Update README.md

When running private gpt with external ollama API, ollama service
returns 503 on startup because ollama service (traefik) might not be
ready.

- Add healthcheck to ollama service to test for connection to external
ollama
- private-gpt-ollama service depends on ollama being service_healthy

Co-authored-by: Koh Meng Hui <kohmh@duck.com>

.docker/router.yml

@@ -0,0 +1,16 @@
+http:
+  services:
+    ollama:
+      loadBalancer:
+        healthCheck:
+          interval: 5s
+          path: /
+        servers:
+          - url: http://ollama-cpu:11434
+          - url: http://ollama-cuda:11434
+          - url: http://host.docker.internal:11434
+
+  routers:
+    ollama-router:
+      rule: "PathPrefix(`/`)"
+      service: ollama

.github/release_please/.release-please-config.json

@@ -0,0 +1,19 @@
+{
+    "$schema": "https://raw.githubusercontent.com/googleapis/release-please/main/schemas/config.json",
+    "release-type": "simple",
+    "version-file": "version.txt",
+    "extra-files": [
+      {
+        "type": "toml",
+        "path": "pyproject.toml",
+        "jsonpath": "$.tool.poetry.version"
+      },
+      {
+        "type": "generic",
+        "path": "docker-compose.yaml"
+      }
+    ],
+    "packages": {
+      ".": {}
+    }
+  }

.github/release_please/.release-please-manifest.json

@@ -0,0 +1,3 @@
+{
+  ".": "0.6.2"
+}

.github/workflows/docker.yml

@@ -1,45 +0,0 @@
-name: docker
-
-on:
-  release:
-    types: [ published ]
-  workflow_dispatch:
-
-env:
-  REGISTRY: ghcr.io
-  IMAGE_NAME: ${{ github.repository }}
-
-jobs:
-  build-and-push-image:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-      - name: Log in to the Container registry
-        uses: docker/login-action@v3
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
-          tags: |
-            type=ref,event=branch
-            type=ref,event=pr
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-            type=sha
-      - name: Build and push Docker image
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          file: Dockerfile.external
-          push: true
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/generate-release.yml

@@ -0,0 +1,83 @@
+name: generate-release
+
+on:
+  release:
+    types: [ published ]
+  workflow_dispatch:
+
+env:
+  REGISTRY: docker.io
+  IMAGE_NAME: zylonai/private-gpt
+  platforms: linux/amd64,linux/arm64
+  DEFAULT_TYPE: "ollama"
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        type: [ llamacpp-cpu, ollama ]
+
+    permissions:
+      contents: read
+      packages: write
+
+    outputs:
+      version: ${{ steps.version.outputs.version }}
+
+    steps:
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          tool-cache: false
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          tags: |
+            type=semver,pattern={{version}},enable=${{ matrix.type == env.DEFAULT_TYPE }}
+            type=semver,pattern={{version}}-${{ matrix.type }}
+            type=semver,pattern={{major}}.{{minor}},enable=${{ matrix.type == env.DEFAULT_TYPE }}
+            type=semver,pattern={{major}}.{{minor}}-${{ matrix.type }}
+            type=raw,value=latest,enable=${{ matrix.type == env.DEFAULT_TYPE }}
+            type=sha
+          flavor: |
+            latest=false
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: Dockerfile.${{ matrix.type }}
+          platforms: ${{ env.platforms }}
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+
+      - name: Version output
+        id: version
+        run: echo "version=${{ steps.meta.outputs.version }}" >> "$GITHUB_OUTPUT"

.github/workflows/release-please.yml

@@ -13,7 +13,8 @@ jobs:
   release-please:
     runs-on: ubuntu-latest
     steps:
-      - uses: google-github-actions/release-please-action@v3
+      - uses: google-github-actions/release-please-action@v4
+        id: release
         with:
-          release-type: simple
-          version-file: version.txt
+          config-file: .github/release_please/.release-please-config.json
+          manifest-file: .github/release_please/.release-please-manifest.json

.github/workflows/tests.yml

@@ -14,7 +14,7 @@ jobs:
   setup:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: ./.github/workflows/actions/install_dependencies
 
   checks:
@@ -28,7 +28,7 @@ jobs:
           - ruff
           - mypy
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: ./.github/workflows/actions/install_dependencies
       - name: run ${{ matrix.quality-command }}
         run: make ${{ matrix.quality-command }}
@@ -38,7 +38,7 @@ jobs:
     runs-on: ubuntu-latest
     name: test
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: ./.github/workflows/actions/install_dependencies
       - name: run test
         run: make test-coverage

CHANGELOG.md

@@ -1,5 +1,25 @@
 # Changelog
 
+## [0.6.2](https://github.com/zylon-ai/private-gpt/compare/v0.6.1...v0.6.2) (2024-08-08)
+
+
+### Bug Fixes
+
+* add numpy issue to troubleshooting ([#2048](https://github.com/zylon-ai/private-gpt/issues/2048)) ([4ca6d0c](https://github.com/zylon-ai/private-gpt/commit/4ca6d0cb556be7a598f7d3e3b00d2a29214ee1e8))
+* auto-update version ([#2052](https://github.com/zylon-ai/private-gpt/issues/2052)) ([7fefe40](https://github.com/zylon-ai/private-gpt/commit/7fefe408b4267684c6e3c1a43c5dc2b73ec61fe4))
+* publish image name ([#2043](https://github.com/zylon-ai/private-gpt/issues/2043)) ([b1acf9d](https://github.com/zylon-ai/private-gpt/commit/b1acf9dc2cbca2047cd0087f13254ff5cda6e570))
+* update matplotlib to 3.9.1-post1 to fix win install ([b16abbe](https://github.com/zylon-ai/private-gpt/commit/b16abbefe49527ac038d235659854b98345d5387))
+
+## [0.6.1](https://github.com/zylon-ai/private-gpt/compare/v0.6.0...v0.6.1) (2024-08-05)
+
+
+### Bug Fixes
+
+* add built image from DockerHub ([#2042](https://github.com/zylon-ai/private-gpt/issues/2042)) ([f09f6dd](https://github.com/zylon-ai/private-gpt/commit/f09f6dd2553077d4566dbe6b48a450e05c2f049e))
+* Adding azopenai to model list ([#2035](https://github.com/zylon-ai/private-gpt/issues/2035)) ([1c665f7](https://github.com/zylon-ai/private-gpt/commit/1c665f7900658144f62814b51f6e3434a6d7377f))
+* **deploy:** generate docker release when new version is released ([#2038](https://github.com/zylon-ai/private-gpt/issues/2038)) ([1d4c14d](https://github.com/zylon-ai/private-gpt/commit/1d4c14d7a3c383c874b323d934be01afbaca899e))
+* **deploy:** improve Docker-Compose and quickstart on Docker ([#2037](https://github.com/zylon-ai/private-gpt/issues/2037)) ([dae0727](https://github.com/zylon-ai/private-gpt/commit/dae0727a1b4abd35d2b0851fe30e0a4ed67e0fbb))
+
 ## [0.6.0](https://github.com/zylon-ai/private-gpt/compare/v0.5.0...v0.6.0) (2024-08-02)
 
 

Dockerfile.llamacpp-cpu

@@ -1,6 +1,6 @@
 ### IMPORTANT, THIS IMAGE CAN ONLY BE RUN IN LINUX DOCKER
 ### You will run into a segfault in mac
-FROM python:3.11.6-slim-bookworm as base
+FROM python:3.11.6-slim-bookworm AS base
 
 # Install poetry
 RUN pip install pipx
@@ -20,14 +20,14 @@ RUN apt update && apt install -y \
 # https://python-poetry.org/docs/configuration/#virtualenvsin-project
 ENV POETRY_VIRTUALENVS_IN_PROJECT=true
 
-FROM base as dependencies
+FROM base AS dependencies
 WORKDIR /home/worker/app
 COPY pyproject.toml poetry.lock ./
 
 ARG POETRY_EXTRAS="ui embeddings-huggingface llms-llama-cpp vector-stores-qdrant"
 RUN poetry install --no-root --extras "${POETRY_EXTRAS}"
 
-FROM base as app
+FROM base AS app
 
 ENV PYTHONUNBUFFERED=1
 ENV PORT=8080

Dockerfile.ollama

@@ -1,4 +1,4 @@
-FROM python:3.11.6-slim-bookworm as base
+FROM python:3.11.6-slim-bookworm AS base
 
 # Install poetry
 RUN pip install pipx
@@ -10,14 +10,14 @@ ENV PATH=".venv/bin/:$PATH"
 # https://python-poetry.org/docs/configuration/#virtualenvsin-project
 ENV POETRY_VIRTUALENVS_IN_PROJECT=true
 
-FROM base as dependencies
+FROM base AS dependencies
 WORKDIR /home/worker/app
 COPY pyproject.toml poetry.lock ./
 
 ARG POETRY_EXTRAS="ui vector-stores-qdrant llms-ollama embeddings-ollama"
 RUN poetry install --no-root --extras "${POETRY_EXTRAS}"
 
-FROM base as app
+FROM base AS app
 ENV PYTHONUNBUFFERED=1
 ENV PORT=8080
 ENV APP_ENV=prod

README.md

@@ -1,4 +1,6 @@
-# 🔒 PrivateGPT 📑
+# PrivateGPT 
+
+<a href="https://trendshift.io/repositories/2601" target="_blank"><img src="https://trendshift.io/api/badge/repositories/2601" alt="imartinez%2FprivateGPT | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 
 [![Tests](https://github.com/zylon-ai/private-gpt/actions/workflows/tests.yml/badge.svg)](https://github.com/zylon-ai/private-gpt/actions/workflows/tests.yml?query=branch%3Amain)
 [![Website](https://img.shields.io/website?up_message=check%20it&down_message=down&url=https%3A%2F%2Fdocs.privategpt.dev%2F&label=Documentation)](https://docs.privategpt.dev/)

docker-compose.yaml

@@ -1,19 +1,116 @@
 services:
-  private-gpt:
+
+  #-----------------------------------
+  #---- Private-GPT services ---------
+  #-----------------------------------
+
+  # Private-GPT service for the Ollama CPU and GPU modes
+  # This service builds from an external Dockerfile and runs the Ollama mode.
+  private-gpt-ollama:
+    image: ${PGPT_IMAGE:-zylonai/private-gpt}:${PGPT_TAG:-0.6.2}-ollama  # x-release-please-version
+    user: root
     build:
-      dockerfile: Dockerfile.external
+      context: .
+      dockerfile: Dockerfile.ollama
     volumes:
-      - ./local_data/:/home/worker/app/local_data
+      - ./local_data:/home/worker/app/local_data
     ports:
-      - 8001:8001
+      - "8001:8001"
     environment:
       PORT: 8001
       PGPT_PROFILES: docker
       PGPT_MODE: ollama
       PGPT_EMBED_MODE: ollama
+      PGPT_OLLAMA_API_BASE: http://ollama:11434
+      HF_TOKEN: ${HF_TOKEN:-}
+    profiles:
+      - ""
+      - ollama-cpu
+      - ollama-cuda
+      - ollama-api
+    depends_on:
       ollama:
+        condition: service_healthy
+
+  # Private-GPT service for the local mode
+  # This service builds from a local Dockerfile and runs the application in local mode.
+  private-gpt-llamacpp-cpu:
+    image: ${PGPT_IMAGE:-zylonai/private-gpt}:${PGPT_TAG:-0.6.2}-llamacpp-cpu # x-release-please-version
+    user: root
+    build:
+      context: .
+      dockerfile: Dockerfile.llamacpp-cpu
+    volumes:
+      - ./local_data/:/home/worker/app/local_data
+      - ./models/:/home/worker/app/models
+    entrypoint: sh -c ".venv/bin/python scripts/setup && .venv/bin/python -m private_gpt"
+    ports:
+      - "8001:8001"
+    environment:
+      PORT: 8001
+      PGPT_PROFILES: local
+      HF_TOKEN: ${HF_TOKEN:-}
+    profiles:
+      - llamacpp-cpu
+
+  #-----------------------------------
+  #---- Ollama services --------------
+  #-----------------------------------
+
+  # Traefik reverse proxy for the Ollama service
+  # This will route requests to the Ollama service based on the profile.
+  ollama:
+    image: traefik:v2.10
+    healthcheck:
+      test: ["CMD", "sh", "-c", "wget -q --spider http://ollama:11434 || exit 1"]
+      interval: 10s
+      retries: 3
+      start_period: 5s
+      timeout: 5s
+    ports:
+      - "8080:8080"
+    command:
+      - "--providers.file.filename=/etc/router.yml"
+      - "--log.level=ERROR"
+      - "--api.insecure=true"
+      - "--providers.docker=true"
+      - "--providers.docker.exposedbydefault=false"
+      - "--entrypoints.web.address=:11434"
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+      - ./.docker/router.yml:/etc/router.yml:ro
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    profiles:
+      - ""
+      - ollama-cpu
+      - ollama-cuda
+      - ollama-api
+
+  # Ollama service for the CPU mode
+  ollama-cpu:
     image: ollama/ollama:latest
     ports:
-      - 11434:11434
+      - "11434:11434"
     volumes:
       - ./models:/root/.ollama
+    profiles:
+      - ""
+      - ollama-cpu
+
+  # Ollama service for the CUDA mode
+  ollama-cuda:
+    image: ollama/ollama:latest
+    ports:
+      - "11434:11434"
+    volumes:
+      - ./models:/root/.ollama
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    profiles:
+      - ollama-cuda

fern/docs.yml

@@ -10,6 +10,9 @@ tabs:
   overview:
     display-name: Overview
     icon: "fa-solid fa-home"
+  quickstart:
+    display-name: Quickstart
+    icon: "fa-solid fa-rocket"
   installation:
     display-name: Installation
     icon: "fa-solid fa-download"
@@ -32,6 +35,12 @@ navigation:
         contents:
           - page: Introduction
             path: ./docs/pages/overview/welcome.mdx
+  - tab: quickstart
+    layout:
+      - section: Getting started
+        contents:
+          - page: Quickstart
+            path: ./docs/pages/quickstart/quickstart.mdx
   # How to install PrivateGPT, with FAQ and troubleshooting
   - tab: installation
     layout:

fern/docs/pages/installation/installation.mdx

@@ -307,11 +307,12 @@ If you have all required dependencies properly configured running the
 following powershell command should succeed.
 
 ```powershell
-$env:CMAKE_ARGS='-DLLAMA_CUBLAS=on'; poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python
+$env:CMAKE_ARGS='-DLLAMA_CUBLAS=on'; poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python numpy==1.26.0
 ```
 
 If your installation was correct, you should see a message similar to the following next
-time you start the server `BLAS = 1`.
+time you start the server `BLAS = 1`. If there is some issue, please refer to the
+[troubleshooting](/installation/getting-started/troubleshooting#building-llama-cpp-with-nvidia-gpu-support) section.
 
 ```console
 llama_new_context_with_model: total VRAM used: 4857.93 MB (model: 4095.05 MB, context: 762.87 MB)
@@ -339,11 +340,12 @@ Some tips:
 After that running the following command in the repository will install llama.cpp with GPU support:
 
 ```bash
-CMAKE_ARGS='-DLLAMA_CUBLAS=on' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python
+CMAKE_ARGS='-DLLAMA_CUBLAS=on' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python numpy==1.26.0
 ```
 
 If your installation was correct, you should see a message similar to the following next
-time you start the server `BLAS = 1`.
+time you start the server `BLAS = 1`. If there is some issue, please refer to the
+[troubleshooting](/installation/getting-started/troubleshooting#building-llama-cpp-with-nvidia-gpu-support) section.
 
 ```
 llama_new_context_with_model: total VRAM used: 4857.93 MB (model: 4095.05 MB, context: 762.87 MB)

fern/docs/pages/installation/troubleshooting.mdx

@@ -47,3 +47,18 @@ embedding:
   embed_dim: 384
 ```
 </Callout>
+
+# Building Llama-cpp with NVIDIA GPU support
+
+## Out-of-memory error
+
+If you encounter an out-of-memory error while running `llama-cpp` with CUDA, you can try the following steps to resolve the issue:
+1. **Set the next environment:**
+    ```bash
+    TOKENIZERS_PARALLELISM=true
+    ```
+2. **Run PrivateGPT:**
+    ```bash
+    poetry run python -m privategpt
+    ```
+Give thanks to [MarioRossiGithub](https://github.com/MarioRossiGithub) for providing the following solution.

fern/docs/pages/quickstart/quickstart.mdx

@@ -0,0 +1,105 @@
+This guide provides a quick start for running different profiles of PrivateGPT using Docker Compose.
+The profiles cater to various environments, including Ollama setups (CPU, CUDA, MacOS), and a fully local setup.
+
+By default, Docker Compose will download pre-built images from a remote registry when starting the services. However, you have the option to build the images locally if needed. Details on building Docker image locally are provided at the end of this guide.
+
+If you want to run PrivateGPT locally without Docker, refer to the [Local Installation Guide](/installation).
+
+## Prerequisites
+- **Docker and Docker Compose:** Ensure both are installed on your system.
+  [Installation Guide for Docker](https://docs.docker.com/get-docker/), [Installation Guide for Docker Compose](https://docs.docker.com/compose/install/).
+- **Clone PrivateGPT Repository:** Clone the PrivateGPT repository to your machine and navigate to the directory:
+  ```sh
+  git clone https://github.com/zylon-ai/private-gpt.git
+  cd private-gpt
+  ```
+
+## Setups
+
+### Ollama Setups (Recommended)
+
+#### 1. Default/Ollama CPU
+
+**Description:**
+This profile runs the Ollama service using CPU resources. It is the standard configuration for running Ollama-based Private-GPT services without GPU acceleration.
+
+**Run:**
+To start the services using pre-built images, run:
+```sh
+docker-compose up
+```
+or with a specific profile:
+```sh
+docker-compose --profile ollama-cpu up
+```
+
+#### 2. Ollama Nvidia CUDA
+
+**Description:**
+This profile leverages GPU acceleration with CUDA support, suitable for computationally intensive tasks that benefit from GPU resources.
+
+**Requirements:**
+Ensure that your system has compatible GPU hardware and the necessary NVIDIA drivers installed. The installation process is detailed [here](https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html).
+
+**Run:**
+To start the services with CUDA support using pre-built images, run:
+```sh
+docker-compose --profile ollama-cuda up
+```
+
+#### 3. Ollama External API
+
+**Description:**
+This profile is designed for running PrivateGPT using Ollama installed on the host machine. This setup is particularly useful for MacOS users, as Docker does not yet support Metal GPU.
+
+**Requirements:**
+Install Ollama on your machine by following the instructions at [ollama.ai](https://ollama.ai/).
+
+**Run:**
+To start the Ollama service, use:
+```sh
+OLLAMA_HOST=0.0.0.0 ollama serve
+```
+To start the services with the host configuration using pre-built images, run:
+```sh
+docker-compose --profile ollama-api up
+```
+
+### Fully Local Setups
+
+#### 1. LlamaCPP CPU
+
+**Description:**
+This profile runs the Private-GPT services locally using `llama-cpp` and Hugging Face models.
+
+**Requirements:**
+A **Hugging Face Token (HF_TOKEN)** is required for accessing Hugging Face models. Obtain your token following [this guide](/installation/getting-started/troubleshooting#downloading-gated-and-private-models).
+
+**Run:**
+Start the services with your Hugging Face token using pre-built images:
+```sh
+HF_TOKEN=<your_hf_token> docker-compose --profile llamacpp-cpu up
+```
+Replace `<your_hf_token>` with your actual Hugging Face token.
+
+## Building Locally
+
+If you prefer to build Docker images locally, which is useful when making changes to the codebase or the Dockerfiles, follow these steps:
+
+### Building Locally
+To build the Docker images locally, navigate to the cloned repository directory and run:
+```sh
+docker-compose build
+```
+This command compiles the necessary Docker images based on the current codebase and Dockerfile configurations.
+
+### Forcing a Rebuild with --build
+If you have made changes and need to ensure these changes are reflected in the Docker images, you can force a rebuild before starting the services:
+```sh
+docker-compose up --build
+```
+or with a specific profile:
+```sh
+docker-compose --profile <profile_name> up --build
+```
+Replace `<profile_name>` with the desired profile.

private_gpt/components/embedding/embedding_component.py

@@ -144,6 +144,23 @@ class EmbeddingComponent:
                     api_key=settings.gemini.api_key,
                     model_name=settings.gemini.embedding_model,
                 )
+            case "mistralai":
+                try:
+                    from llama_index.embeddings.mistralai import (  # type: ignore
+                        MistralAIEmbedding,
+                    )
+                except ImportError as e:
+                    raise ImportError(
+                        "Mistral dependencies not found, install with `poetry install --extras embeddings-mistral`"
+                    ) from e
+
+                api_key = settings.openai.api_key
+                model = settings.openai.embedding_model
+
+                self.embedding_model = MistralAIEmbedding(
+                    api_key=api_key,
+                    model=model,
+                )
             case "mock":
                 # Not a random number, is the dimensionality used by
                 # the default embedding model

private_gpt/components/ingest/ingest_component.py

@@ -403,7 +403,7 @@ class PipelineIngestComponent(BaseIngestComponentWithIndex):
                 self.transformations,
                 show_progress=self.show_progress,
             )
-            self.node_q.put(("process", file_name, documents, nodes))
+            self.node_q.put(("process", file_name, documents, list(nodes)))
         finally:
             self.doc_semaphore.release()
             self.doc_q.task_done()  # unblock Q joins

private_gpt/components/ingest/ingest_helper.py

@@ -92,7 +92,13 @@ class IngestionHelper:
             return string_reader.load_data([file_data.read_text()])
 
         logger.debug("Specific reader found for extension=%s", extension)
-        return reader_cls().load_data(file_data)
+        documents = reader_cls().load_data(file_data)
+
+        # Sanitize NUL bytes in text which can't be stored in Postgres
+        for i in range(len(documents)):
+            documents[i].text = documents[i].text.replace("\u0000", "")
+
+        return documents
 
     @staticmethod
     def _exclude_metadata(documents: list[Document]) -> None:

private_gpt/components/llm/llm_component.py

@@ -120,7 +120,6 @@ class LLMComponent:
                     api_version="",
                     temperature=settings.llm.temperature,
                     context_window=settings.llm.context_window,
-                    max_new_tokens=settings.llm.max_new_tokens,
                     messages_to_prompt=prompt_style.messages_to_prompt,
                     completion_to_prompt=prompt_style.completion_to_prompt,
                     tokenizer=settings.llm.tokenizer,
@@ -184,10 +183,10 @@ class LLMComponent:
 
                         return wrapper
 
-                    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.chat = add_keep_alive(Ollama.chat)  # type: ignore
+                    Ollama.stream_chat = add_keep_alive(Ollama.stream_chat)  # type: ignore
+                    Ollama.complete = add_keep_alive(Ollama.complete)  # type: ignore
+                    Ollama.stream_complete = add_keep_alive(Ollama.stream_complete)  # type: ignore
 
                 self.llm = llm
 

private_gpt/components/llm/prompt_helper.py

@@ -40,7 +40,8 @@ class AbstractPromptStyle(abc.ABC):
         logger.debug("Got for messages='%s' the prompt='%s'", messages, prompt)
         return prompt
 
-    def completion_to_prompt(self, completion: str) -> str:
+    def completion_to_prompt(self, prompt: str) -> str:
+        completion = prompt  # Fix: Llama-index parameter has to be named as prompt
         prompt = self._completion_to_prompt(completion)
         logger.debug("Got for completion='%s' the prompt='%s'", completion, prompt)
         return prompt
@@ -285,8 +286,9 @@ class ChatMLPromptStyle(AbstractPromptStyle):
 
 
 def get_prompt_style(
-    prompt_style: Literal["default", "llama2", "llama3", "tag", "mistral", "chatml"]
-    | None
+    prompt_style: (
+        Literal["default", "llama2", "llama3", "tag", "mistral", "chatml"] | None
+    )
 ) -> AbstractPromptStyle:
     """Get the prompt style to use from the given string.
 

private_gpt/components/node_store/node_store_component.py

@@ -38,10 +38,10 @@ class NodeStoreComponent:
 
             case "postgres":
                 try:
-                    from llama_index.core.storage.docstore.postgres_docstore import (
+                    from llama_index.storage.docstore.postgres import (  # type: ignore
                         PostgresDocumentStore,
                     )
-                    from llama_index.core.storage.index_store.postgres_index_store import (
+                    from llama_index.storage.index_store.postgres import (  # type: ignore
                         PostgresIndexStore,
                     )
                 except ImportError:
@@ -55,6 +55,7 @@ class NodeStoreComponent:
                 self.index_store = PostgresIndexStore.from_params(
                     **settings.postgres.model_dump(exclude_none=True)
                 )
+
                 self.doc_store = PostgresDocumentStore.from_params(
                     **settings.postgres.model_dump(exclude_none=True)
                 )

private_gpt/components/vector_store/batched_chroma.py

@@ -1,14 +1,17 @@
-from collections.abc import Generator
-from typing import Any
+from collections.abc import Generator, Sequence
+from typing import TYPE_CHECKING, Any
 
 from llama_index.core.schema import BaseNode, MetadataMode
 from llama_index.core.vector_stores.utils import node_to_metadata_dict
 from llama_index.vector_stores.chroma import ChromaVectorStore  # type: ignore
 
+if TYPE_CHECKING:
+    from collections.abc import Mapping
+
 
 def chunk_list(
-    lst: list[BaseNode], max_chunk_size: int
-) -> Generator[list[BaseNode], None, None]:
+    lst: Sequence[BaseNode], max_chunk_size: int
+) -> Generator[Sequence[BaseNode], None, None]:
     """Yield successive max_chunk_size-sized chunks from lst.
 
     Args:
@@ -60,7 +63,7 @@ class BatchedChromaVectorStore(ChromaVectorStore):  # type: ignore
         )
         self.chroma_client = chroma_client
 
-    def add(self, nodes: list[BaseNode], **add_kwargs: Any) -> list[str]:
+    def add(self, nodes: Sequence[BaseNode], **add_kwargs: Any) -> list[str]:
         """Add nodes to index, batching the insertion to avoid issues.
 
         Args:
@@ -78,8 +81,8 @@ class BatchedChromaVectorStore(ChromaVectorStore):  # type: ignore
 
         all_ids = []
         for node_chunk in node_chunks:
-            embeddings = []
-            metadatas = []
+            embeddings: list[Sequence[float]] = []
+            metadatas: list[Mapping[str, Any]] = []
             ids = []
             documents = []
             for node in node_chunk:

private_gpt/server/chat/chat_service.py

@@ -1,4 +1,5 @@
 from dataclasses import dataclass
+from typing import TYPE_CHECKING
 
 from injector import inject, singleton
 from llama_index.core.chat_engine import ContextChatEngine, SimpleChatEngine
@@ -26,6 +27,9 @@ from private_gpt.open_ai.extensions.context_filter import ContextFilter
 from private_gpt.server.chunks.chunks_service import Chunk
 from private_gpt.settings.settings import Settings
 
+if TYPE_CHECKING:
+    from llama_index.core.postprocessor.types import BaseNodePostprocessor
+
 
 class Completion(BaseModel):
     response: str
@@ -114,12 +118,15 @@ class ChatService:
                 context_filter=context_filter,
                 similarity_top_k=self.settings.rag.similarity_top_k,
             )
-            node_postprocessors = [
+            node_postprocessors: list[BaseNodePostprocessor] = [
                 MetadataReplacementPostProcessor(target_metadata_key="window"),
+            ]
+            if settings.rag.similarity_value:
+                node_postprocessors.append(
                     SimilarityPostprocessor(
                         similarity_cutoff=settings.rag.similarity_value
-                ),
-            ]
+                    )
+                )
 
             if settings.rag.rerank.enabled:
                 rerank_postprocessor = SentenceTransformerRerank(

private_gpt/server/recipes/summarize/summarize_service.py

@@ -90,9 +90,9 @@ class SummarizeService:
         # Add context documents to summarize
         if use_context:
             # 1. Recover all ref docs
-            ref_docs: dict[
-                str, RefDocInfo
-            ] | None = self.storage_context.docstore.get_all_ref_doc_info()
+            ref_docs: dict[str, RefDocInfo] | None = (
+                self.storage_context.docstore.get_all_ref_doc_info()
+            )
             if ref_docs is None:
                 raise ValueError("No documents have been ingested yet.")
 

private_gpt/settings/settings.py

@@ -136,9 +136,8 @@ class LLMSettings(BaseModel):
         0.1,
         description="The temperature of the model. Increasing the temperature will make the model answer more creatively. A value of 0.1 would be more factual.",
     )
-    prompt_style: Literal[
-        "default", "llama2", "llama3", "tag", "mistral", "chatml"
-    ] = Field(
+    prompt_style: Literal["default", "llama2", "llama3", "tag", "mistral", "chatml"] = (
+        Field(
             "llama2",
             description=(
                 "The prompt style to use for the chat engine. "
@@ -150,6 +149,7 @@ class LLMSettings(BaseModel):
                 "`llama2` is the historic behaviour. `default` might work better with your custom models."
             ),
         )
+    )
 
 
 class VectorstoreSettings(BaseModel):
@@ -197,7 +197,14 @@ class HuggingFaceSettings(BaseModel):
 
 class EmbeddingSettings(BaseModel):
     mode: Literal[
-        "huggingface", "openai", "azopenai", "sagemaker", "ollama", "mock", "gemini"
+        "huggingface",
+        "openai",
+        "azopenai",
+        "sagemaker",
+        "ollama",
+        "mock",
+        "gemini",
+        "mistralai",
     ]
     ingest_mode: Literal["simple", "batch", "parallel", "pipeline"] = Field(
         "simple",
@@ -350,6 +357,10 @@ class AzureOpenAISettings(BaseModel):
 class UISettings(BaseModel):
     enabled: bool
     path: str
+    default_mode: Literal["RAG", "Search", "Basic", "Summarize"] = Field(
+        "RAG",
+        description="The default mode.",
+    )
     default_chat_system_prompt: str = Field(
         None,
         description="The default system prompt to use for the chat mode.",

private_gpt/ui/ui.py

@@ -1,4 +1,5 @@
 """This file should be imported if and only if you want to run the UI locally."""
+
 import base64
 import logging
 import time
@@ -99,8 +100,11 @@ class PrivateGptUi:
         self._selected_filename = None
 
         # Initialize system prompt based on default mode
-        self.mode = MODES[0]
-        self._system_prompt = self._get_default_system_prompt(self.mode)
+        default_mode_map = {mode.value: mode for mode in Modes}
+        self._default_mode = default_mode_map.get(
+            settings().ui.default_mode, Modes.RAG_MODE
+        )
+        self._system_prompt = self._get_default_system_prompt(self._default_mode)
 
     def _chat(
         self, message: str, history: list[list[str]], mode: Modes, *_: Any
@@ -390,7 +394,7 @@ class PrivateGptUi:
 
             with gr.Row(equal_height=False):
                 with gr.Column(scale=3):
-                    default_mode = MODES[0]
+                    default_mode = self._default_mode
                     mode = gr.Radio(
                         [mode.value for mode in MODES],
                         label="Mode",
@@ -519,6 +523,7 @@ class PrivateGptUi:
                             "llamacpp": config_settings.llamacpp.llm_hf_model_file,
                             "openai": config_settings.openai.model,
                             "openailike": config_settings.openai.model,
+                            "azopenai": config_settings.azopenai.llm_model,
                             "sagemaker": config_settings.sagemaker.llm_endpoint_name,
                             "mock": llm_mode,
                             "ollama": config_settings.ollama.llm_model,

private_gpt/utils/ollama.py

@@ -3,10 +3,13 @@ from collections import deque
 from collections.abc import Iterator, Mapping
 from typing import Any
 
+from httpx import ConnectError
 from tqdm import tqdm  # type: ignore
 
+from private_gpt.utils.retry import retry
+
 try:
-    from ollama import Client  # type: ignore
+    from ollama import Client, ResponseError  # type: ignore
 except ImportError as e:
     raise ImportError(
         "Ollama dependencies not found, install with `poetry install --extras llms-ollama or embeddings-ollama`"
@@ -14,13 +17,25 @@ except ImportError as e:
 
 logger = logging.getLogger(__name__)
 
+_MAX_RETRIES = 5
+_JITTER = (3.0, 10.0)
 
+
+@retry(
+    is_async=False,
+    exceptions=(ConnectError, ResponseError),
+    tries=_MAX_RETRIES,
+    jitter=_JITTER,
+    logger=logger,
+)
 def check_connection(client: Client) -> bool:
     try:
         client.list()
         return True
+    except (ConnectError, ResponseError) as e:
+        raise e
     except Exception as e:
-        logger.error(f"Failed to connect to Ollama: {e!s}")
+        logger.error(f"Failed to connect to Ollama: {type(e).__name__}: {e!s}")
         return False
 
 

private_gpt/utils/retry.py

@@ -0,0 +1,31 @@
+import logging
+from collections.abc import Callable
+from typing import Any
+
+from retry_async import retry as retry_untyped  # type: ignore
+
+retry_logger = logging.getLogger(__name__)
+
+
+def retry(
+    exceptions: Any = Exception,
+    *,
+    is_async: bool = False,
+    tries: int = -1,
+    delay: float = 0,
+    max_delay: float | None = None,
+    backoff: float = 1,
+    jitter: float | tuple[float, float] = 0,
+    logger: logging.Logger = retry_logger,
+) -> Callable[..., Any]:
+    wrapped = retry_untyped(
+        exceptions=exceptions,
+        is_async=is_async,
+        tries=tries,
+        delay=delay,
+        max_delay=max_delay,
+        backoff=backoff,
+        jitter=jitter,
+        logger=logger,
+    )
+    return wrapped  # type: ignore

pyproject.toml

@@ -1,88 +1,81 @@
 [tool.poetry]
 name = "private-gpt"
-version = "0.6.0"
+version = "0.6.2"
 description = "Private GPT"
 authors = ["Zylon <hi@zylon.ai>"]
 
 [tool.poetry.dependencies]
 python = ">=3.11,<3.12"
 # PrivateGPT
-fastapi = { extras = ["all"], version = "^0.111.0" }
-python-multipart = "^0.0.9"
-injector = "^0.21.0"
-pyyaml = "^6.0.1"
+fastapi = { extras = ["all"], version = "^0.115.0" }
+python-multipart = "^0.0.10"
+injector = "^0.22.0"
+pyyaml = "^6.0.2"
 watchdog = "^4.0.1"
-transformers = "^4.42.3"
+transformers = "^4.44.2"
 docx2txt = "^0.8"
 cryptography = "^3.1"
 # LlamaIndex core libs
-llama-index-core = "^0.10.52"
-llama-index-readers-file = "^0.1.27"
+llama-index-core = ">=0.11.2,<0.12.0"
+llama-index-readers-file = "*"
 # Optional LlamaIndex integration libs
-llama-index-llms-llama-cpp = {version = "^0.1.4", optional = true}
-llama-index-llms-openai = {version = "^0.1.25", optional = true}
-llama-index-llms-openai-like = {version ="^0.1.3", optional = true}
-llama-index-llms-ollama = {version ="^0.2.2", optional = true}
-llama-index-llms-azure-openai = {version ="^0.1.8", optional = true}
-llama-index-llms-gemini = {version ="^0.1.11", optional = true}
-llama-index-embeddings-ollama = {version ="^0.1.2", optional = true}
-llama-index-embeddings-huggingface = {version ="^0.2.2", optional = true}
-llama-index-embeddings-openai = {version ="^0.1.10", optional = true}
-llama-index-embeddings-azure-openai = {version ="^0.1.10", optional = true}
-llama-index-embeddings-gemini = {version ="^0.1.8", optional = true}
-llama-index-vector-stores-qdrant = {version ="^0.2.10", optional = true}
-llama-index-vector-stores-milvus = {version ="^0.1.20", optional = true}
-llama-index-vector-stores-chroma = {version ="^0.1.10", optional = true}
-llama-index-vector-stores-postgres = {version ="^0.1.11", optional = true}
-llama-index-vector-stores-clickhouse = {version ="^0.1.3", optional = true}
-llama-index-storage-docstore-postgres = {version ="^0.1.3", optional = true}
-llama-index-storage-index-store-postgres = {version ="^0.1.4", optional = true}
+llama-index-llms-llama-cpp = {version = "*", optional = true}
+llama-index-llms-openai = {version ="*", optional = true}
+llama-index-llms-openai-like = {version ="*", optional = true}
+llama-index-llms-ollama = {version ="*", optional = true}
+llama-index-llms-azure-openai = {version ="*", optional = true}
+llama-index-llms-gemini = {version ="*", optional = true}
+llama-index-embeddings-ollama = {version ="*", optional = true}
+llama-index-embeddings-huggingface = {version ="*", optional = true}
+llama-index-embeddings-openai = {version ="*", optional = true}
+llama-index-embeddings-azure-openai = {version ="*", optional = true}
+llama-index-embeddings-gemini = {version ="*", optional = true}
+llama-index-embeddings-mistralai = {version ="*", optional = true}
+llama-index-vector-stores-qdrant = {version ="*", optional = true}
+llama-index-vector-stores-milvus = {version ="*", optional = true}
+llama-index-vector-stores-chroma = {version ="*", optional = true}
+llama-index-vector-stores-postgres = {version ="*", optional = true}
+llama-index-vector-stores-clickhouse = {version ="*", optional = true}
+llama-index-storage-docstore-postgres = {version ="*", optional = true}
+llama-index-storage-index-store-postgres = {version ="*", optional = true}
 # Postgres
 psycopg2-binary = {version ="^2.9.9", optional = true}
 asyncpg = {version="^0.29.0", optional = true}
 
 # ClickHouse
-clickhouse-connect = {version = "^0.7.15", optional = true}
+clickhouse-connect = {version = "^0.7.19", optional = true}
 
 # Optional Sagemaker dependency
-boto3 = {version ="^1.34.139", optional = true}
-
-# Optional Qdrant client
-qdrant-client = {version ="^1.9.0", optional = true}
+boto3 = {version ="^1.35.26", optional = true}
 
 # Optional Reranker dependencies
-torch = {version ="^2.3.1", optional = true}
-sentence-transformers = {version ="^3.0.1", optional = true}
+torch = {version ="^2.4.1", optional = true}
+sentence-transformers = {version ="^3.1.1", optional = true}
 
 # Optional UI
-gradio = {version ="^4.37.2", optional = true}
-# Fix: https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/16289#issuecomment-2255106490
-ffmpy = {git = "https://github.com/EuDs63/ffmpy.git", rev = "333a19ee4d21f32537c0508aa1942ef1aa7afe24", optional = true}
-
-# Optional Google Gemini dependency
-google-generativeai = {version ="^0.5.4", optional = true}
-
-# Optional Ollama client
-ollama = {version ="^0.3.0", optional = true}
+gradio = {version ="^4.44.0", optional = true}
+ffmpy = {version ="^0.4.0", optional = true}
 
 # Optional HF Transformers
 einops = {version = "^0.8.0", optional = true}
+retry-async = "^0.1.4"
 
 [tool.poetry.extras]
 ui = ["gradio", "ffmpy"]
 llms-llama-cpp = ["llama-index-llms-llama-cpp"]
 llms-openai = ["llama-index-llms-openai"]
 llms-openai-like = ["llama-index-llms-openai-like"]
-llms-ollama = ["llama-index-llms-ollama", "ollama"]
+llms-ollama = ["llama-index-llms-ollama"]
 llms-sagemaker = ["boto3"]
 llms-azopenai = ["llama-index-llms-azure-openai"]
-llms-gemini = ["llama-index-llms-gemini", "google-generativeai"]
-embeddings-ollama = ["llama-index-embeddings-ollama", "ollama"]
+llms-gemini = ["llama-index-llms-gemini"]
+embeddings-ollama = ["llama-index-embeddings-ollama"]
 embeddings-huggingface = ["llama-index-embeddings-huggingface", "einops"]
 embeddings-openai = ["llama-index-embeddings-openai"]
 embeddings-sagemaker = ["boto3"]
 embeddings-azopenai = ["llama-index-embeddings-azure-openai"]
 embeddings-gemini = ["llama-index-embeddings-gemini"]
+embeddings-mistral = ["llama-index-embeddings-mistralai"]
 vector-stores-qdrant = ["llama-index-vector-stores-qdrant"]
 vector-stores-clickhouse = ["llama-index-vector-stores-clickhouse", "clickhouse_connect"]
 vector-stores-chroma = ["llama-index-vector-stores-chroma"]
@@ -92,14 +85,14 @@ storage-nodestore-postgres = ["llama-index-storage-docstore-postgres","llama-ind
 rerank-sentence-transformers = ["torch", "sentence-transformers"]
 
 [tool.poetry.group.dev.dependencies]
-black = "^22"
-mypy = "^1.2"
-pre-commit = "^2"
-pytest = "^7"
-pytest-cov = "^3"
+black = "^24"
+mypy = "^1.11"
+pre-commit = "^3"
+pytest = "^8"
+pytest-cov = "^5"
 ruff = "^0"
-pytest-asyncio = "^0.21.1"
-types-pyyaml = "^6.0.12.12"
+pytest-asyncio = "^0.24.0"
+types-pyyaml = "^6.0.12.20240917"
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]

settings.yaml

@@ -25,6 +25,8 @@ data:
 ui:
   enabled: true
   path: /
+  # "RAG", "Search", "Basic", or "Summarize"
+  default_mode: "RAG"
   default_chat_system_prompt: >
     You are a helpful, respectful and honest assistant.
     Always answer as helpfully as possible and follow ALL given instructions.

tests/fixtures/fast_api_test_client.py

@@ -5,7 +5,7 @@ from private_gpt.launcher import create_app
 from tests.fixtures.mock_injector import MockInjector
 
 
-@pytest.fixture()
+@pytest.fixture
 def test_client(request: pytest.FixtureRequest, injector: MockInjector) -> TestClient:
     if request is not None and hasattr(request, "param"):
         injector.bind_settings(request.param or {})

tests/fixtures/ingest_helper.py

@@ -19,6 +19,6 @@ class IngestHelper:
         return ingest_result
 
 
-@pytest.fixture()
+@pytest.fixture
 def ingest_helper(test_client: TestClient) -> IngestHelper:
     return IngestHelper(test_client)

tests/fixtures/mock_injector.py

@@ -37,6 +37,6 @@ class MockInjector:
         return self.test_injector.get(interface)
 
 
-@pytest.fixture()
+@pytest.fixture
 def injector() -> MockInjector:
     return MockInjector()

tests/server/ingest/test_local_ingest.py

@@ -6,7 +6,7 @@ import pytest
 from fastapi.testclient import TestClient
 
 
-@pytest.fixture()
+@pytest.fixture
 def file_path() -> str:
     return "test.txt"
 

version.txt

@@ -1 +1 @@
-0.6.0
+0.6.2