aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2026-02-17 20:24:30 +01:00
Code Issues Packages Projects Releases Wiki Activity

feat(agent/core): Add Anthropic Claude 3 support (#7085)

Browse Source 
- feat(agent/core): Add `AnthropicProvider`
  - Add `ANTHROPIC_API_KEY` to .env.template and docs

  Notable differences in logic compared to `OpenAIProvider`:
  - Merges subsequent user messages in `AnthropicProvider._get_chat_completion_args`
  - Merges and extracts all system messages into `system` parameter in `AnthropicProvider._get_chat_completion_args`
  - Supports prefill; merges prefill content (if any) into generated response

- Prompt changes to improve compatibility with `AnthropicProvider`
  Anthropic has a slightly different API compared to OpenAI, and has much stricter input validation. E.g. Anthropic only supports a single `system` prompt, where OpenAI allows multiple `system` messages. Anthropic also forbids sequences of multiple `user` or `assistant` messages and requires that messages alternate between roles.
  - Move response format instruction from separate message into main system prompt
  - Fix clock message format
  - Add pre-fill to `OneShot` generated prompt

- refactor(agent/core): Tweak `model_providers.schema`
  - Simplify `ModelProviderUsage`
     - Remove attribute `total_tokens` as it is always equal to `prompt_tokens + completion_tokens`
     - Modify signature of `update_usage(..)`; no longer requires a full `ModelResponse` object as input
  - Improve `ModelProviderBudget`
     - Change type of attribute `usage` to `defaultdict[str, ModelProviderUsage]` -> allow per-model usage tracking
     - Modify signature of `update_usage_and_cost(..)`; no longer requires a full `ModelResponse` object as input
     - Allow `ModelProviderBudget` zero-argument instantiation
  - Fix type of `AssistantChatMessage.role` to match `ChatMessage.role` (str -> `ChatMessage.Role`)
  - Add shared attributes and constructor to `ModelProvider` base class
  - Add `max_output_tokens` parameter to `create_chat_completion` interface
  - Add pre-filling as a global feature
    - Add `prefill_response` field to `ChatPrompt` model
    - Add `prefill_response` parameter to `create_chat_completion` interface
  - Add `ChatModelProvider.get_available_models()` and remove `ApiManager`
  - Remove unused `OpenAIChatParser` typedef in openai.py
  - Remove redundant `budget` attribute definition on `OpenAISettings`
  - Remove unnecessary `usage` in `OpenAIProvider` > `default_settings` > `budget`

- feat(agent): Allow use of any available LLM provider through `MultiProvider`
  - Add `MultiProvider` (`model_providers.multi`)
  - Replace all references to / uses of `OpenAIProvider` with `MultiProvider`
  - Change type of `Config.smart_llm` and `Config.fast_llm` from `str` to `ModelName`

- feat(agent/core): Validate function call arguments in `create_chat_completion`
    - Add `validate_call` method to `CompletionModelFunction` in `model_providers.schema`
    - Add `validate_tool_calls` utility function in `model_providers.utils`
    - Add tool call validation step to `create_chat_completion` in `OpenAIProvider` and `AnthropicProvider`
    - Remove (now redundant) command argument validation logic in agent.py and models/command.py

- refactor(agent): Rename `get_openai_command_specs` to `function_specs_from_commands`
This commit is contained in:
Reinier van der Leer
2024-05-04 20:33:25 +02:00
committed by GitHub
parent 78d83bb3ce
commit 39c46ef6be
24 changed files with 923 additions and 149 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/content/AutoGPT/configuration/options.md
View File

@@ -7,6 +7,7 @@ Configuration is controlled through the `Config` object. You can set configurati
- `AI_SETTINGS_FILE`: Location of the AI Settings file relative to the AutoGPT root directory. Default: ai_settings.yaml
- `AUDIO_TO_TEXT_PROVIDER`: Audio To Text Provider. Only option currently is `huggingface`. Default: huggingface
- `AUTHORISE_COMMAND_KEY`: Key response accepted when authorising commands. Default: y
- `ANTHROPIC_API_KEY`: Set this if you want to use Anthropic models with AutoGPT
- `AZURE_CONFIG_FILE`: Location of the Azure Config file relative to the AutoGPT root directory. Default: azure.yaml
- `BROWSE_CHUNK_MAX_LENGTH`: When browsing website, define the length of chunks to summarize. Default: 3000
- `BROWSE_SPACY_LANGUAGE_MODEL`: [spaCy language model](https://spacy.io/usage/models) to use when creating chunks. Default: en_core_web_sm