Merge remote-tracking branch 'origin/main' into j_main

Author: jaluma

.github/workflows/actions/install_dependencies/action.yml

@@ -8,7 +8,7 @@ inputs:
   poetry_version:
     required: true
     type: string
-    default: "1.5.1"
+    default: "1.8.3"
 
 runs:
   using: composite

Dockerfile.external

@@ -3,7 +3,7 @@ FROM python:3.11.6-slim-bookworm as base
 # Install poetry
 RUN pip install pipx
 RUN python3 -m pipx ensurepath
-RUN pipx install poetry
+RUN pipx install poetry==1.8.3
 ENV PATH="/root/.local/bin:$PATH"
 ENV PATH=".venv/bin/:$PATH"
 
@@ -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 mkdir models; chown worker models
+RUN chown worker /home/worker/app
+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 *.md ./
+COPY --chown=worker *.yaml .
 COPY --chown=worker scripts/ scripts
 
-ENV PYTHONPATH="$PYTHONPATH:/private_gpt/"
-
 USER worker
-ENTRYPOINT python -m private_gpt
+ENTRYPOINT python -m private_gpt

Dockerfile.local

@@ -5,7 +5,7 @@ FROM python:3.11.6-slim-bookworm as base
 # Install poetry
 RUN pip install pipx
 RUN python3 -m pipx ensurepath
-RUN pipx install poetry
+RUN pipx install poetry==1.8.3
 ENV PATH="/root/.local/bin:$PATH"
 ENV PATH=".venv/bin/:$PATH"
 
@@ -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
-RUN adduser --system --ingroup worker 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 mkdir models; chown worker models
+RUN chown worker /home/worker/app
+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 *.md ./
+COPY --chown=worker *.yaml ./
 COPY --chown=worker scripts/ scripts
 
-ENV PYTHONPATH="$PYTHONPATH:/private_gpt/"
-
 USER worker
 ENTRYPOINT python -m private_gpt

README.md

@@ -2,21 +2,21 @@
 
 [![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/)
-
 [![Discord](https://img.shields.io/discord/1164200432894234644?logo=discord&label=PrivateGPT)](https://discord.gg/bK6mRVpErU)
 [![X (formerly Twitter) Follow](https://img.shields.io/twitter/follow/ZylonPrivateGPT)](https://twitter.com/ZylonPrivateGPT)
 
-
-> Install & usage docs: https://docs.privategpt.dev/
-> 
-> Join the community: [Twitter](https://twitter.com/ZylonPrivateGPT) & [Discord](https://discord.gg/bK6mRVpErU)
-
 ![Gradio UI](/fern/docs/assets/ui.png?raw=true)
 
 PrivateGPT is a production-ready AI project that allows you to ask questions about your documents using the power
 of Large Language Models (LLMs), even in scenarios without an Internet connection. 100% private, no data leaves your
 execution environment at any point.
 
+>[!TIP]
+> If you are looking for an **enterprise-ready, fully private AI workspace**
+> check out [Zylon's website](https://zylon.ai)  or [request a demo](https://cal.com/zylon/demo?source=pgpt-readme).
+> Crafted by the team behind PrivateGPT, Zylon is a best-in-class AI collaborative
+> workspace that can be easily deployed on-premise (data center, bare metal...) or in your private cloud (AWS, GCP, Azure...).
+
 The project provides an API offering all the primitives required to build private, context-aware AI applications.
 It follows and extends the [OpenAI API standard](https://openai.com/blog/openai-api),
 and supports both normal and streaming responses.
@@ -38,13 +38,10 @@ In addition to this, a working [Gradio UI](https://www.gradio.app/)
 client is provided to test the API, together with a set of useful tools such as bulk model
 download script, ingestion script, documents folder watch, etc.
 
-> 👂 **Need help applying PrivateGPT to your specific use case?**
-> [Let us know more about it](https://forms.gle/4cSDmH13RZBHV9at7)
-> and we'll try to help! We are refining PrivateGPT through your feedback.
-
 ## 🎞️ Overview
-DISCLAIMER: This README is not updated as frequently as the [documentation](https://docs.privategpt.dev/).
-Please check it out for the latest updates!
+>[!WARNING]
+>  This README is not updated as frequently as the [documentation](https://docs.privategpt.dev/).
+>  Please check it out for the latest updates!
 
 ### Motivation behind PrivateGPT
 Generative AI is a game changer for our society, but adoption in companies of all sizes and data-sensitive

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

fern/docs.yml

@@ -74,14 +74,16 @@ navigation:
             path: ./docs/pages/ui/gradio.mdx
           - page: Alternatives
             path: ./docs/pages/ui/alternatives.mdx
-  # Small code snippet or example of usage to help users
   - tab: recipes
     layout:
-      - section: Choice of LLM
+      - section: Getting started
+        contents:
+          - page: Quickstart
+            path: ./docs/pages/recipes/quickstart.mdx
+      - section: General use cases
         contents:
-          # TODO: add recipes
-          - page: List of LLMs
-            path: ./docs/pages/recipes/list-llm.mdx
+          - page: Summarize
+            path: ./docs/pages/recipes/summarize.mdx
   # More advanced usage of PrivateGPT, by API
   - tab: api-reference
     layout:

fern/docs/assets/ui.png

@@ -28,6 +28,11 @@ pyenv local 3.11
 Install [Poetry](https://python-poetry.org/docs/#installing-with-the-official-installer) for dependency management:
 Follow the instructions on the official Poetry website to install it.
 
+<Callout intent="warning">
+A bug exists in Poetry versions 1.7.0 and earlier. We strongly recommend upgrading to a tested version.
+To upgrade Poetry to latest tested version, run `poetry self update 1.8.3` after installing it.
+</Callout>
+
 ### 4. Optional: Install `make`
 To run various scripts, you need to install `make`. Follow the instructions for your operating system:
 #### macOS
@@ -130,16 +135,20 @@ Go to [ollama.ai](https://ollama.ai/) and follow the instructions to install Oll
 
 After the installation, make sure the Ollama desktop app is closed.
 
-Install the models to be used, the default settings-ollama.yaml is configured to user `mistral 7b` LLM (~4GB) and `nomic-embed-text` Embeddings (~275MB). Therefore:
-
+Now, start Ollama service (it will start a local inference server, serving both the LLM and the Embeddings):
 ```bash
-ollama pull mistral
-ollama pull nomic-embed-text
+ollama serve
 ```
 
-Now, start Ollama service (it will start a local inference server, serving both the LLM and the Embeddings):
+Install the models to be used, the default settings-ollama.yaml is configured to user llama3.1 8b LLM (~4GB) and nomic-embed-text Embeddings (~275MB)
+
+By default, PGPT will automatically pull models as needed. This behavior can be changed by modifying the `ollama.autopull_models` property.
+
+In any case, if you want to manually pull models, run the following commands:
+
 ```bash
-ollama serve
+ollama pull llama3.1
+ollama pull nomic-embed-text
 ```
 
 Once done, on a different terminal, you can install PrivateGPT with the following command:

fern/docs/pages/installation/installation.mdx

@@ -24,8 +24,26 @@ PrivateGPT uses the `AutoTokenizer` library to tokenize input text accurately. I
    In your `settings.yaml` file, specify the model you want to use:
    ```yaml
    llm:
-     tokenizer: mistralai/Mistral-7B-Instruct-v0.2
+     tokenizer: meta-llama/Meta-Llama-3.1-8B-Instruct
    ```
 2. **Set Access Token for Gated Models:**
    If you are using a gated model, ensure the `access_token` is set as mentioned in the previous section.
-This configuration ensures that PrivateGPT can download and use the correct tokenizer for the model you are working with.
+This configuration ensures that PrivateGPT can download and use the correct tokenizer for the model you are working with.
+
+# Embedding dimensions mismatch
+If you encounter an error message like `Embedding dimensions mismatch`, it is likely due to the embedding model and
+current vector dimension mismatch. To resolve this issue, ensure that the model and the input data have the same vector dimensions.
+
+By default, PrivateGPT uses `nomic-embed-text` embeddings, which have a vector dimension of 768.
+If you are using a different embedding model, ensure that the vector dimensions match the model's output.
+
+<Callout intent = "warning">
+In versions below to 0.6.0, the default embedding model was `BAAI/bge-small-en-v1.5` in `huggingface` setup.
+If you plan to reuse the old generated embeddings, you need to update the `settings.yaml` file to use the correct embedding model:
+```yaml
+huggingface:
+  embedding_hf_model_name: BAAI/bge-small-en-v1.5
+embedding:
+  embed_dim: 384
+```
+</Callout>

fern/docs/pages/installation/troubleshooting.mdx

@@ -8,6 +8,14 @@ The ingestion of documents can be done in different ways:
 
 ## Bulk Local Ingestion
 
+You will need to activate `data.local_ingestion.enabled` in your setting file to use this feature. Additionally,
+it is probably a good idea to set `data.local_ingestion.allow_ingest_from` to specify which folders are allowed to be ingested.
+
+<Callout intent = "warning">
+Be careful enabling this feature in a production environment, as it can be a security risk, as it allows users to
+ingest any local file with permissions.
+</Callout>
+
 When you are running PrivateGPT in a fully local setup, you can ingest a complete folder for convenience (containing
 pdf, text files, etc.)
 and optionally watch changes on it with the command: