Separate local mode into llms-llama-cpp and embeddings-huggingface for clarity

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

@@ -25,6 +25,6 @@ runs:
         python-version: ${{ inputs.python_version }}
         cache: "poetry"
     - name: Install Dependencies
-      run: poetry install --extras "ui qdrant" --no-root
+      run: poetry install --extras "ui vector-stores-qdrant" --no-root
       shell: bash
 

Dockerfile.external

@@ -14,7 +14,7 @@ FROM base as dependencies
 WORKDIR /home/worker/app
 COPY pyproject.toml poetry.lock ./
 
-RUN poetry install --extras "ui qdrant"
+RUN poetry install --extras "ui vector-stores-qdrant"
 
 FROM base as app
 

Dockerfile.local

@@ -24,7 +24,7 @@ FROM base as dependencies
 WORKDIR /home/worker/app
 COPY pyproject.toml poetry.lock ./
 
-RUN poetry install --extras "ui local qdrant"
+RUN poetry install --extras "ui embeddings-huggingface llms-llama-cpp vector-stores-qdrant"
 
 FROM base as app
 

fern/docs/pages/installation/concepts.mdx

@@ -17,7 +17,10 @@ There is an extra component that can be enabled or disabled: the UI. It is a Gra
 ### Setups and Dependencies
 Your setup will be the combination of the different options available. You'll find recommended setups in the [installation](/installation) section.
 PrivateGPT uses poetry to manage its dependencies. You can install the dependencies for the different setups by running `poetry install --extras "<extra1> <extra2>..."`.
-Extras are the different options available for each component. For example, to install the dependencies for a local setup with UI and qdrant as vector database, you would run `poetry install --extras "ui local qdrant"`.
+Extras are the different options available for each component. For example, to install the dependencies for a a local setup with UI and qdrant as vector database, Ollama as LLM and HuggingFace as local embeddings, you would run
+
+`poetry install --extras "ui vector-stores-qdrant llms-ollama embeddings-huggingface"`.
+
 Refer to the [installation](/installation) section for more details.
 
 ### Setups and Configuration
@@ -35,9 +38,9 @@ will load the configuration from `settings.yaml` and `settings-ollama.yaml`.
 ## About Fully Local Setups
 In order to run PrivateGPT in a fully local setup, you will need to run the LLM, Embeddings and Vector Store locally.
 ### Vector stores
-The 3 vector stores supported (Qdrant, ChromaDB and Postgres) run locally by default.
+The vector stores supported (Qdrant, ChromaDB and Postgres) run locally by default.
 ### Embeddings
-For local embeddings you need to install the 'local' extra dependencies. It will use Huggingface Embeddings.
+For local embeddings you need to install the 'embeddings-huggingface' extra dependencies. It will use Huggingface Embeddings.
 
 Note: Ollama will support Embeddings in the short term for easier installation, but it doesn't as of today.
 
@@ -48,7 +51,7 @@ poetry run python scripts/setup
 ### LLM
 For local LLM there are two options:
 * (Recommended) You can use the 'ollama' option in PrivateGPT, which will connect to your local Ollama instance. Ollama simplifies a lot the installation of local LLMs.
-* You can use the 'local' option in PrivateGPT, which will use LlamaCPP. It works great on Mac with Metal most of the times (leverages Metal GPU), but it can be tricky in certain Linux and Windows distributions, depending on the GPU. In the installation document you'll find guides and troubleshooting.
+* You can use the 'llms-llama-cpp' option in PrivateGPT, which will use LlamaCPP. It works great on Mac with Metal most of the times (leverages Metal GPU), but it can be tricky in certain Linux and Windows distributions, depending on the GPU. In the installation document you'll find guides and troubleshooting.
 
 In order for local LLM to work (the second option), you need to download the embeddings model to the `models` folder. You can do so by running the `setup` script:
 ```bash

fern/docs/pages/installation/installation.mdx

@@ -30,8 +30,8 @@ pyenv local 3.11
 PrivateGPT allows to customize the setup -from fully local to cloud based- by deciding the modules to use.
 Here are the different options available:
 
-- LLM: "local" (uses LlamaCPP), "ollama", "sagemaker", "openai", "openailike"
-- Embeddings: "local" (uses HuggingFace embeddings), "openai", "sagemaker"
+- LLM: "llama-cpp", "ollama", "sagemaker", "openai", "openailike"
+- Embeddings: "huggingface", "openai", "sagemaker"
 - Vector stores: "qdrant", "chroma", "postgres"
 - UI: whether or not to enable UI (Gradio) or just go with the API
 
@@ -44,14 +44,17 @@ poetry install --extras "<extra1> <extra2>..."
 Where `<extra>` can be any of the following:
 
 - ui: adds support for UI using Gradio
-- local: adds support for local LLM and Embeddings using LlamaCPP - expect a messy installation process on some platforms
-- openai: adds support for OpenAI LLM and Embeddings, requires OpenAI API key
-- sagemaker: adds support for Amazon Sagemaker LLM and Embeddings, requires Sagemaker endpoints
-- ollama: adds support for Ollama LLM, the easiest way to get a local LLM running
-- openai-like: adds support for 3rd party LLM providers that are compatible with OpenAI's API
-- qdrant: adds support for Qdrant vector store
-- chroma: adds support for Chroma DB vector store
-- postgres: adds support for Postgres vector store
+- llms-ollama: adds support for Ollama LLM, the easiest way to get a local LLM running
+- llms-llama-cpp: adds support for local LLM using LlamaCPP - expect a messy installation process on some platforms
+- llms-sagemaker: adds support for Amazon Sagemaker LLM, requires Sagemaker inference endpoints
+- llms-openai: adds support for OpenAI LLM, requires OpenAI API key
+- llms-openai-like: adds support for 3rd party LLM providers that are compatible with OpenAI's API
+- embeddings-huggingface: adds support for local Embeddings using HuggingFace
+- embeddings-sagemaker: adds support for Amazon Sagemaker Embeddings, requires Sagemaker inference endpoints
+- embeddings-openai = adds support for OpenAI Embeddings, requires OpenAI API key
+- vector-stores-qdrant: adds support for Qdrant vector store
+- vector-stores-chroma: adds support for Chroma DB vector store
+- vector-stores-postgres: adds support for Postgres vector store
 
 ## Recommended Setups
 
@@ -66,10 +69,10 @@ Go to [ollama.ai](https://ollama.ai/) and follow the instructions to install Oll
 
 Once done, you can install PrivateGPT with the following command:
 ```bash
-poetry install --extras "ui local ollama qdrant"
+poetry install --extras "ui llms-ollama embeddings-huggingface vector-stores-qdrant"
 ```
 
-We are installing "local" dependency to support local embeddings, because Ollama doesn't support embeddings just yet. But they working on it!
+We are installing "embeddings-huggingface" dependency to support local embeddings, because Ollama doesn't support embeddings just yet. But they working on it!
 In order for local embeddings to work, you need to download the embeddings model to the `models` folder. You can do so by running the `setup` script:
 ```bash
 poetry run python scripts/setup
@@ -95,7 +98,7 @@ Edit the `settings-sagemaker.yaml` file to include the correct Sagemaker endpoin
 
 Then, install PrivateGPT with the following command:
 ```bash
-poetry install --extras "ui sagemaker qdrant"
+poetry install --extras "ui llms-sagemaker embeddings-sagemaker vector-stores-qdrant"
 ```
 
 Once installed, you can run PrivateGPT. Make sure you have a working Ollama running locally before running the following command.
@@ -113,7 +116,7 @@ The UI will be available at http://localhost:8001
 If you want to run PrivateGPT fully locally without relying on Ollama, you can run the following command:
 
 ```bash
-poetry install --extras "ui local qdrant"
+poetry install --extras "ui llms-llama-cpp embeddings-huggingface vector-stores-qdrant"
 ```
 
 In order for local LLM and embeddings to work, you need to download the models to the `models` folder. You can do so by running the `setup` script:
@@ -127,7 +130,53 @@ Once installed, you can run PrivateGPT with the following command:
 PGPT_PROFILES=local make run
 ```
 
-PrivateGPT will load the already existing `settings-local.yaml` file, which is already configured to use LlamaCPP and Qdrant.
+PrivateGPT will load the already existing `settings-local.yaml` file, which is already configured to use LlamaCPP LLM, HuggingFace embeddings and Qdrant.
+
+The UI will be available at http://localhost:8001
+
+### Non-Private, OpenAI-powered test setup
+
+If you want to test PrivateGPT with OpenAI's LLM and Embeddings -taking into account your data is going to OpenAI!- you can run the following command:
+
+You need an OPENAI API key to run this setup.
+
+Edit the `settings-openai.yaml` file to include the correct API KEY. Never commit it! It's a secret! As an alternative to editing `settings-openai.yaml`, you can just set the env var OPENAI_API_KEY.
+
+Then, install PrivateGPT with the following command:
+```bash
+poetry install --extras "ui llms-openai embeddings-openai vector-stores-qdrant"
+```
+
+Once installed, you can run PrivateGPT.
+
+```bash
+PGPT_PROFILES=openai make run
+```
+
+PrivateGPT will use the already existing `settings-openai.yaml` settings file, which is already configured to use OpenAI LLM and Embeddings endpoints, and Qdrant.
+
+The UI will be available at http://localhost:8001
+
+### Local, Llama-CPP powered setup
+
+If you want to run PrivateGPT fully locally without relying on Ollama, you can run the following command:
+
+```bash
+poetry install --extras "ui llms-llama-cpp embeddings-huggingface vector-stores-qdrant"
+```
+
+In order for local LLM and embeddings to work, you need to download the models to the `models` folder. You can do so by running the `setup` script:
+```bash
+poetry run python scripts/setup
+```
+
+Once installed, you can run PrivateGPT with the following command:
+
+```bash
+PGPT_PROFILES=local make run
+```
+
+PrivateGPT will load the already existing `settings-local.yaml` file, which is already configured to use LlamaCPP LLM, HuggingFace embeddings and Qdrant.
 
 The UI will be available at http://localhost:8001
 

poetry.lock

@@ -5895,17 +5895,20 @@ docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.link
 testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-ignore-flaky", "pytest-mypy (>=0.9.1)", "pytest-ruff"]
 
 [extras]
-chroma = ["llama-index-vector-stores-chroma"]
-local = ["llama-index-embeddings-huggingface", "llama-index-llms-llama-cpp"]
-ollama = ["llama-index-llms-ollama"]
-openai = ["llama-index-embeddings-openai", "llama-index-llms-openai"]
-openai-like = ["llama-index-llms-openai-like"]
-postgres = ["llama-index-vector-stores-postgres"]
-qdrant = ["llama-index-vector-stores-qdrant"]
-sagemaker = ["boto3"]
+embeddings-huggingface = ["llama-index-embeddings-huggingface"]
+embeddings-openai = ["llama-index-embeddings-openai"]
+embeddings-sagemaker = ["boto3"]
+llms-llama-cpp = ["llama-index-llms-llama-cpp"]
+llms-ollama = ["llama-index-llms-ollama"]
+llms-openai = ["llama-index-llms-openai"]
+llms-openai-like = ["llama-index-llms-openai-like"]
+llms-sagemaker = ["boto3"]
 ui = ["gradio"]
+vector-stores-chroma = ["llama-index-vector-stores-chroma"]
+vector-stores-postgres = ["llama-index-vector-stores-postgres"]
+vector-stores-qdrant = ["llama-index-vector-stores-qdrant"]
 
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.11,<3.12"
-content-hash = "c2e3a4c948a9a49cc11ea085a20dc82b73dc0516fefa11ee941389b6f1ca1f3e"
+content-hash = "0249c25c783180d0c483c533d9102e3885e4a4f5261dc331a41323bd79d446f3"

private_gpt/components/embedding/embedding_component.py

@@ -18,18 +18,18 @@ class EmbeddingComponent:
         embedding_mode = settings.embedding.mode
         logger.info("Initializing the embedding model in mode=%s", embedding_mode)
         match embedding_mode:
-            case "local":
+            case "huggingface":
                 try:
                     from llama_index.embeddings.huggingface import (  # type: ignore
                         HuggingFaceEmbedding,
                     )
                 except ImportError as e:
                     raise ImportError(
-                        "Local dependencies not found, install with `poetry install --extras local`"
+                        "Local dependencies not found, install with `poetry install --extras embeddings-huggingface`"
                     ) from e
 
                 self.embedding_model = HuggingFaceEmbedding(
-                    model_name=settings.local.embedding_hf_model_name,
+                    model_name=settings.huggingface.embedding_hf_model_name,
                     cache_folder=str(models_cache_path),
                 )
             case "sagemaker":
@@ -39,7 +39,7 @@ class EmbeddingComponent:
                     )
                 except ImportError as e:
                     raise ImportError(
-                        "Sagemaker dependencies not found, install with `poetry install --extras sagemaker`"
+                        "Sagemaker dependencies not found, install with `poetry install --extras embeddings-sagemaker`"
                     ) from e
 
                 self.embedding_model = SagemakerEmbedding(
@@ -52,7 +52,7 @@ class EmbeddingComponent:
                     )
                 except ImportError as e:
                     raise ImportError(
-                        "OpenAI dependencies not found, install with `poetry install --extras openai`"
+                        "OpenAI dependencies not found, install with `poetry install --extras embeddings-openai`"
                     ) from e
 
                 openai_settings = settings.openai.api_key

private_gpt/components/llm/custom/sagemaker.py

@@ -7,26 +7,20 @@ import logging
 from typing import TYPE_CHECKING, Any
 
 import boto3  # type: ignore
-from llama_index.bridge.pydantic import Field
-from llama_index.llms import (
+from llama_index.core.base.llms.generic_utils import (
+    completion_response_to_chat_response,
+    stream_completion_response_to_chat_response,
+)
+from llama_index.core.bridge.pydantic import Field
+from llama_index.core.llms import (
     CompletionResponse,
     CustomLLM,
     LLMMetadata,
 )
-from llama_index.llms.base import (
+from llama_index.core.llms.callbacks import (
     llm_chat_callback,
     llm_completion_callback,
 )
-from llama_index.llms.generic_utils import (
-    completion_response_to_chat_response,
-    stream_completion_response_to_chat_response,
-)
-from llama_index.llms.llama_utils import (
-    completion_to_prompt as generic_completion_to_prompt,
-)
-from llama_index.llms.llama_utils import (
-    messages_to_prompt as generic_messages_to_prompt,
-)
 
 if TYPE_CHECKING:
     from collections.abc import Sequence
@@ -161,8 +155,8 @@ class SagemakerLLM(CustomLLM):
         model_kwargs = model_kwargs or {}
         model_kwargs.update({"n_ctx": context_window, "verbose": verbose})
 
-        messages_to_prompt = messages_to_prompt or generic_messages_to_prompt
-        completion_to_prompt = completion_to_prompt or generic_completion_to_prompt
+        messages_to_prompt = messages_to_prompt or {}
+        completion_to_prompt = completion_to_prompt or {}
 
         generate_kwargs = generate_kwargs or {}
         generate_kwargs.update(

private_gpt/components/llm/llm_component.py

@@ -30,18 +30,18 @@ class LLMComponent:
 
         logger.info("Initializing the LLM in mode=%s", llm_mode)
         match settings.llm.mode:
-            case "local":
+            case "llamacpp":
                 try:
                     from llama_index.llms.llama_cpp import LlamaCPP  # type: ignore
                 except ImportError as e:
                     raise ImportError(
-                        "Local dependencies not found, install with `poetry install --extras local`"
+                        "Local dependencies not found, install with `poetry install --extras llms-llama-cpp`"
                     ) from e
 
-                prompt_style = get_prompt_style(settings.local.prompt_style)
+                prompt_style = get_prompt_style(settings.llamacpp.prompt_style)
 
                 self.llm = LlamaCPP(
-                    model_path=str(models_path / settings.local.llm_hf_model_file),
+                    model_path=str(models_path / settings.llamacpp.llm_hf_model_file),
                     temperature=0.1,
                     max_new_tokens=settings.llm.max_new_tokens,
                     context_window=settings.llm.context_window,
@@ -60,7 +60,7 @@ class LLMComponent:
                     from private_gpt.components.llm.custom.sagemaker import SagemakerLLM
                 except ImportError as e:
                     raise ImportError(
-                        "Sagemaker dependencies not found, install with `poetry install --extras sagemaker`"
+                        "Sagemaker dependencies not found, install with `poetry install --extras llms-sagemaker`"
                     ) from e
 
                 self.llm = SagemakerLLM(
@@ -73,7 +73,7 @@ class LLMComponent:
                     from llama_index.llms.openai import OpenAI  # type: ignore
                 except ImportError as e:
                     raise ImportError(
-                        "OpenAI dependencies not found, install with `poetry install --extras openai`"
+                        "OpenAI dependencies not found, install with `poetry install --extras llms-openai`"
                     ) from e
 
                 openai_settings = settings.openai
@@ -87,7 +87,7 @@ class LLMComponent:
                     from llama_index.llms.openai_like import OpenAILike  # type: ignore
                 except ImportError as e:
                     raise ImportError(
-                        "OpenAILike dependencies not found, install with `poetry install --extras openailike`"
+                        "OpenAILike dependencies not found, install with `poetry install --extras llms-openailike`"
                     ) from e
 
                 openai_settings = settings.openai
@@ -104,7 +104,7 @@ class LLMComponent:
                     from llama_index.llms.ollama import Ollama  # type: ignore
                 except ImportError as e:
                     raise ImportError(
-                        "Ollama dependencies not found, install with `poetry install --extras ollama`"
+                        "Ollama dependencies not found, install with `poetry install --extras llms-ollama`"
                     ) from e
 
                 ollama_settings = settings.ollama

private_gpt/components/vector_store/vector_store_component.py

@@ -45,7 +45,7 @@ class VectorStoreComponent:
                     )
                 except ImportError as e:
                     raise ImportError(
-                        "Postgres dependencies not found, install with `poetry install --extras postgres`"
+                        "Postgres dependencies not found, install with `poetry install --extras vector-stores-postgres`"
                     ) from e
 
                 if settings.pgvector is None:
@@ -72,7 +72,7 @@ class VectorStoreComponent:
                     )
                 except ImportError as e:
                     raise ImportError(
-                        "ChromaDB dependencies not found, install with `poetry install --extras chroma`"
+                        "ChromaDB dependencies not found, install with `poetry install --extras vector-stores-chroma`"
                     ) from e
 
                 chroma_settings = ChromaSettings(anonymized_telemetry=False)
@@ -99,7 +99,7 @@ class VectorStoreComponent:
                     from qdrant_client import QdrantClient
                 except ImportError as e:
                     raise ImportError(
-                        "Qdrant dependencies not found, install with `poetry install --extras qdrant`"
+                        "Qdrant dependencies not found, install with `poetry install --extras vector-stores-qdrant`"
                     ) from e
 
                 if settings.qdrant is None:

private_gpt/settings/settings.py

@@ -81,7 +81,7 @@ class DataSettings(BaseModel):
 
 
 class LLMSettings(BaseModel):
-    mode: Literal["local", "openai", "openailike", "sagemaker", "mock", "ollama"]
+    mode: Literal["llamacpp", "openai", "openailike", "sagemaker", "mock", "ollama"]
     max_new_tokens: int = Field(
         256,
         description="The maximum number of token that the LLM is authorized to generate in one completion.",
@@ -104,12 +104,9 @@ class VectorstoreSettings(BaseModel):
     database: Literal["chroma", "qdrant", "pgvector"]
 
 
-class LocalSettings(BaseModel):
+class LlamaCPPSettings(BaseModel):
     llm_hf_repo_id: str
     llm_hf_model_file: str
-    embedding_hf_model_name: str = Field(
-        description="Name of the HuggingFace model to use for embeddings"
-    )
     prompt_style: Literal["default", "llama2", "tag", "mistral", "chatml"] = Field(
         "llama2",
         description=(
@@ -123,8 +120,14 @@ class LocalSettings(BaseModel):
     )
 
 
+class HuggingFaceSettings(BaseModel):
+    embedding_hf_model_name: str = Field(
+        description="Name of the HuggingFace model to use for embeddings"
+    )
+
+
 class EmbeddingSettings(BaseModel):
-    mode: Literal["local", "openai", "sagemaker", "mock"]
+    mode: Literal["huggingface", "openai", "sagemaker", "mock"]
     ingest_mode: Literal["simple", "batch", "parallel"] = Field(
         "simple",
         description=(
@@ -292,7 +295,8 @@ class Settings(BaseModel):
     ui: UISettings
     llm: LLMSettings
     embedding: EmbeddingSettings
-    local: LocalSettings
+    llamacpp: LlamaCPPSettings
+    huggingface: HuggingFaceSettings
     sagemaker: SagemakerSettings
     openai: OpenAISettings
     ollama: OllamaSettings

pyproject.toml

@@ -33,14 +33,17 @@ gradio = {version ="^4.19.2", optional = true}
 
 [tool.poetry.extras]
 ui = ["gradio"]
-local = ["llama-index-llms-llama-cpp", "llama-index-embeddings-huggingface"]
-openai = ["llama-index-llms-openai", "llama-index-embeddings-openai"]
-openai-like = ["llama-index-llms-openai-like"]
-ollama = ["llama-index-llms-ollama"]
-sagemaker = ["boto3"]
-qdrant = ["llama-index-vector-stores-qdrant"]
-chroma = ["llama-index-vector-stores-chroma"]
-postgres = ["llama-index-vector-stores-postgres"]
+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"]
+llms-sagemaker = ["boto3"]
+embeddings-huggingface = ["llama-index-embeddings-huggingface"]
+embeddings-openai = ["llama-index-embeddings-openai"]
+embeddings-sagemaker = ["boto3"]
+vector-stores-qdrant = ["llama-index-vector-stores-qdrant"]
+vector-stores-chroma = ["llama-index-vector-stores-chroma"]
+vector-stores-postgres = ["llama-index-vector-stores-postgres"]
 
 
 [tool.poetry.group.dev.dependencies]

settings-docker.yaml

@@ -8,9 +8,11 @@ llm:
 embedding:
   mode: ${PGPT_MODE:sagemaker}
 
-local:
+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:

settings-local.yaml

@@ -2,23 +2,25 @@ server:
   env_name: ${APP_ENV:local}
 
 llm:
-  mode: local
+  mode: llamacpp
   # Should be matching the selected model
   max_new_tokens: 512
   context_window: 3900
   tokenizer: mistralai/Mistral-7B-Instruct-v0.2
 
+llamacpp:
+  prompt_style: "mistral"
+  llm_hf_repo_id: TheBloke/Mistral-7B-Instruct-v0.2-GGUF
+  llm_hf_model_file: mistral-7b-instruct-v0.2.Q4_K_M.gguf
+
 embedding:
-  mode: local
+  mode: huggingface
+
+huggingface:
+  embedding_hf_model_name: BAAI/bge-small-en-v1.5
 
 vectorstore:
   database: qdrant
 
 qdrant:
-  path: local_data/private_gpt/qdrant
-
-local:
-  prompt_style: "mistral"
-  llm_hf_repo_id: TheBloke/Mistral-7B-Instruct-v0.2-GGUF
-  llm_hf_model_file: mistral-7b-instruct-v0.2.Q4_K_M.gguf
-  embedding_hf_model_name: BAAI/bge-small-en-v1.5
+  path: local_data/private_gpt/qdrant

settings-mock.yaml

@@ -4,5 +4,6 @@ server:
 # This configuration allows you to use GPU for creating embeddings while avoiding loading LLM into vRAM
 llm:
   mode: mock
+
 embedding:
-  mode: local
+  mode: huggingface

settings-ollama.yaml

@@ -11,7 +11,10 @@ ollama:
   api_base: http://localhost:11434
 
 embedding:
-  mode: local
+  mode: huggingface
+
+huggingface:
+  embedding_hf_model_name: BAAI/bge-small-en-v1.5
 
 vectorstore:
   database: qdrant
@@ -19,6 +22,3 @@ vectorstore:
 qdrant:
   path: local_data/private_gpt/qdrant
 
-local:
-  prompt_style: "llama2"
-  embedding_hf_model_name: BAAI/bge-small-en-v1.5

settings-openai.yaml

@@ -0,0 +1,12 @@
+server:
+  env_name: ${APP_ENV:openai}
+
+llm:
+  mode: openai
+
+embedding:
+  mode: openai
+
+openai:
+  api_key: ${OPENAI_API_KEY:}
+  model: gpt-3.5-turbo

settings-sagemaker.yaml

@@ -1,5 +1,5 @@
 server:
-  env_name: ${APP_ENV:prod}
+  env_name: ${APP_ENV:sagemaker}
   port: ${PORT:8001}
 
 ui:
@@ -13,5 +13,5 @@ embedding:
   mode: sagemaker
 
 sagemaker:
-  llm_endpoint_name: huggingface-pytorch-tgi-inference-2023-09-25-19-53-32-140
-  embedding_endpoint_name: huggingface-pytorch-inference-2023-11-03-07-41-36-479
+  llm_endpoint_name: llm
+  embedding_endpoint_name: embedding

settings-test.yaml

@@ -14,5 +14,8 @@ qdrant:
 llm:
   mode: mock
 
+embedding:
+  mode: mock
+
 ui:
   enabled: false

settings-vllm.yaml

@@ -1,11 +1,14 @@
+server:
+  env_name: ${APP_ENV:vllm}
+
 llm:
   mode: openailike
 
 embedding:
-  mode: local
+  mode: huggingface
   ingest_mode: simple
 
-local:
+huggingface:
   embedding_hf_model_name: BAAI/bge-small-en-v1.5
 
 openai:

settings.yaml

@@ -35,17 +35,24 @@ ui:
   delete_all_files_button_enabled: true
 
 llm:
-  mode: local
+  mode: llamacpp
   # Should be matching the selected model
   max_new_tokens: 512
   context_window: 3900
-  tokenizer: mistralai/Mistral-7B-Instruct-v0.2
+
+llamacpp:
+  prompt_style: "mistral"
+  llm_hf_repo_id: TheBloke/Mistral-7B-Instruct-v0.2-GGUF
+  llm_hf_model_file: mistral-7b-instruct-v0.2.Q4_K_M.gguf
 
 embedding:
   # Should be matching the value above in most cases
-  mode: local
+  mode: huggingface
   ingest_mode: simple
 
+huggingface:
+  embedding_hf_model_name: BAAI/bge-small-en-v1.5
+
 vectorstore:
   database: qdrant
 
@@ -62,12 +69,6 @@ pgvector:
   schema_name: private_gpt
   table_name: embeddings
 
-local:
-  prompt_style: "mistral"
-  llm_hf_repo_id: TheBloke/Mistral-7B-Instruct-v0.2-GGUF
-  llm_hf_model_file: mistral-7b-instruct-v0.2.Q4_K_M.gguf
-  embedding_hf_model_name: BAAI/bge-small-en-v1.5
-
 sagemaker:
   llm_endpoint_name: huggingface-pytorch-tgi-inference-2023-09-25-19-53-32-140
   embedding_endpoint_name: huggingface-pytorch-inference-2023-11-03-07-41-36-479