Merge branch 'geekan:main' into main

config/config.yaml

@@ -1,23 +1,33 @@
 
-# Do not modify here, create a new key.yaml, define OPENAI_API_KEY. The configuration of key.yaml has a higher priority and will not enter git
+# DO NOT MODIFY THIS FILE, create a new key.yaml, define OPENAI_API_KEY.
+# The configuration of key.yaml has a higher priority and will not enter git
+
+#### if OpenAI
+
 OPENAI_API_KEY: "YOUR_API_KEY"
 #OPENAI_API_BASE: "YOUR_API_BASE"
 OPENAI_API_MODEL: "gpt-4"
 MAX_TOKENS: 1500
 RPM: 10
 
+#### if AZURE, check https://github.com/openai/openai-cookbook/blob/main/examples/azure/chat.ipynb
+
+#OPENAI_API_TYPE: "azure"
+#OPENAI_API_BASE: "YOUR_AZURE_ENDPOINT"
+#OPENAI_API_KEY: "YOUR_AZURE_API_KEY"
+#OPENAI_API_VERSION: "YOUR_AZURE_API_VERSION"
+#DEPLOYMENT_ID: "YOUR_DEPLOYMENT_ID"
+
+#### for Search
+
 ## Visit https://serpapi.com/ to get key.
 #SERPAPI_API_KEY: "YOUR_API_KEY"
-#
 ## Visit https://console.cloud.google.com/apis/credentials to get key.
 #GOOGLE_API_KEY: "YOUR_API_KEY"
 ## Visit https://programmablesearchengine.google.com/controlpanel/create to get id.
 #GOOGLE_CSE_ID: "YOUR_CSE_ID"
-#
-#AZURE_OPENAI_KEY: "YOUR_API_KEY"
-#AZURE_OPENAI_ENDPOINT: "YOUR_API_BASE"
-#AZURE_DEPLOYMENT_NAME: "gpt-35"
-#AZURE_OPENAI_API_VERSION: "2023-03-15-preview"
-#
+
+#### for TTS
+
 #AZURE_TTS_SUBSCRIPTION_KEY: "YOUR_API_KEY"
-#AZURE_TTS_REGION: "eastus"
+#AZURE_TTS_REGION: "eastus"

metagpt/config.py

@@ -52,6 +52,7 @@ def __init__(self, yaml_file=default_yaml_file):
         self.openai_api_rpm = self._get('RPM', 3)
         self.openai_api_model = self._get('OPENAI_API_MODEL', "gpt-4")
         self.max_tokens_rsp = self._get('MAX_TOKENS', 2048)
+        self.deployment_id = self._get('DEPLOYMENT_ID')
 
         self.serpapi_api_key = self._get('SERPAPI_API_KEY')
         self.google_api_key = self._get('GOOGLE_API_KEY')

metagpt/const.py

@@ -14,7 +14,7 @@ def get_project_root():
     while True:
         if (current_path / '.git').exists() or \
            (current_path / '.project_root').exists() or \
-           (current_path.name.lower() == 'metagpt'):
+           (current_path / '.gitignore').exists():
             return current_path
         parent_path = current_path.parent
         if parent_path == current_path:

metagpt/provider/__init__.py

@@ -6,5 +6,4 @@
 @File    : __init__.py
 """
 
-from metagpt.provider.openai_api import OpenAIGPTAPI
-from metagpt.provider.azure_api import AzureGPTAPI
+from metagpt.provider.openai_api import OpenAIGPTAPI

metagpt/provider/openai_api.py

@@ -13,7 +13,7 @@
 from metagpt.logs import logger
 
 from metagpt.provider.base_gpt_api import BaseGPTAPI
-from metagpt.config import Config
+from metagpt.config import CONFIG
 from metagpt.utils.singleton import Singleton
 from metagpt.utils.token_counter import count_message_tokens, TOKEN_COSTS, count_string_tokens
 
@@ -69,7 +69,6 @@ def __init__(self):
         self.total_completion_tokens = 0
         self.total_cost = 0
         self.total_budget = 0
-        self.config = Config()
 
     def update_cost(self, prompt_tokens, completion_tokens, model):
         """
@@ -87,9 +86,9 @@ def update_cost(self, prompt_tokens, completion_tokens, model):
             + completion_tokens * TOKEN_COSTS[model]["completion"]
         ) / 1000
         self.total_cost += cost
-        logger.info(f"Total running cost: ${self.total_cost:.3f} | Max budget: ${self.config.max_budget:.3f} | "
+        logger.info(f"Total running cost: ${self.total_cost:.3f} | Max budget: ${CONFIG.max_budget:.3f} | "
                     f"Current cost: ${cost:.3f}, {prompt_tokens=}, {completion_tokens=}")
-        self.config.total_cost = self.total_cost
+        CONFIG.total_cost = self.total_cost
 
     def get_total_prompt_tokens(self):
         """
@@ -128,10 +127,9 @@ class OpenAIGPTAPI(BaseGPTAPI, RateLimiter):
     Check https://platform.openai.com/examples for examples
     """
     def __init__(self):
-        self.config = Config()
-        self.__init_openai(self.config)
+        self.__init_openai(CONFIG)
         self.llm = openai
-        self.model = self.config.openai_api_model
+        self.model = CONFIG.openai_api_model
         self._cost_manager = CostManager()
         RateLimiter.__init__(self, rpm=self.rpm)
 
@@ -146,12 +144,7 @@ def __init_openai(self, config):
 
     async def _achat_completion_stream(self, messages: list[dict]) -> str:
         response = await openai.ChatCompletion.acreate(
-            model=self.model,
-            messages=messages,
-            max_tokens=self.config.max_tokens_rsp,
-            n=1,
-            stop=None,
-            temperature=0,
+            **self._cons_kwargs(messages),
             stream=True
         )
 
@@ -172,27 +165,34 @@ async def _achat_completion_stream(self, messages: list[dict]) -> str:
         self._update_costs(usage)
         return full_reply_content
 
+    def _cons_kwargs(self, messages: list[dict]) -> dict:
+        if CONFIG.openai_api_type == 'azure':
+            kwargs = {
+                "deployment_id": CONFIG.deployment_id,
+                "messages": messages,
+                "max_tokens": CONFIG.max_tokens_rsp,
+                "n": 1,
+                "stop": None,
+                "temperature": 0.5
+            }
+        else:
+            kwargs = {
+                "model": self.model,
+                "messages": messages,
+                "max_tokens": CONFIG.max_tokens_rsp,
+                "n": 1,
+                "stop": None,
+                "temperature": 0.5
+            }
+        return kwargs
+
     async def _achat_completion(self, messages: list[dict]) -> dict:
-        rsp = await self.llm.ChatCompletion.acreate(
-            model=self.model,
-            messages=messages,
-            max_tokens=self.config.max_tokens_rsp,
-            n=1,
-            stop=None,
-            temperature=0.5,
-        )
+        rsp = await self.llm.ChatCompletion.acreate(**self._cons_kwargs(messages))
         self._update_costs(rsp.get('usage'))
         return rsp
 
     def _chat_completion(self, messages: list[dict]) -> dict:
-        rsp = self.llm.ChatCompletion.create(
-            model=self.model,
-            messages=messages,
-            max_tokens=self.config.max_tokens_rsp,
-            n=1,
-            stop=None,
-            temperature=0.5,
-        )
+        rsp = self.llm.ChatCompletion.create(**self._cons_kwargs(messages))
         self._update_costs(rsp)
         return rsp