mirror of
https://github.com/zylon-ai/private-gpt.git
synced 2025-12-22 04:30:11 +01:00
65c5a1708b
Some checks are pending
release-please / release-please (push) Waiting to run
tests / setup (push) Waiting to run
tests / ${{ matrix.quality-command }} (black) (push) Blocked by required conditions
tests / ${{ matrix.quality-command }} (mypy) (push) Blocked by required conditions
tests / ${{ matrix.quality-command }} (ruff) (push) Blocked by required conditions
tests / test (push) Blocked by required conditions
tests / all_checks_passed (push) Blocked by required conditions
* `UID` and `GID` build arguments for `worker` user * `POETRY_EXTRAS` build argument with default values * Copy `Makefile` for `make ingest` command * Do NOT copy markdown files I doubt anyone reads a markdown file within a Docker image * Fix PYTHONPATH value * Set home directory to `/home/worker` when creating user * Combine `ENV` instructions together * Define environment variables with their defaults - For documentation purposes - Reflect defaults set in settings-docker.yml * `PGPT_EMBEDDING_MODE` to define embedding mode * Remove ineffective `python3 -m pipx ensurepath` * Use `&&` instead of `;` to chain commands to detect failure better * Add `--no-root` flag to poetry install commands * Set PGPT_PROFILES to docker * chore: remove envs * chore: update to use ollama in docker-compose * chore: don't copy makefile * chore: don't copy fern * fix: tiktoken cache * fix: docker compose port * fix: ffmpy dependency (#2020) * fix: ffmpy dependency * fix: block ffmpy to commit sha * feat(llm): autopull ollama models (#2019) * chore: update ollama (llm) * feat: allow to autopull ollama models * fix: mypy * chore: install always ollama client * refactor: check connection and pull ollama method to utils * docs: update ollama config with autopulling info ... * chore: autopull ollama models * chore: add GID/UID comment ... --------- Co-authored-by: Javier Martinez <javiermartinezalvarez98@gmail.com>
37 lines
1.1 KiB
YAML
37 lines
1.1 KiB
YAML
server:
|
|
env_name: ${APP_ENV:prod}
|
|
port: ${PORT:8080}
|
|
|
|
llm:
|
|
mode: ${PGPT_MODE:mock}
|
|
|
|
embedding:
|
|
mode: ${PGPT_EMBED_MODE:mock}
|
|
|
|
llamacpp:
|
|
llm_hf_repo_id: ${PGPT_HF_REPO_ID:TheBloke/Mistral-7B-Instruct-v0.1-GGUF}
|
|
llm_hf_model_file: ${PGPT_HF_MODEL_FILE:mistral-7b-instruct-v0.1.Q4_K_M.gguf}
|
|
|
|
huggingface:
|
|
embedding_hf_model_name: ${PGPT_EMBEDDING_HF_MODEL_NAME:BAAI/bge-small-en-v1.5}
|
|
|
|
sagemaker:
|
|
llm_endpoint_name: ${PGPT_SAGEMAKER_LLM_ENDPOINT_NAME:}
|
|
embedding_endpoint_name: ${PGPT_SAGEMAKER_EMBEDDING_ENDPOINT_NAME:}
|
|
|
|
ollama:
|
|
llm_model: ${PGPT_OLLAMA_LLM_MODEL:mistral}
|
|
embedding_model: ${PGPT_OLLAMA_EMBEDDING_MODEL:nomic-embed-text}
|
|
api_base: ${PGPT_OLLAMA_API_BASE:http://ollama:11434}
|
|
embedding_api_base: ${PGPT_OLLAMA_EMBEDDING_API_BASE:http://ollama:11434}
|
|
tfs_z: ${PGPT_OLLAMA_TFS_Z:1.0}
|
|
top_k: ${PGPT_OLLAMA_TOP_K:40}
|
|
top_p: ${PGPT_OLLAMA_TOP_P:0.9}
|
|
repeat_last_n: ${PGPT_OLLAMA_REPEAT_LAST_N:64}
|
|
repeat_penalty: ${PGPT_OLLAMA_REPEAT_PENALTY:1.2}
|
|
request_timeout: ${PGPT_OLLAMA_REQUEST_TIMEOUT:600.0}
|
|
autopull_models: ${PGPT_OLLAMA_AUTOPULL_MODELS:true}
|
|
|
|
ui:
|
|
enabled: true
|
|
path: /
|