mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-27 15:37:44 +00:00
docs: Config Docs Update (#148)
* Add a table & factor debug * Congfig setting * Update env example and configuration list. Also change api priority * Add a TODO for the rst * CI: shorter line * Update docs/installation_and_configuration.rst * Update docs/installation_and_configuration.rst * Update links & standard config * Add TODO * Fix bug * Update rdagent/oai/llm_utils.py --------- Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
This commit is contained in:
cyncyw
+24
-9
@@ -1,15 +1,30 @@
|
||||
"""
|
||||
This file is a template for the .env file.
|
||||
|
||||
Please copy this file to .env and fill in the values.
|
||||
|
||||
For more information about configuration options, please refer to the documentation
|
||||
|
||||
"""
|
||||
|
||||
# Global configs:
|
||||
USE_AZURE=False
|
||||
USE_AZURE_TOKEN_PROVIDER=False
|
||||
MAX_RETRY=10
|
||||
RETRY_WAIT_SECONDS=20
|
||||
|
||||
# api key
|
||||
OPENAI_API_KEY=your_api_key
|
||||
|
||||
# embedding model configs:
|
||||
EMBEDDING_MODEL=text-embedding-3-small
|
||||
|
||||
# chat model configs:
|
||||
CHAT_MODEL=your_model_version
|
||||
# LLM API Setting:
|
||||
OPENAI_API_KEY=<your_api_key>
|
||||
CHAT_MODEL=gpt-4-turbo
|
||||
CHAT_MAX_TOKENS=3000
|
||||
CHAT_TEMPERATURE=0.7
|
||||
CHAT_STREAM=True
|
||||
# CHAT_AZURE_API_BASE=<for_Azure_user>
|
||||
# CHAT_AZURE_API_VERSION=<for_Azure_user>
|
||||
|
||||
EMBEDDING_MODEL=text-embedding-3-small
|
||||
# EMBEDDING_AZURE_API_BASE=<for_Azure_user>
|
||||
# EMBEDDING_AZURE_API_VERSION=<for_Azure_user>
|
||||
|
||||
# Cache Setting (Optional):
|
||||
|
||||
# Senario Configs:
|
||||
+1
-1
@@ -11,7 +11,7 @@ Welcome to RDAgent's documentation!
|
||||
:caption: Doctree:
|
||||
|
||||
demo_and_introduction
|
||||
installation
|
||||
installation_and_configuration
|
||||
scenarios_and_quickstart
|
||||
project_framework_introduction
|
||||
development
|
||||
|
||||
@@ -1,72 +0,0 @@
|
||||
=========================
|
||||
Installation
|
||||
=========================
|
||||
|
||||
Installation
|
||||
============
|
||||
|
||||
For different scenarios
|
||||
- for purely users:
|
||||
- for dev users: link to development
|
||||
|
||||
Configuration
|
||||
=============
|
||||
|
||||
To run the application, please create a `.env` file in the root directory of the project and add environment variables according to your requirements.
|
||||
|
||||
The standard configuration options for the user using the OpenAI API are provided in the `.env.example` file.
|
||||
|
||||
Here are some other configuration options that you can use:
|
||||
|
||||
OpenAI API
|
||||
------------
|
||||
|
||||
You can use different OpenAI API keys for embedding model and chat model.
|
||||
|
||||
.. code-block:: Properties
|
||||
|
||||
EMBEDDING_OPENAI_API_KEY=<replace_with_your_openai_api_key>
|
||||
EMBEDDING_MODEL=text-embedding-3-small
|
||||
|
||||
CHAT_OPENAI_API_KEY=<replace_with_your_openai_api_key>
|
||||
CHAT_MODEL=gpt-4-turbo
|
||||
|
||||
Azure OpenAI
|
||||
------------
|
||||
|
||||
The following environment variables are standard configuration options for the user using the OpenAI API.
|
||||
|
||||
.. code-block:: Properties
|
||||
|
||||
USE_AZURE=True
|
||||
|
||||
OPENAI_API_KEY=<replace_with_your_openai_api_key>
|
||||
|
||||
EMBEDDING_MODEL=text-embedding-3-small
|
||||
EMBEDDING_AZURE_API_BASE= # The base URL for the Azure OpenAI API.
|
||||
EMBEDDING_AZURE_API_VERSION = # The version of the Azure OpenAI API.
|
||||
|
||||
CHAT_MODEL=gpt-4-turbo
|
||||
CHAT_AZURE_API_VERSION = # The version of the Azure OpenAI API.
|
||||
|
||||
Use Azure Token Provider
|
||||
------------------------
|
||||
|
||||
If you are using the Azure token provider, you need to set the `USE_AZURE_TOKEN_PROVIDER` environment variable to `True`. then
|
||||
use the environment variables provided in the `Azure Configuration section <installation.html#azure-openai>`_.
|
||||
|
||||
☁️ Azure Configuration
|
||||
- Install Azure CLI:
|
||||
|
||||
```sh
|
||||
curl -L https://aka.ms/InstallAzureCli | bash
|
||||
```
|
||||
|
||||
- Log in to Azure:
|
||||
|
||||
```sh
|
||||
az login --use-device-code
|
||||
```
|
||||
|
||||
- `exit` and re-login to your environment (this step may not be necessary).
|
||||
|
||||
@@ -0,0 +1,142 @@
|
||||
==============================
|
||||
Installation and Configuration
|
||||
==============================
|
||||
|
||||
Installation
|
||||
============
|
||||
|
||||
For different scenarios
|
||||
- for purely users:
|
||||
- for dev users: `See development <development.html>`_
|
||||
|
||||
Configuration
|
||||
=============
|
||||
|
||||
To run the application, please create a `.env` file in the root directory of the project and add environment variables according to your requirements.
|
||||
|
||||
The standard configuration options for the user using the OpenAI API are provided in the `.env.example` file.
|
||||
|
||||
Here are some other configuration options that you can use:
|
||||
|
||||
OpenAI API
|
||||
------------
|
||||
|
||||
Here is a standard configuration for the user using the OpenAI API.
|
||||
|
||||
.. code-block:: Properties
|
||||
|
||||
OPENAI_API_KEY=<your_api_key>
|
||||
EMBEDDING_MODEL=text-embedding-3-small
|
||||
CHAT_MODEL=gpt-4-turbo
|
||||
|
||||
Azure OpenAI
|
||||
------------
|
||||
|
||||
The following environment variables are standard configuration options for the user using the OpenAI API.
|
||||
|
||||
.. code-block:: Properties
|
||||
|
||||
USE_AZURE=True
|
||||
|
||||
OPENAI_API_KEY=<replace_with_your_openai_api_key>
|
||||
|
||||
EMBEDDING_MODEL=text-embedding-3-small
|
||||
EMBEDDING_AZURE_API_BASE= # The base URL for the Azure OpenAI API.
|
||||
EMBEDDING_AZURE_API_VERSION = # The version of the Azure OpenAI API.
|
||||
|
||||
CHAT_MODEL=gpt-4-turbo
|
||||
CHAT_AZURE_API_VERSION = # The version of the Azure OpenAI API.
|
||||
|
||||
Use Azure Token Provider
|
||||
------------------------
|
||||
|
||||
If you are using the Azure token provider, you need to set the `USE_AZURE_TOKEN_PROVIDER` environment variable to `True`. then
|
||||
use the environment variables provided in the `Azure Configuration section <installation_and_configuration.html#azure-openai>`_.
|
||||
|
||||
|
||||
☁️ Azure Configuration
|
||||
- Install Azure CLI:
|
||||
|
||||
```sh
|
||||
curl -L https://aka.ms/InstallAzureCli | bash
|
||||
```
|
||||
|
||||
- Log in to Azure:
|
||||
|
||||
```sh
|
||||
az login --use-device-code
|
||||
```
|
||||
|
||||
- `exit` and re-login to your environment (this step may not be necessary).
|
||||
|
||||
|
||||
Configuration List
|
||||
------------------
|
||||
|
||||
.. TODO: use `autodoc-pydantic` .
|
||||
|
||||
- OpenAI API Setting
|
||||
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| Configuration Option | Meaning | Default Value |
|
||||
+=============================+==================================================+=========================+
|
||||
| OPENAI_API_KEY | API key for both chat and embedding models | None |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| EMBEDDING_OPENAI_API_KEY | Use a different API key for embedding model | None |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| CHAT_OPENAI_API_KEY | Set to use a different API key for chat model | None |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| EMBEDDING_MODEL | Name of the embedding model | text-embedding-3-small |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| CHAT_MODEL | Name of the chat model | gpt-4-turbo |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| EMBEDDING_AZURE_API_BASE | Base URL for the Azure OpenAI API | None |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| EMBEDDING_AZURE_API_VERSION | Version of the Azure OpenAI API | None |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| CHAT_AZURE_API_BASE | Base URL for the Azure OpenAI API | None |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| CHAT_AZURE_API_VERSION | Version of the Azure OpenAI API | None |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| USE_AZURE | True if you are using Azure OpenAI | False |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| USE_AZURE_TOKEN_PROVIDER | True if you are using a Azure Token Provider | False |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
|
||||
- Globol Setting
|
||||
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| Configuration Option | Meaning | Default Value |
|
||||
+=============================+==================================================+=========================+
|
||||
| max_retry | Maximum number of times to retry | 10 |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
| retry_wait_seconds | Number of seconds to wait before retrying | 1 |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
+ log_trace_path | Path to log trace file | None |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
+ log_llm_chat_content | Flag to indicate if chat content is logged | True |
|
||||
+-----------------------------+--------------------------------------------------+-------------------------+
|
||||
|
||||
|
||||
- Cache Setting
|
||||
|
||||
.. TODO: update Meaning for caches
|
||||
|
||||
+------------------------------+--------------------------------------------------+-------------------------+
|
||||
| Configuration Option | Meaning | Default Value |
|
||||
+==============================+==================================================+=========================+
|
||||
| dump_chat_cache | Flag to indicate if chat cache is dumped | False |
|
||||
+------------------------------+--------------------------------------------------+-------------------------+
|
||||
| dump_embedding_cache | Flag to indicate if embedding cache is dumped | False |
|
||||
+------------------------------+--------------------------------------------------+-------------------------+
|
||||
| use_chat_cache | Flag to indicate if chat cache is used | False |
|
||||
+------------------------------+--------------------------------------------------+-------------------------+
|
||||
| use_embedding_cache | Flag to indicate if embedding cache is used | False |
|
||||
+------------------------------+--------------------------------------------------+-------------------------+
|
||||
| prompt_cache_path | Path to prompt cache | ./prompt_cache.db |
|
||||
+------------------------------+--------------------------------------------------+-------------------------+
|
||||
| session_cache_folder_location| Path to session cache | ./session_cache_folder |
|
||||
+------------------------------+--------------------------------------------------+-------------------------+
|
||||
| max_past_message_include | Maximum number of past messages to include | 10 |
|
||||
+------------------------------+--------------------------------------------------+-------------------------+
|
||||
|
||||
@@ -20,7 +20,7 @@ class RDAgentSettings(BaseSettings):
|
||||
log_trace_path: str | None = None
|
||||
log_llm_chat_content: bool = True
|
||||
|
||||
use_azure: bool = True
|
||||
use_azure: bool = False
|
||||
use_azure_token_provider: bool = False
|
||||
managed_identity_client_id: str | None = None
|
||||
max_retry: int = 10
|
||||
@@ -48,7 +48,7 @@ class RDAgentSettings(BaseSettings):
|
||||
chat_token_limit: int = (
|
||||
100000 # 100000 is the maximum limit of gpt4, which might increase in the future version of gpt
|
||||
)
|
||||
default_system_prompt: str = "You are an AI assistant who helps to answer user's questions about finance."
|
||||
default_system_prompt: str = "You are an AI assistant who helps to answer user's questions."
|
||||
|
||||
# Embedding configs
|
||||
embedding_openai_api_key: str = ""
|
||||
|
||||
@@ -298,14 +298,21 @@ class APIBackend:
|
||||
self.use_azure_token_provider = self.cfg.use_azure_token_provider
|
||||
self.managed_identity_client_id = self.cfg.managed_identity_client_id
|
||||
|
||||
if self.cfg.openai_api_key:
|
||||
self.chat_api_key = self.cfg.openai_api_key
|
||||
self.embedding_api_key = self.cfg.openai_api_key
|
||||
else:
|
||||
self.chat_api_key = self.cfg.chat_openai_api_key if chat_api_key is None else chat_api_key
|
||||
self.embedding_api_key = (
|
||||
self.cfg.embedding_openai_api_key if embedding_api_key is None else embedding_api_key
|
||||
)
|
||||
# Priority: chat_api_key/embedding_api_key > openai_api_key > os.environ.get("OPENAI_API_KEY")
|
||||
# TODO: Simplify the key design. Consider Pandatic's field alias & priority.
|
||||
self.chat_api_key = (
|
||||
chat_api_key
|
||||
or self.cfg.chat_openai_api_key
|
||||
or self.cfg.openai_api_key
|
||||
or os.environ.get("OPENAI_API_KEY")
|
||||
)
|
||||
self.embedding_api_key = (
|
||||
embedding_api_key
|
||||
or self.cfg.embedding_openai_api_key
|
||||
or self.cfg.openai_api_key
|
||||
or os.environ.get("OPENAI_API_KEY")
|
||||
)
|
||||
|
||||
self.chat_model = self.cfg.chat_model if chat_model is None else chat_model
|
||||
self.encoder = tiktoken.encoding_for_model(self.chat_model)
|
||||
self.chat_api_base = self.cfg.chat_azure_api_base if chat_api_base is None else chat_api_base
|
||||
|
||||
Reference in New Issue
Block a user