Updated docker compose

.dockerignore

@@ -10,3 +10,5 @@ terraform
 tests
 Dockerfile
 Dockerfile.*
+private_gpt/static/unchecked
+local_data/private_gpt

Dockerfile.external

@@ -1,4 +1,16 @@
 FROM python:3.11.6-slim-bookworm as base
+# Set noninteractive mode
+ENV DEBIAN_FRONTEND noninteractive
+# Install necessary dependencies including CMake and g++
+RUN apt-get update && apt-get install -y \
+    libopenblas-dev \
+    ninja-build \
+    build-essential \
+    pkg-config \
+    wget \
+    libgl1-mesa-glx \
+    python3-opencv \
+    && apt-get clean
 
 # Install poetry
 RUN pip install pipx
@@ -6,36 +18,39 @@ RUN python3 -m pipx ensurepath
 RUN pipx install poetry
 ENV PATH="/root/.local/bin:$PATH"
 ENV PATH=".venv/bin/:$PATH"
-
 # https://python-poetry.org/docs/configuration/#virtualenvsin-project
 ENV POETRY_VIRTUALENVS_IN_PROJECT=true
 
 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"
 
 FROM base as app
-
 ENV PYTHONUNBUFFERED=1
-ENV PORT=8080
-EXPOSE 8080
+ENV PORT=8000
 
 # Prepare a non-root user
 RUN adduser --system worker
 WORKDIR /home/worker/app
-
 RUN mkdir local_data; chown worker local_data
 RUN mkdir models; chown worker models
+RUN mkdir tiktoken_cache; chown worker tiktoken_cache
 COPY --chown=worker --from=dependencies /home/worker/app/.venv/ .venv
 COPY --chown=worker private_gpt/ private_gpt
+COPY --chown=worker alembic/ alembic
 COPY --chown=worker fern/ fern
 COPY --chown=worker *.yaml *.md ./
 COPY --chown=worker scripts/ scripts
-RUN 
+COPY --chown=worker *.ini ./ 
+# Copy the docker-entrypoint.sh file
+COPY docker-entrypoint.sh /home/worker/app/
 
+RUN chmod +x /home/worker/app/docker-entrypoint.sh
 ENV PYTHONPATH="$PYTHONPATH:/private_gpt/"
-
 USER worker
-ENTRYPOINT python -m private_gpt
+
+EXPOSE 8000
+# Copy the rest of the application code into the container
+COPY . /home/worker/app
+ENTRYPOINT [ "/home/worker/app/docker-entrypoint.sh" ]

docker-compose.yaml

@@ -1,28 +1,46 @@
+version: '3.8'
+
 services:
   private-gpt:
     build:
       dockerfile: Dockerfile.external
-    volumes:
-      - ./local_data/:/home/worker/app/local_data
-    ports:
-<<<<<<< HEAD
-      - 80:80
-    environment:
-      PORT: 80
-      PGPT_PROFILES: docker
-      PGPT_MODE: local
+    entrypoint: ./docker-entrypoint.sh
 
     env_file:
       - .env
-    
-=======
-      - 8001:8080
+    volumes:
+      - ./local_data/:/home/worker/app/local_data
+    ports:
+      - 8000:8000
+    depends_on:
+      - db
+      - ollama
     environment:
-      PORT: 8080
+      PORT: 8000
       PGPT_PROFILES: docker
       PGPT_MODE: ollama
+      DATABASE_URL: postgresql+psycopg2://${DB_USER}:${DB_PASSWORD}@db:${DB_PORT}/${DB_NAME}
+    
   ollama:
     image: ollama/ollama:latest
     volumes:
       - ./models:/root/.ollama
->>>>>>> dev
+
+  db:
+    image: postgres:15-alpine
+    container_name: db
+    env_file:
+      - .env
+    environment:
+      POSTGRES_USER: ${DB_USER}
+      POSTGRES_PASSWORD: ${DB_PASSWORD}
+      POSTGRES_DB: ${DB_NAME}
+      # POSTGRES_HOST_AUTH_METHOD: trust
+    restart: always
+    volumes:
+      - postgres-data:/var/lib/postgresql/data
+    ports:
+      - 5433:${DB_PORT}
+
+volumes:
+  postgres-data:

docker-entrypoint.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+
+# Initialize alembic ini
+# echo "Apply makemigrations "
+# alembic init alembic
+
+# Apply database migrations
+echo "Apply makemigrations "
+alembic revision --autogenerate
+
+# Apply database migrations
+echo "Apply database migrations"
+alembic upgrade head
+
+# Start server
+echo "Starting server"
+python -m private_gpt

private_gpt/components/llm/llm_component.py

@@ -13,6 +13,8 @@ from private_gpt.paths import models_cache_path, models_path
 from private_gpt.settings.settings import Settings
 
 logger = logging.getLogger(__name__)
+
+
 @singleton
 class LLMComponent:
     llm: LLM
@@ -20,7 +22,9 @@ class LLMComponent:
     @inject
     def __init__(self, settings: Settings) -> None:
         llm_mode = settings.llm.mode
-        if settings.llm.tokenizer:
+        if settings.llm.tokenizer and settings.llm.mode != "mock":
+            # Try to download the tokenizer. If it fails, the LLM will still work
+            # using the default one, which is less accurate.
             try:
                 set_global_tokenizer(
                     AutoTokenizer.from_pretrained(
@@ -37,7 +41,6 @@ class LLMComponent:
                     e,
                 )
 
-
         logger.info("Initializing the LLM in mode=%s", llm_mode)
         match settings.llm.mode:
             case "llamacpp":
@@ -58,7 +61,8 @@ class LLMComponent:
                     "offload_kqv": True,
                 }
                 self.llm = LlamaCPP(
-                    model_path=str(models_path / settings.llamacpp.llm_hf_model_file),
+                    model_path=str(
+                        models_path / settings.llamacpp.llm_hf_model_file),
                     temperature=settings.llm.temperature,
                     max_new_tokens=settings.llm.max_new_tokens,
                     context_window=settings.llm.context_window,
@@ -159,7 +163,8 @@ class LLMComponent:
                     Ollama.chat = add_keep_alive(Ollama.chat)
                     Ollama.stream_chat = add_keep_alive(Ollama.stream_chat)
                     Ollama.complete = add_keep_alive(Ollama.complete)
-                    Ollama.stream_complete = add_keep_alive(Ollama.stream_complete)
+                    Ollama.stream_complete = add_keep_alive(
+                        Ollama.stream_complete)
 
             case "azopenai":
                 try:

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "private-gpt"
-version = "0.5.0"
+version = "0.4.0"
 description = "Private GPT"
 authors = ["Zylon <hi@zylon.ai>"]
 
@@ -16,7 +16,7 @@ alembic = "^1.13.1"
 sqlalchemy = "^2.0.28"
 bcrypt = "4.0.1"
 python-jose = "^3.3.0"
-#psycopg2-binary = "^2.9.9"
+psycopg2-binary = "^2.9.9"
 passlib = "^1.7.4"
 docx2txt = "^0.8"
 ldap3 = "^2.9.1"
@@ -25,7 +25,7 @@ python-doctr = "^0.8.1"
 python-docx = "^1.1.0"
 watchdog = "^4.0.0"
 # https://stackoverflow.com/questions/76327419/valueerror-libcublas-so-0-9-not-found-in-the-system-path
-#torch = ">=2.0.0, !=2.0.1, !=2.1.0"
+torch = ">=2.0.0, !=2.0.1, !=2.1.0"
 torchvision = "^0.17.1"
 transformers = "^4.38.2"
 
@@ -38,28 +38,16 @@ llama-index-llms-llama-cpp = {version = "^0.1.3", optional = true}
 llama-index-llms-openai = {version = "^0.1.6", optional = true}
 llama-index-llms-openai-like = {version ="^0.1.3", optional = true}
 llama-index-llms-ollama = {version ="^0.1.2", optional = true}
-llama-index-llms-azure-openai = {version ="^0.1.5", optional = true}
 llama-index-embeddings-ollama = {version ="^0.1.2", optional = true}
 llama-index-embeddings-huggingface = {version ="^0.1.4", optional = true}
 llama-index-embeddings-openai = {version ="^0.1.6", optional = true}
-llama-index-embeddings-azure-openai = {version ="^0.1.6", optional = true}
 llama-index-vector-stores-qdrant = {version ="^0.1.3", optional = true}
 llama-index-vector-stores-chroma = {version ="^0.1.4", optional = true}
 llama-index-vector-stores-postgres = {version ="^0.1.2", optional = true}
-llama-index-storage-docstore-postgres = {version ="^0.1.2", optional = true}
-llama-index-storage-index-store-postgres = {version ="^0.1.2", optional = true}
-
-# Postgres
-psycopg2-binary = {version ="^2.9.9", optional = false}
-asyncpg = {version="^0.29.0", optional = true}
 
 # Optional Sagemaker dependency
 boto3 = {version ="^1.34.51", optional = true}
 
-# Optional Reranker dependencies
-torch = {version ="^2.1.2", optional = false}
-sentence-transformers = {version ="^2.6.1", optional = true}
-
 # Optional UI
 gradio = {version ="^4.19.2", optional = true}
 aiofiles = "^23.2.1"
@@ -78,17 +66,14 @@ llms-openai = ["llama-index-llms-openai"]
 llms-openai-like = ["llama-index-llms-openai-like"]
 llms-ollama = ["llama-index-llms-ollama"]
 llms-sagemaker = ["boto3"]
-llms-azopenai = ["llama-index-llms-azure-openai"]
 embeddings-ollama = ["llama-index-embeddings-ollama"]
 embeddings-huggingface = ["llama-index-embeddings-huggingface"]
 embeddings-openai = ["llama-index-embeddings-openai"]
 embeddings-sagemaker = ["boto3"]
-embeddings-azopenai = ["llama-index-embeddings-azure-openai"]
 vector-stores-qdrant = ["llama-index-vector-stores-qdrant"]
 vector-stores-chroma = ["llama-index-vector-stores-chroma"]
 vector-stores-postgres = ["llama-index-vector-stores-postgres"]
-storage-nodestore-postgres = ["llama-index-storage-docstore-postgres","llama-index-storage-index-store-postgres","psycopg2-binary","asyncpg"]
-rerank-sentence-transformers = ["torch", "sentence-transformers"]
+
 
 [tool.poetry.group.dev.dependencies]
 black = "^22"

settings.yaml

@@ -99,7 +99,7 @@ openai:
   model: gpt-3.5-turbo
 
 ollama:
-  llm_model: llama2
+  llm_model: llama3
   embedding_model: nomic-embed-text
   api_base: http://localhost:11434
   embedding_api_base: http://localhost:11434  # change if your embedding model runs on another ollama