.to_owned(),
|
||||
}),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -90,5 +99,14 @@ fn convert_user_message(matrix_message: &MatrixMessage) -> Option<Message> {
|
||||
)),
|
||||
timestamp: matrix_message.timestamp.to_owned(),
|
||||
}),
|
||||
MatrixMessageContent::File(file_content, mime_type, media_bytes) => Some(Message {
|
||||
author: Author::User,
|
||||
content: MessageContent::File(FileDetails::new(
|
||||
file_content.clone(),
|
||||
mime_type.clone(),
|
||||
media_bytes.clone(),
|
||||
)),
|
||||
timestamp: matrix_message.timestamp.to_owned(),
|
||||
}),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2,7 +2,9 @@ use chrono::{DateTime, Utc};
|
||||
use regex::Regex;
|
||||
|
||||
use mxlink::matrix_sdk::ruma::OwnedUserId;
|
||||
use mxlink::matrix_sdk::ruma::events::room::message::ImageMessageEventContent;
|
||||
use mxlink::matrix_sdk::ruma::events::room::message::{
|
||||
FileMessageEventContent, ImageMessageEventContent,
|
||||
};
|
||||
use mxlink::mime::Mime;
|
||||
|
||||
#[derive(Clone)]
|
||||
@@ -18,6 +20,7 @@ pub enum MatrixMessageContent {
|
||||
Text(String),
|
||||
Notice(String),
|
||||
Image(ImageMessageEventContent, Mime, Vec<u8>),
|
||||
File(FileMessageEventContent, Mime, Vec<u8>),
|
||||
}
|
||||
|
||||
#[derive(Clone)]
|
||||
|
||||
@@ -234,6 +234,7 @@ pub async fn convert_matrix_native_event_to_matrix_message(
|
||||
MessageType::Text(text_content) => (text_content.body.clone(), false),
|
||||
MessageType::Notice(notice_content) => (notice_content.body.clone(), true),
|
||||
MessageType::Image(image_content) => (image_content.body.clone(), false),
|
||||
MessageType::File(file_content) => (file_content.body.clone(), false),
|
||||
_ => return Ok(None),
|
||||
};
|
||||
|
||||
@@ -291,6 +292,67 @@ pub async fn convert_matrix_native_event_to_matrix_message(
|
||||
}));
|
||||
}
|
||||
|
||||
if let MessageType::File(file_content) = &room_message.msgtype {
|
||||
let media_request = mxlink::matrix_sdk::media::MediaRequestParameters {
|
||||
source: file_content.source.to_owned(),
|
||||
format: mxlink::matrix_sdk::media::MediaFormat::File,
|
||||
};
|
||||
|
||||
let file_name = file_content
|
||||
.filename
|
||||
.clone()
|
||||
.unwrap_or(file_content.body.clone());
|
||||
|
||||
let mime_type = file_content
|
||||
.info
|
||||
.as_ref()
|
||||
.and_then(|info| info.mimetype.clone())
|
||||
.and_then(|mimetype| mimetype.parse::<mxlink::mime::Mime>().ok())
|
||||
.unwrap_or_else(|| get_mime_type_from_file_name(&file_name));
|
||||
|
||||
tracing::debug!("Determined mime type {} for file {}", mime_type, file_name);
|
||||
|
||||
if mime_type == mxlink::mime::APPLICATION_OCTET_STREAM {
|
||||
tracing::debug!(
|
||||
"Skipping file {} with unsupported MIME type {}. It will be represented as a text message.",
|
||||
file_name,
|
||||
mime_type,
|
||||
);
|
||||
|
||||
return Ok(Some(MatrixMessage {
|
||||
sender_id: matrix_native_event.sender().to_owned(),
|
||||
content: MatrixMessageContent::Text(format!(
|
||||
"[A file ({}) was attached but skipped because its content type ({}) is not supported. Let the user know.]",
|
||||
file_name, mime_type,
|
||||
)),
|
||||
mentioned_users,
|
||||
timestamp,
|
||||
}));
|
||||
}
|
||||
|
||||
let span = tracing::debug_span!("get_media_content", file_name = %file_name, mime_type = %mime_type);
|
||||
|
||||
let media_bytes = matrix_link
|
||||
.client()
|
||||
.media()
|
||||
.get_media_content(&media_request, true)
|
||||
.instrument(span)
|
||||
.await?;
|
||||
|
||||
tracing::debug!(
|
||||
"Downloaded {} bytes for file {}",
|
||||
media_bytes.len(),
|
||||
file_name
|
||||
);
|
||||
|
||||
return Ok(Some(MatrixMessage {
|
||||
sender_id: matrix_native_event.sender().to_owned(),
|
||||
content: MatrixMessageContent::File(file_content.clone(), mime_type, media_bytes),
|
||||
mentioned_users,
|
||||
timestamp,
|
||||
}));
|
||||
}
|
||||
|
||||
Ok(Some(MatrixMessage {
|
||||
sender_id: matrix_native_event.sender().to_owned(),
|
||||
content: if is_notice {
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
use mxlink::matrix_sdk::ruma::events::room::message::{
|
||||
AudioMessageEventContent, ImageMessageEventContent, MessageType, TextMessageEventContent,
|
||||
AudioMessageEventContent, FileMessageEventContent, ImageMessageEventContent, MessageType,
|
||||
TextMessageEventContent,
|
||||
};
|
||||
use mxlink::matrix_sdk::ruma::{OwnedEventId, OwnedUserId};
|
||||
|
||||
@@ -30,6 +31,7 @@ pub enum MessagePayload {
|
||||
Text(TextMessageEventContent),
|
||||
Audio(AudioMessageEventContent),
|
||||
Image(ImageMessageEventContent),
|
||||
File(FileMessageEventContent),
|
||||
|
||||
Reaction {
|
||||
key: String,
|
||||
@@ -57,6 +59,7 @@ impl TryInto<MessagePayload> for MessageType {
|
||||
MessagePayload::Audio(audio_content)
|
||||
}
|
||||
MessageType::Image(image_content) => MessagePayload::Image(image_content),
|
||||
MessageType::File(file_content) => MessagePayload::File(file_content),
|
||||
other => {
|
||||
return Err(format!("Unsupported message type: {:?}", other));
|
||||
}
|
||||
|
||||
@@ -17,18 +17,7 @@ pub fn get_file_extension(mime_type: &mime::Mime) -> String {
|
||||
}
|
||||
|
||||
pub fn get_mime_type_from_file_name(file_name: &str) -> mime::Mime {
|
||||
let extension = file_name.rsplit('.').next().unwrap_or("");
|
||||
|
||||
match extension.to_lowercase().as_str() {
|
||||
"jpg" | "jpeg" => mime::IMAGE_JPEG,
|
||||
"png" => mime::IMAGE_PNG,
|
||||
"gif" => mime::IMAGE_GIF,
|
||||
"webp" => "image/webp".parse().unwrap(),
|
||||
"svg" => mime::IMAGE_SVG,
|
||||
"tiff" | "tif" => "image/tiff".parse().unwrap(),
|
||||
"bmp" => "image/bmp".parse().unwrap(),
|
||||
"heic" | "heif" => "image/heic".parse().unwrap(),
|
||||
"avif" => "image/avif".parse().unwrap(),
|
||||
_ => mime::APPLICATION_OCTET_STREAM,
|
||||
}
|
||||
mime_guess::from_path(file_name)
|
||||
.first()
|
||||
.unwrap_or(mime::APPLICATION_OCTET_STREAM)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user