Simple bot to interact with Open Source LLM's running in Ollama using Telegram

Find a file

Alexey Skobkin 9f65c26bb5 Revert "Trying to manually lessen Go version requirement for CI." This reverts commit `943dcecfb2`.		2024-08-16 03:40:12 +03:00
bot	Allowing selection of models using ENV.	2024-08-16 03:07:47 +03:00
extractor	fix #15 slog usage. Also adding more logging.	2024-03-12 22:07:22 +03:00
llm	Improving single request and chat context prompts.	2024-08-16 03:28:43 +03:00
stats	Closes #14 . Adding inline queries. Also small refactoring of context prompt based on RequestContext.	2024-03-13 01:18:01 +03:00
.drone.yml	Also changing image tag for build step.	2024-03-10 05:57:59 +03:00
.gitignore	initial. Draft of SIMPLE LLM bot for Telegram chat.	2024-03-08 05:18:45 +03:00
Dockerfile	Allowing selection of models using ENV.	2024-08-16 03:07:47 +03:00
go.mod	Revert "Trying to manually lessen Go version requirement for CI."	2024-08-16 03:40:12 +03:00
go.sum	Updating dependencies.	2024-08-16 03:10:12 +03:00
LICENSE	LICENSE file.	2024-03-08 05:19:26 +03:00
main.go	Allowing selection of models using ENV.	2024-08-16 03:07:47 +03:00
README.md	Updating docs according to recent changes.	2024-08-16 03:35:31 +03:00

README.md

telegram-ollama-reply-bot

Usage

Docker

docker run \
  -e OPENAI_API_TOKEN=123 \
  -e OPENAI_API_BASE_URL=http://ollama.localhost:11434/v1 \
  -e TELEGRAM_TOKEN=12345 \
  -e MODEL_TEXT_REQUEST=llama3.1:8b-instruct-q6_K
  -e MODEL_TEXT_REQUEST=mistral-nemo:12b-instruct-2407-q4_K_M
  skobkin/telegram-llm-bot