Merge branch 'main' into feat/llama3.1

# Conflicts:
#	Dockerfile.external
#	Dockerfile.local

Dockerfile.external

@@ -14,27 +14,38 @@ FROM base as dependencies
 WORKDIR /home/worker/app
 COPY pyproject.toml poetry.lock ./
 
-RUN poetry install --extras "ui vector-stores-qdrant llms-ollama embeddings-ollama"
+ARG POETRY_EXTRAS="ui vector-stores-qdrant llms-ollama embeddings-ollama"
+RUN poetry install --no-root --extras "${POETRY_EXTRAS}"
 
 FROM base as app
-
 ENV PYTHONUNBUFFERED=1
 ENV PORT=8080
+ENV APP_ENV=prod
+ENV PYTHONPATH="$PYTHONPATH:/home/worker/app/private_gpt/"
 EXPOSE 8080
 
 # Prepare a non-root user
-RUN adduser --system worker
+# More info about how to configure UIDs and GIDs in Docker:
+# https://github.com/systemd/systemd/blob/main/docs/UIDS-GIDS.md
+
+# Define the User ID (UID) for the non-root user
+# UID 100 is chosen to avoid conflicts with existing system users
+ARG UID=100
+
+# Define the Group ID (GID) for the non-root user
+# GID 65534 is often used for the 'nogroup' or 'nobody' group
+ARG GID=65534
+
+RUN adduser --system --gid ${GID} --uid ${UID} --home /home/worker worker
 WORKDIR /home/worker/app
 
-RUN mkdir local_data; chown worker local_data
+RUN chown worker /home/worker/app
-RUN mkdir models; chown worker models
+RUN mkdir local_data && chown worker local_data
+RUN mkdir models && chown worker models
 COPY --chown=worker --from=dependencies /home/worker/app/.venv/ .venv
 COPY --chown=worker private_gpt/ private_gpt
-COPY --chown=worker fern/ fern
+COPY --chown=worker *.yaml .
-COPY --chown=worker *.yaml *.md ./
 COPY --chown=worker scripts/ scripts
 
-ENV PYTHONPATH="$PYTHONPATH:/private_gpt/"
-
 USER worker
-ENTRYPOINT python -m private_gpt
+ENTRYPOINT python -m private_gpt

Dockerfile.local

@@ -24,28 +24,39 @@ FROM base as dependencies
 WORKDIR /home/worker/app
 COPY pyproject.toml poetry.lock ./
 
-RUN poetry install --extras "ui embeddings-huggingface llms-llama-cpp vector-stores-qdrant"
+ARG POETRY_EXTRAS="ui embeddings-huggingface llms-llama-cpp vector-stores-qdrant"
+RUN poetry install --no-root --extras "${POETRY_EXTRAS}"
 
 FROM base as app
 
 ENV PYTHONUNBUFFERED=1
 ENV PORT=8080
+ENV APP_ENV=prod
+ENV PYTHONPATH="$PYTHONPATH:/home/worker/app/private_gpt/"
 EXPOSE 8080
 
 # Prepare a non-root user
-RUN adduser --group worker
+# More info about how to configure UIDs and GIDs in Docker:
-RUN adduser --system --ingroup worker worker
+# https://github.com/systemd/systemd/blob/main/docs/UIDS-GIDS.md
+
+# Define the User ID (UID) for the non-root user
+# UID 100 is chosen to avoid conflicts with existing system users
+ARG UID=100
+
+# Define the Group ID (GID) for the non-root user
+# GID 65534 is often used for the 'nogroup' or 'nobody' group
+ARG GID=65534
+
+RUN adduser --system --gid ${GID} --uid ${UID} --home /home/worker worker
 WORKDIR /home/worker/app
 
-RUN mkdir local_data; chown worker local_data
+RUN chown worker /home/worker/app
-RUN mkdir models; chown worker models
+RUN mkdir local_data && chown worker local_data
+RUN mkdir models && chown worker models
 COPY --chown=worker --from=dependencies /home/worker/app/.venv/ .venv
 COPY --chown=worker private_gpt/ private_gpt
-COPY --chown=worker fern/ fern
+COPY --chown=worker *.yaml ./
-COPY --chown=worker *.yaml *.md ./
 COPY --chown=worker scripts/ scripts
 
-ENV PYTHONPATH="$PYTHONPATH:/private_gpt/"
-
 USER worker
 ENTRYPOINT python -m private_gpt

docker-compose.yaml

@@ -5,12 +5,15 @@ services:
     volumes:
       - ./local_data/:/home/worker/app/local_data
     ports:
-      - 8001:8080
+      - 8001:8001
     environment:
-      PORT: 8080
+      PORT: 8001
       PGPT_PROFILES: docker
       PGPT_MODE: ollama
+      PGPT_EMBED_MODE: ollama
   ollama:
     image: ollama/ollama:latest
+    ports:
+      - 11434:11434
     volumes:
       - ./models:/root/.ollama

settings-docker.yaml

@@ -6,7 +6,7 @@ llm:
   mode: ${PGPT_MODE:mock}
 
 embedding:
-  mode: ${PGPT_MODE:sagemaker}
+  mode: ${PGPT_EMBED_MODE:mock}
 
 llamacpp:
   llm_hf_repo_id: ${PGPT_HF_REPO_ID:lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF}
@@ -30,6 +30,7 @@ ollama:
   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