langroid 0.2.6__tar.gz → 0.2.7__tar.gz

{langroid-0.2.6 → langroid-0.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.2.6
+Version: 0.2.7
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani

{langroid-0.2.6 → langroid-0.2.7}/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-0.2.6 → langroid-0.2.7}/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-0.2.6 → langroid-0.2.7}/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-0.2.6 → langroid-0.2.7}/langroid/language_models/openai_gpt.py

@@ -478,8 +478,9 @@ 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 +493,7 @@ 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 +506,10 @@ 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 +819,8 @@ 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 +828,8 @@ 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-0.2.6 → langroid-0.2.7}/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 → langroid-0.2.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langroid"
-version = "0.2.6"
+version = "0.2.7"
 description = "Harness LLMs with Multi-Agent Programming"
 authors = ["Prasad Chalasani <pchalasani@gmail.com>"]
 readme = "README.md"