aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2025-12-17 22:14:28 +01:00
Code Issues Packages Projects Releases Wiki Activity

feat(agent/llm): Use new OpenAI models as default SMART_LLM, FAST_LLM, and EMBEDDING_MODEL

Browse Source 
- Change default `SMART_LLM` from `gpt-4` to `gpt-4-turbo-preview`
- Change default `FAST_LLM` from `gpt-3.5-turbo-16k` to `gpt-3.5-turbo-0125`
- Change default `EMBEDDING_MODEL` from `text-embedding-ada-002` to `text-embedding-3-small`
- Update .env.template, azure.yaml.template, and documentation accordingly
This commit is contained in:
Reinier van der Leer
2024-02-12 13:19:37 +01:00
parent 7bf9ba5502
commit 1d653973e9
5 changed files with 16 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
autogpts/autogpt/.env.template
View File

@@ -86,14 +86,14 @@ OPENAI_API_KEY=your-openai-api-key
### LLM MODELS ### LLM MODELS
################################################################################ ################################################################################
## SMART_LLM - Smart language model (Default: gpt-4-0314) ## SMART_LLM - Smart language model (Default: gpt-4-turbo-preview)
# SMART_LLM=gpt-4-0314 # SMART_LLM=gpt-4-turbo-preview
## FAST_LLM - Fast language model (Default: gpt-3.5-turbo-16k) ## FAST_LLM - Fast language model (Default: gpt-3.5-turbo-0125)
# FAST_LLM=gpt-3.5-turbo-16k # FAST_LLM=gpt-3.5-turbo-0125
## EMBEDDING_MODEL - Model to use for creating embeddings ## EMBEDDING_MODEL - Model to use for creating embeddings
# EMBEDDING_MODEL=text-embedding-ada-002 # EMBEDDING_MODEL=text-embedding-3-small
################################################################################ ################################################################################
### SHELL EXECUTION ### SHELL EXECUTION

6
autogpts/autogpt/autogpt/config/config.py
View File

@@ -80,11 +80,11 @@ class Config(SystemSettings, arbitrary_types_allowed=True):
# Model configuration # Model configuration
fast_llm: str = UserConfigurable( fast_llm: str = UserConfigurable(
default="gpt-3.5-turbo-16k", default="gpt-3.5-turbo-0125",
from_env=lambda: os.getenv("FAST_LLM"), from_env=lambda: os.getenv("FAST_LLM"),
) )
smart_llm: str = UserConfigurable( smart_llm: str = UserConfigurable(
default="gpt-4", default="gpt-4-turbo-preview",
from_env=lambda: os.getenv("SMART_LLM"), from_env=lambda: os.getenv("SMART_LLM"),
) )
temperature: float = UserConfigurable( temperature: float = UserConfigurable(
@@ -95,7 +95,7 @@ class Config(SystemSettings, arbitrary_types_allowed=True):
default=False, from_env=lambda: os.getenv("OPENAI_FUNCTIONS", "False") == "True" default=False, from_env=lambda: os.getenv("OPENAI_FUNCTIONS", "False") == "True"
) )
embedding_model: str = UserConfigurable( embedding_model: str = UserConfigurable(
default="text-embedding-ada-002", from_env="EMBEDDING_MODEL" default="text-embedding-3-small", from_env="EMBEDDING_MODEL"
) )
browse_spacy_language_model: str = UserConfigurable( browse_spacy_language_model: str = UserConfigurable(
default="en_core_web_sm", from_env="BROWSE_SPACY_LANGUAGE_MODEL" default="en_core_web_sm", from_env="BROWSE_SPACY_LANGUAGE_MODEL"

6
autogpts/autogpt/azure.yaml.template
View File

@@ -2,6 +2,6 @@ azure_api_type: azure
azure_api_version: api-version-for-azure azure_api_version: api-version-for-azure
azure_endpoint: your-azure-openai-endpoint azure_endpoint: your-azure-openai-endpoint
azure_model_map: azure_model_map:
gpt-3.5-turbo: gpt35-deployment-id-for-azure gpt-3.5-turbo-0125: gpt35-deployment-id-for-azure
gpt-4: gpt4-deployment-id-for-azure gpt-4-turbo-preview: gpt4-deployment-id-for-azure
text-embedding-ada-002: embedding-deployment-id-for-azure text-embedding-3-small: embedding-deployment-id-for-azure

6
docs/content/AutoGPT/configuration/options.md
View File

@@ -14,10 +14,10 @@ Configuration is controlled through the `Config` object. You can set configurati
- `DISABLED_COMMAND_CATEGORIES`: Command categories to disable. Command categories are Python module names, e.g. autogpt.commands.execute_code. See the directory `autogpt/commands` in the source for all command modules. Default: None - `DISABLED_COMMAND_CATEGORIES`: Command categories to disable. Command categories are Python module names, e.g. autogpt.commands.execute_code. See the directory `autogpt/commands` in the source for all command modules. Default: None
- `ELEVENLABS_API_KEY`: ElevenLabs API Key. Optional. - `ELEVENLABS_API_KEY`: ElevenLabs API Key. Optional.
- `ELEVENLABS_VOICE_ID`: ElevenLabs Voice ID. Optional. - `ELEVENLABS_VOICE_ID`: ElevenLabs Voice ID. Optional.
- `EMBEDDING_MODEL`: LLM Model to use for embedding tasks. Default: text-embedding-ada-002 - `EMBEDDING_MODEL`: LLM Model to use for embedding tasks. Default: `text-embedding-3-small`
- `EXECUTE_LOCAL_COMMANDS`: If shell commands should be executed locally. Default: False - `EXECUTE_LOCAL_COMMANDS`: If shell commands should be executed locally. Default: False
- `EXIT_KEY`: Exit key accepted to exit. Default: n - `EXIT_KEY`: Exit key accepted to exit. Default: n
- `FAST_LLM`: LLM Model to use for most tasks. Default: gpt-3.5-turbo - `FAST_LLM`: LLM Model to use for most tasks. Default: `gpt-3.5-turbo-0125`
- `GITHUB_API_KEY`: [Github API Key](https://github.com/settings/tokens). Optional. - `GITHUB_API_KEY`: [Github API Key](https://github.com/settings/tokens). Optional.
- `GITHUB_USERNAME`: GitHub Username. Optional. - `GITHUB_USERNAME`: GitHub Username. Optional.
- `GOOGLE_API_KEY`: Google API key. Optional. - `GOOGLE_API_KEY`: Google API key. Optional.
@@ -44,7 +44,7 @@ Configuration is controlled through the `Config` object. You can set configurati
- `SHELL_ALLOWLIST`: List of shell commands that ARE allowed to be executed by AutoGPT. Only applies if `SHELL_COMMAND_CONTROL` is set to `allowlist`. Default: None - `SHELL_ALLOWLIST`: List of shell commands that ARE allowed to be executed by AutoGPT. Only applies if `SHELL_COMMAND_CONTROL` is set to `allowlist`. Default: None
- `SHELL_COMMAND_CONTROL`: Whether to use `allowlist` or `denylist` to determine what shell commands can be executed (Default: denylist) - `SHELL_COMMAND_CONTROL`: Whether to use `allowlist` or `denylist` to determine what shell commands can be executed (Default: denylist)
- `SHELL_DENYLIST`: List of shell commands that ARE NOT allowed to be executed by AutoGPT. Only applies if `SHELL_COMMAND_CONTROL` is set to `denylist`. Default: sudo,su - `SHELL_DENYLIST`: List of shell commands that ARE NOT allowed to be executed by AutoGPT. Only applies if `SHELL_COMMAND_CONTROL` is set to `denylist`. Default: sudo,su
- `SMART_LLM`: LLM Model to use for "smart" tasks. Default: gpt-4 - `SMART_LLM`: LLM Model to use for "smart" tasks. Default: `gpt-4-turbo-preview`
- `STREAMELEMENTS_VOICE`: StreamElements voice to use. Default: Brian - `STREAMELEMENTS_VOICE`: StreamElements voice to use. Default: Brian
- `TEMPERATURE`: Value of temperature given to OpenAI. Value from 0 to 2. Lower is more deterministic, higher is more random. See https://platform.openai.com/docs/api-reference/completions/create#completions/create-temperature - `TEMPERATURE`: Value of temperature given to OpenAI. Value from 0 to 2. Lower is more deterministic, higher is more random. See https://platform.openai.com/docs/api-reference/completions/create#completions/create-temperature
- `TEXT_TO_SPEECH_PROVIDER`: Text to Speech Provider. Options are `gtts`, `macos`, `elevenlabs`, and `streamelements`. Default: gtts - `TEXT_TO_SPEECH_PROVIDER`: Text to Speech Provider. Options are `gtts`, `macos`, `elevenlabs`, and `streamelements`. Default: gtts

7
docs/content/AutoGPT/setup/docker.md
View File

@@ -124,10 +124,7 @@ found in the [repository].
If you want to use GPT on an Azure instance, set `USE_AZURE` to `True` and If you want to use GPT on an Azure instance, set `USE_AZURE` to `True` and
make an Azure configuration file: make an Azure configuration file:
- Rename `azure.yaml.template` to `azure.yaml` and provide the relevant `azure_api_base`, `azure_api_version` and all the deployment IDs for the relevant models in the `azure_model_map` section: - Rename `azure.yaml.template` to `azure.yaml` and provide the relevant `azure_api_base`, `azure_api_version` and all the deployment IDs for the relevant models in the `azure_model_map` section.
- `fast_llm_deployment_id`: your gpt-3.5-turbo or gpt-4 deployment ID
- `smart_llm_deployment_id`: your gpt-4 deployment ID
- `embedding_model_deployment_id`: your text-embedding-ada-002 v2 deployment ID
Example: Example:
@@ -135,7 +132,7 @@ found in the [repository].
# Please specify all of these values as double-quoted strings # Please specify all of these values as double-quoted strings
# Replace string in angled brackets (<>) to your own deployment Name # Replace string in angled brackets (<>) to your own deployment Name
azure_model_map: azure_model_map:
fast_llm_deployment_id: "<auto-gpt-deployment>" gpt-4-turbo-preview: "<gpt-4-turbo deployment ID>"
... ...
``` ```