langroid 0.2.6__py3-none-any.whl → 0.2.9__py3-none-any.whl

langroid/agent/openai_assistant.py

@@ -100,6 +100,10 @@ class OpenAIAssistant(ChatAgent):
         super().__init__(config)
         self.config: OpenAIAssistantConfig = config
         self.llm: OpenAIGPT = OpenAIGPT(self.config.llm)
+        assert (
+            self.llm.cache is not None
+        ), "OpenAIAssistant requires a cache to store Assistant and Thread ids"
+
         if not isinstance(self.llm.client, openai.OpenAI):
             raise ValueError("Client must be OpenAI")
         # handles for various entities and methods
@@ -235,19 +239,23 @@ class OpenAIAssistant(ChatAgent):
         """Try to retrieve cached thread_id associated with
         this user + machine + organization"""
         key = self._cache_thread_key()
+        if self.llm.cache is None:
+            return None
         return self.llm.cache.retrieve(key)
 
     @no_type_check
     def _cache_assistant_lookup(self) -> str | None:
         """Try to retrieve cached assistant_id associated with
         this user + machine + organization"""
+        if self.llm.cache is None:
+            return None
         key = self._cache_assistant_key()
         return self.llm.cache.retrieve(key)
 
     @no_type_check
     def _cache_messages_lookup(self) -> LLMResponse | None:
         """Try to retrieve cached response for the message-list-hash"""
-        if not settings.cache:
+        if not settings.cache or self.llm.cache is None:
             return None
         key = self._cache_messages_key()
         cached_dict = self.llm.cache.retrieve(key)
@@ -260,6 +268,8 @@ class OpenAIAssistant(ChatAgent):
         Cache the assistant_id, thread_id associated with
         this user + machine + organization
         """
+        if self.llm.cache is None:
+            return
         if self.thread is None or self.assistant is None:
             raise ValueError("Thread or Assistant is None")
         thread_key = self._cache_thread_key()
@@ -336,7 +346,8 @@ class OpenAIAssistant(ChatAgent):
                         Could not delete thread with id {cached}, ignoring. 
                         """
                     )
-                self.llm.cache.delete_keys([self._cache_thread_key()])
+                if self.llm.cache is not None:
+                    self.llm.cache.delete_keys([self._cache_thread_key()])
         if self.thread is None:
             if self.assistant is None:
                 raise ValueError("Assistant is None")
@@ -392,7 +403,8 @@ class OpenAIAssistant(ChatAgent):
                         Could not delete assistant with id {cached}, ignoring. 
                         """
                     )
-                self.llm.cache.delete_keys([self._cache_assistant_key()])
+                if self.llm.cache is not None:
+                    self.llm.cache.delete_keys([self._cache_assistant_key()])
         if self.assistant is None:
             self.assistant = self.client.beta.assistants.create(
                 name=self.config.name,
@@ -614,7 +626,8 @@ class OpenAIAssistant(ChatAgent):
             usage=None,  # TODO
             cached=False,  # TODO - revisit when able to insert Assistant responses
         )
-        self.llm.cache.store(key, result.dict())
+        if self.llm.cache is not None:
+            self.llm.cache.store(key, result.dict())
         return result
 
     def _parse_run_required_action(self) -> List[AssistantToolCall]:

langroid/agent/task.py

@@ -73,7 +73,7 @@ class TaskConfig(BaseModel):
         inf_loop_wait_factor (int): wait this * cycle_len msgs before loop-check
         restart_subtask_run (bool): whether to restart *every* run of this task
             when run as a subtask.
-        addressing_prefix (str): prefix an agent can use to address other
+        addressing_prefix (str): "@"-like prefix an agent can use to address other
             agents, or entities of the agent. E.g., if this is "@", the addressing
             string would be "@Alice", or "@user", "@llm", "@agent", etc.
             If this is an empty string, then addressing is disabled.
@@ -85,6 +85,10 @@ class TaskConfig(BaseModel):
             Instead, use the `RecipientTool` to have agents address other agents or
             entities. If you do choose to use `addressing_prefix`, the recommended
             setting is to use `langroid.utils.constants.AT`, which currently is "|@|".
+            Note that this setting does NOT affect the use of `constants.SEND_TO` --
+            this is always enabled since this is a critical way for responders to
+            indicate that the message should be sent to a specific entity/agent.
+            (Search for "SEND_TO" in the examples/ dir to see how this is used.)
     """
 
     inf_loop_cycle_len: int = 10
@@ -223,7 +227,7 @@ class Task:
             set_parent_agent=noop_fn,
         )
         self.config = config
-        # how to behave as a sub-task; can be overriden by `add_sub_task()`
+        # how to behave as a sub-task; can be overridden by `add_sub_task()`
         self.config_sub_task = copy.deepcopy(config)
         # counts of distinct pending messages in history,
         # to help detect (exact) infinite loops

langroid/language_models/__init__.py

@@ -16,6 +16,7 @@ from .base import (
 )
 from .openai_gpt import (
     OpenAIChatModel,
+    AnthropicModel,
     OpenAICompletionModel,
     OpenAIGPTConfig,
     OpenAIGPT,
@@ -39,6 +40,7 @@ __all__ = [
     "LLMTokenUsage",
     "LLMResponse",
     "OpenAIChatModel",
+    "AnthropicModel",
     "OpenAICompletionModel",
     "OpenAIGPTConfig",
     "OpenAIGPT",

langroid/language_models/base.py

@@ -17,6 +17,7 @@ from typing import (
 )
 
 from langroid.cachedb.base import CacheDBConfig
+from langroid.cachedb.redis_cachedb import RedisCacheConfig
 from langroid.parsing.agent_chats import parse_message
 from langroid.parsing.parse_json import top_level_json_field
 from langroid.prompts.dialog import collate_chat_history
@@ -50,7 +51,7 @@ class LLMConfig(BaseSettings):
     # use chat model for completion? For OpenAI models, this MUST be set to True!
     use_chat_for_completion: bool = True
     stream: bool = True  # stream output from API?
-    cache_config: None | CacheDBConfig = None
+    cache_config: None | CacheDBConfig = RedisCacheConfig()
 
     # Dict of model -> (input/prompt cost, output/completion cost)
     chat_cost_per_1k_tokens: Tuple[float, float] = (0.0, 0.0)

langroid/language_models/openai_gpt.py

@@ -65,6 +65,15 @@ OLLAMA_API_KEY = "ollama"
 DUMMY_API_KEY = "xxx"
 
 
+class AnthropicModel(str, Enum):
+    """Enum for Anthropic models"""
+
+    CLAUDE_3_5_SONNET = "claude-3-5-sonnet-20240620"
+    CLAUDE_3_OPUS = "claude-3-opus-20240229"
+    CLAUDE_3_SONNET = "claude-3-sonnet-20240229"
+    CLAUDE_3_HAIKU = "claude-3-turbo-20240307"
+
+
 class OpenAIChatModel(str, Enum):
     """Enum for OpenAI Chat models"""
 
@@ -90,6 +99,10 @@ _context_length: Dict[str, int] = {
     OpenAIChatModel.GPT4_TURBO: 128_000,
     OpenAIChatModel.GPT4o: 128_000,
     OpenAICompletionModel.TEXT_DA_VINCI_003: 4096,
+    AnthropicModel.CLAUDE_3_5_SONNET: 200_000,
+    AnthropicModel.CLAUDE_3_OPUS: 200_000,
+    AnthropicModel.CLAUDE_3_SONNET: 200_000,
+    AnthropicModel.CLAUDE_3_HAIKU: 200_000,
 }
 
 _cost_per_1k_tokens: Dict[str, Tuple[float, float]] = {
@@ -99,6 +112,10 @@ _cost_per_1k_tokens: Dict[str, Tuple[float, float]] = {
     OpenAIChatModel.GPT4: (0.03, 0.06),  # 8K context
     OpenAIChatModel.GPT4_TURBO: (0.01, 0.03),  # 128K context
     OpenAIChatModel.GPT4o: (0.005, 0.015),  # 128K context
+    AnthropicModel.CLAUDE_3_5_SONNET: (0.003, 0.015),
+    AnthropicModel.CLAUDE_3_OPUS: (0.015, 0.075),
+    AnthropicModel.CLAUDE_3_SONNET: (0.003, 0.015),
+    AnthropicModel.CLAUDE_3_HAIKU: (0.00025, 0.00125),
 }
 
 
@@ -478,8 +495,9 @@ class OpenAIGPT(LanguageModel):
                 timeout=Timeout(self.config.timeout),
             )
 
-        self.cache: CacheDB
-        if settings.cache_type == "momento":
+        self.cache: CacheDB | None = None
+        use_cache = self.config.cache_config is not None
+        if settings.cache_type == "momento" and use_cache:
             from langroid.cachedb.momento_cachedb import (
                 MomentoCache,
                 MomentoCacheConfig,
@@ -492,7 +510,7 @@ class OpenAIGPT(LanguageModel):
                 # switch to fresh momento config if needed
                 config.cache_config = MomentoCacheConfig()
             self.cache = MomentoCache(config.cache_config)
-        elif "redis" in settings.cache_type:
+        elif "redis" in settings.cache_type and use_cache:
             if config.cache_config is None or not isinstance(
                 config.cache_config,
                 RedisCacheConfig,
@@ -505,10 +523,10 @@ class OpenAIGPT(LanguageModel):
                 # force use of fake redis if global cache_type is "fakeredis"
                 config.cache_config.fake = True
             self.cache = RedisCache(config.cache_config)
-        else:
+        elif settings.cache_type != "none" and use_cache:
             raise ValueError(
                 f"Invalid cache type {settings.cache_type}. "
-                "Valid types are momento, redis, fakeredis"
+                "Valid types are momento, redis, fakeredis, none"
             )
 
         self.config._validate_litellm()
@@ -818,6 +836,8 @@ class OpenAIGPT(LanguageModel):
         )
 
     def _cache_store(self, k: str, v: Any) -> None:
+        if self.cache is None:
+            return
         try:
             self.cache.store(k, v)
         except Exception as e:
@@ -825,6 +845,8 @@ class OpenAIGPT(LanguageModel):
             pass
 
     def _cache_lookup(self, fn_name: str, **kwargs: Dict[str, Any]) -> Tuple[str, Any]:
+        if self.cache is None:
+            return "", None  # no cache, return empty key and None result
         # Use the kwargs as the cache key
         sorted_kwargs_str = str(sorted(kwargs.items()))
         raw_key = f"{fn_name}:{sorted_kwargs_str}"

langroid/utils/configuration.py

@@ -16,7 +16,7 @@ class Settings(BaseSettings):
     progress: bool = False  # show progress spinners/bars?
     stream: bool = True  # stream output?
     cache: bool = True  # use cache?
-    cache_type: Literal["redis", "fakeredis", "momento"] = "redis"  # cache type
+    cache_type: Literal["redis", "fakeredis", "momento", "none"] = "redis"  # cache type
     interactive: bool = True  # interactive mode?
     gpt3_5: bool = True  # use GPT-3.5?
     chat_model: str = ""  # language model name, e.g. litellm/ollama/llama2

{langroid-0.2.6.dist-info → langroid-0.2.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.2.6
+Version: 0.2.9
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani

{langroid-0.2.6.dist-info → langroid-0.2.9.dist-info}/RECORD

@@ -8,7 +8,7 @@ langroid/agent/chat_agent.py,sha256=nO6Yx5WvFsul5RmTP-HCdzeQPhccmzU_mDcPNdkzQ-s,
 langroid/agent/chat_document.py,sha256=MwtNABK28tfSzqCeQlxoauT8uPn8oldU7dlnrX8aQ10,11232
 langroid/agent/helpers.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/agent/junk,sha256=LxfuuW7Cijsg0szAzT81OjWWv1PMNI-6w_-DspVIO2s,339
-langroid/agent/openai_assistant.py,sha256=rmGJD5n0eE7_O1EkPyXgHFMNGc3vb2GKweZMhzmRWvI,33068
+langroid/agent/openai_assistant.py,sha256=3saI9PwF8IZNJcjqyUy-rj73TInAzdlk14LiOvT_Dkc,33548
 langroid/agent/special/__init__.py,sha256=gik_Xtm_zV7U9s30Mn8UX3Gyuy4jTjQe9zjiE3HWmEo,1273
 langroid/agent/special/doc_chat_agent.py,sha256=CXFLfDMEabaBZwZwFgNOaG3E3S86xcBM4txrsMD_70I,54014
 langroid/agent/special/lance_doc_chat_agent.py,sha256=USp0U3eTaJzwF_3bdqE7CedSLbaqAi2tm-VzygcyLaA,10175
@@ -32,7 +32,7 @@ langroid/agent/special/sql/utils/populate_metadata.py,sha256=1J22UsyEPKzwK0XlJZt
 langroid/agent/special/sql/utils/system_message.py,sha256=qKLHkvQWRQodTtPLPxr1GSLUYUFASZU8x-ybV67cB68,1885
 langroid/agent/special/sql/utils/tools.py,sha256=vFYysk6Vi7HJjII8B4RitA3pt_z3gkSglDNdhNVMiFc,1332
 langroid/agent/special/table_chat_agent.py,sha256=d9v2wsblaRx7oMnKhLV7uO_ujvk9gh59pSGvBXyeyNc,9659
-langroid/agent/task.py,sha256=1ujx4-SN3_-3xE0Z3r0lC-6LYYa4G-0lblg5cZWchBQ,73651
+langroid/agent/task.py,sha256=vKM2dmRYSH4i_VA0lf2axUtZcTGU44rVHz6EyxI4kG0,73990
 langroid/agent/tool_message.py,sha256=wIyZnUcZpxkiRPvM9O3MO3b5BBAdLEEan9kqPbvtApc,9743
 langroid/agent/tools/__init__.py,sha256=e-63cfwQNk_ftRKQwgDAJQK16QLbRVWDBILeXIc7wLk,402
 langroid/agent/tools/duckduckgo_search_tool.py,sha256=NhsCaGZkdv28nja7yveAhSK_w6l_Ftym8agbrdzqgfo,1935
@@ -62,12 +62,12 @@ langroid/embedding_models/protoc/embeddings_pb2.pyi,sha256=UkNy7BrNsmQm0vLb3NtGX
 langroid/embedding_models/protoc/embeddings_pb2_grpc.py,sha256=9dYQqkW3JPyBpSEjeGXTNpSqAkC-6FPtBHyteVob2Y8,2452
 langroid/embedding_models/remote_embeds.py,sha256=6_kjXByVbqhY9cGwl9R83ZcYC2km-nGieNNAo1McHaY,5151
 langroid/exceptions.py,sha256=w_Cr41nPAmsa6gW5nNFaO9yDcBCWdQqRspL1jYvZf5w,2209
-langroid/language_models/__init__.py,sha256=vrBtgR8Cq9UVfoI7nTms0IN7fd4y2JYpUP3GNV1DegY,898
+langroid/language_models/__init__.py,sha256=1sUGobooTqq77XC7LxKsvME0RgSd5GGmeyrPo9SMh4U,940
 langroid/language_models/azure_openai.py,sha256=ncRCbKooqLVOY-PWQUIo9C3yTuKEFbAwyngXT_M4P7k,5989
-langroid/language_models/base.py,sha256=aVptuo_LpymIQFpJh836lcFCUpJNOV3ukxvQAQMCqFc,17426
+langroid/language_models/base.py,sha256=oAK2lXBqksMglqWqE2CjC03X3qPFXWgtjFWpH9hJ3C8,17500
 langroid/language_models/config.py,sha256=9Q8wk5a7RQr8LGMT_0WkpjY8S4ywK06SalVRjXlfCiI,378
 langroid/language_models/mock_lm.py,sha256=qdgj-wtbQBXlibo_0rIRfCt0hGTPRoxy1C4VjN6quI4,2707
-langroid/language_models/openai_gpt.py,sha256=RXnLKULuCSeDeUPQvaZ4naqJgMKcMZogCtRDLycd4j8,50714
+langroid/language_models/openai_gpt.py,sha256=sALSYei56U57x8ugMayGIR6MtR9b9QsJ0MYhdt3_aMA,51674
 langroid/language_models/prompt_formatter/__init__.py,sha256=2-5cdE24XoFDhifOLl8yiscohil1ogbP1ECkYdBlBsk,372
 langroid/language_models/prompt_formatter/base.py,sha256=eDS1sgRNZVnoajwV_ZIha6cba5Dt8xjgzdRbPITwx3Q,1221
 langroid/language_models/prompt_formatter/hf_formatter.py,sha256=TFL6ppmeQWnzr6CKQzRZFYY810zE1mr8DZnhw6i85ok,5217
@@ -104,7 +104,7 @@ langroid/pydantic_v1/main.py,sha256=p_k7kDY9eDrsA5dxNNqXusKLgx7mS_icGnS7fu4goqY,
 langroid/utils/__init__.py,sha256=Sruos2tB4G7Tn0vlblvYlX9PEGR0plI2uE0PJ4d_EC4,353
 langroid/utils/algorithms/__init__.py,sha256=WylYoZymA0fnzpB4vrsH_0n7WsoLhmuZq8qxsOCjUpM,41
 langroid/utils/algorithms/graph.py,sha256=JbdpPnUOhw4-D6O7ou101JLA3xPCD0Lr3qaPoFCaRfo,2866
-langroid/utils/configuration.py,sha256=A70LdvdMuunlLSGI1gBmBL5j6Jhz-1syNP8R4AdjqDc,3295
+langroid/utils/configuration.py,sha256=LgjHGB0qgKKTwBaVt84APiqvJbz6pLwylUvHWYmzyP0,3303
 langroid/utils/constants.py,sha256=w3eBQ5Q2HjxMBN_y1UarK0keREqCwXSxQXizMafsG-M,911
 langroid/utils/docker.py,sha256=kJQOLTgM0x9j9pgIIqp0dZNZCTvoUDhp6i8tYBq1Jr0,1105
 langroid/utils/globals.py,sha256=Az9dOFqR6n9CoTYSqa2kLikQWS0oCQ9DFQIQAnG-2q8,1355
@@ -129,8 +129,8 @@ langroid/vector_store/meilisearch.py,sha256=6frB7GFWeWmeKzRfLZIvzRjllniZ1cYj3Hmh
 langroid/vector_store/momento.py,sha256=QaPzUnTwlswoawGB-paLtUPyLRvckFXLfLDfvbTzjNQ,10505
 langroid/vector_store/qdrant_cloud.py,sha256=3im4Mip0QXLkR6wiqVsjV1QvhSElfxdFSuDKddBDQ-4,188
 langroid/vector_store/qdrantdb.py,sha256=wYOuu5c2vIKn9ZgvTXcAiZXMpV8AOXEWFAzI8S8UP-0,16828
-pyproject.toml,sha256=QRWcQbtqFx0WvwrEVlpHvz0sqaXYaWplEfARV_RiN-0,6957
-langroid-0.2.6.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
-langroid-0.2.6.dist-info/METADATA,sha256=zKW_qJFbNttbgLTicYyef_8RONS-C38OSJYGISr38Xw,53950
-langroid-0.2.6.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-langroid-0.2.6.dist-info/RECORD,,
+pyproject.toml,sha256=vsVtb6-2IMl64e-3J3mqLEdL-hGAIw2X3gBjNk_HILs,6957
+langroid-0.2.9.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
+langroid-0.2.9.dist-info/METADATA,sha256=yColHB7bdfQ1nlYGucfcfH14xywCqm2IAjd8kPs3GhI,53950
+langroid-0.2.9.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+langroid-0.2.9.dist-info/RECORD,,

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langroid"
-version = "0.2.6"
+version = "0.2.9"
 description = "Harness LLMs with Multi-Agent Programming"
 authors = ["Prasad Chalasani <pchalasani@gmail.com>"]
 readme = "README.md"