langroid 0.52.4__tar.gz → 0.52.6__tar.gz

{langroid-0.52.4 → langroid-0.52.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langroid
-Version: 0.52.4
+Version: 0.52.6
 Summary: Harness LLMs with Multi-Agent Programming
 Author-email: Prasad Chalasani <pchalasani@gmail.com>
 License: MIT
@@ -151,8 +151,6 @@ Provides-Extra: meilisearch
 Requires-Dist: meilisearch-python-sdk<3.0.0,>=2.2.3; extra == 'meilisearch'
 Provides-Extra: metaphor
 Requires-Dist: metaphor-python<0.2.0,>=0.1.23; extra == 'metaphor'
-Provides-Extra: momento
-Requires-Dist: momento<1.21.0,>=1.10.2; extra == 'momento'
 Provides-Extra: mysql
 Requires-Dist: pymysql<2.0.0,>=1.1.0; extra == 'mysql'
 Provides-Extra: neo4j
@@ -617,9 +615,8 @@ section above)
 providers ([local/open](https://langroid.github.io/langroid/tutorials/local-llm-setup/) or [remote/commercial](https://langroid.github.io/langroid/tutorials/non-openai-llms/)) via proxy libraries and local model servers
 such as [ollama](https://github.com/ollama), [oobabooga](https://github.com/oobabooga/text-generation-webui), 
   [LiteLLM](https://docs.litellm.ai/docs/providers) that in effect mimic the OpenAI API. See the [supported LLMs](https://langroid.github.io/langroid/tutorials/supported-models/). 
-- **Caching of LLM responses:** Langroid supports [Redis](https://redis.com/try-free/) and 
-  [Momento](https://www.gomomento.com/) to cache LLM responses.
-- **Vector-stores**: [LanceDB](https://github.com/lancedb/lancedb), [Qdrant](https://qdrant.tech/), [Chroma](https://www.trychroma.com/) are currently supported.
+- **Caching of LLM responses:** Langroid supports [Redis](https://redis.com/try-free/) to cache LLM responses.
+- **Vector-stores**: [Qdrant](https://qdrant.tech/), [Chroma](https://www.trychroma.com/), LanceDB, Pinecone, PostgresDB (PGVector), Weaviate are currently supported.
   Vector stores allow for Retrieval-Augmented-Generation (RAG).
 - **Grounding and source-citation:** Access to external documents via vector-stores 
    allows for grounding and source-citation.

{langroid-0.52.4 → langroid-0.52.6}/README.md

@@ -415,9 +415,8 @@ section above)
 providers ([local/open](https://langroid.github.io/langroid/tutorials/local-llm-setup/) or [remote/commercial](https://langroid.github.io/langroid/tutorials/non-openai-llms/)) via proxy libraries and local model servers
 such as [ollama](https://github.com/ollama), [oobabooga](https://github.com/oobabooga/text-generation-webui), 
   [LiteLLM](https://docs.litellm.ai/docs/providers) that in effect mimic the OpenAI API. See the [supported LLMs](https://langroid.github.io/langroid/tutorials/supported-models/). 
-- **Caching of LLM responses:** Langroid supports [Redis](https://redis.com/try-free/) and 
-  [Momento](https://www.gomomento.com/) to cache LLM responses.
-- **Vector-stores**: [LanceDB](https://github.com/lancedb/lancedb), [Qdrant](https://qdrant.tech/), [Chroma](https://www.trychroma.com/) are currently supported.
+- **Caching of LLM responses:** Langroid supports [Redis](https://redis.com/try-free/) to cache LLM responses.
+- **Vector-stores**: [Qdrant](https://qdrant.tech/), [Chroma](https://www.trychroma.com/), LanceDB, Pinecone, PostgresDB (PGVector), Weaviate are currently supported.
   Vector stores allow for Retrieval-Augmented-Generation (RAG).
 - **Grounding and source-citation:** Access to external documents via vector-stores 
    allows for grounding and source-citation.

{langroid-0.52.4 → langroid-0.52.6}/langroid/agent/chat_agent.py

@@ -735,7 +735,11 @@ class ChatAgent(Agent):
                 self.llm_tools_usable.discard(t)
                 self.llm_functions_usable.discard(t)
 
-        # Set tool instructions and JSON format instructions
+        self._update_tool_instructions()
+
+    def _update_tool_instructions(self) -> None:
+        # Set tool instructions and JSON format instructions,
+        # in case Tools have been enabled/disabled.
         if self.config.use_tools:
             self.system_tool_format_instructions = self.tool_format_rules()
         self.system_tool_instructions = self.tool_instructions()
@@ -977,6 +981,8 @@ class ChatAgent(Agent):
             self.llm_tools_usable.discard(t)
             self.llm_functions_usable.discard(t)
 
+        self._update_tool_instructions()
+
     def disable_message_use_except(self, message_class: Type[ToolMessage]) -> None:
         """
         Disable this agent from USING ALL messages EXCEPT a message class (Tool)
@@ -988,6 +994,7 @@ class ChatAgent(Agent):
         for r in to_remove:
             self.llm_tools_usable.discard(r)
             self.llm_functions_usable.discard(r)
+        self._update_tool_instructions()
 
     def _load_output_format(self, message: ChatDocument) -> None:
         """

{langroid-0.52.4 → langroid-0.52.6}/langroid/agent/special/doc_chat_agent.py

@@ -123,6 +123,9 @@ class DocChatAgentConfig(ChatAgentConfig):
         None  # filter condition for various lexical/semantic search fns
     )
     conversation_mode: bool = True  # accumulate message history?
+    # retain retrieved context? Setting to True increases token consumption, but
+    # helps LLM fix citation errors and improve accuracy of follow-up questions.
+    retain_context: bool = False
     # In assistant mode, DocChatAgent receives questions from another Agent,
     # and those will already be in stand-alone form, so in this mode
     # there is no need to convert them to stand-alone form.
@@ -861,8 +864,11 @@ class DocChatAgent(ChatAgent):
         # one for `final_prompt`, and one for the LLM response
 
         if self.config.conversation_mode:
-            # respond with temporary context
-            answer_doc = super()._llm_response_temp_context(question, final_prompt)
+            if self.config.retain_context:
+                answer_doc = super().llm_response(final_prompt)
+            else:
+                # respond with temporary context
+                answer_doc = super()._llm_response_temp_context(question, final_prompt)
         else:
             answer_doc = super().llm_response_forget(final_prompt)
 

langroid-0.52.6/langroid/cachedb/__init__.py

@@ -0,0 +1,8 @@
+from . import base
+
+from . import redis_cachedb
+
+__all__ = [
+    "base",
+    "redis_cachedb",
+]

{langroid-0.52.4 → langroid-0.52.6}/langroid/language_models/openai_gpt.py

@@ -627,20 +627,7 @@ class OpenAIGPT(LanguageModel):
 
         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,
-            )
-
-            if config.cache_config is None or not isinstance(
-                config.cache_config,
-                MomentoCacheConfig,
-            ):
-                # switch to fresh momento config if needed
-                config.cache_config = MomentoCacheConfig()
-            self.cache = MomentoCache(config.cache_config)
-        elif "redis" in settings.cache_type and use_cache:
+        if "redis" in settings.cache_type and use_cache:
             if config.cache_config is None or not isinstance(
                 config.cache_config,
                 RedisCacheConfig,
@@ -656,7 +643,7 @@ class OpenAIGPT(LanguageModel):
         elif settings.cache_type != "none" and use_cache:
             raise ValueError(
                 f"Invalid cache type {settings.cache_type}. "
-                "Valid types are momento, redis, fakeredis, none"
+                "Valid types are redis, fakeredis, none"
             )
 
         self.config._validate_litellm()

{langroid-0.52.4 → langroid-0.52.6}/langroid/utils/configuration.py

@@ -17,7 +17,7 @@ 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", "none"] = "redis"  # cache type
+    cache_type: Literal["redis", "fakeredis", "none"] = "redis"  # cache type
     chat_model: str = ""  # language model name, e.g. litellm/ollama/llama2
     quiet: bool = False  # quiet mode (i.e. suppress all output)?
     notebook: bool = False  # running in a notebook?

{langroid-0.52.4 → langroid-0.52.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langroid"
-version = "0.52.4"
+version = "0.52.6"
 authors = [
     {name = "Prasad Chalasani", email = "pchalasani@gmail.com"},
 ]
@@ -242,10 +242,6 @@ meilisearch = [
     "meilisearch-python-sdk<3.0.0,>=2.2.3",
 ]
 
-momento = [
-    "momento<1.21.0,>=1.10.2",
-]
-
 fastembed = [
     "fastembed<0.4.0,>=0.3.1",
 ]

langroid-0.52.4/langroid/cachedb/__init__.py

@@ -1,17 +0,0 @@
-from . import base
-
-from . import redis_cachedb
-
-__all__ = [
-    "base",
-    "redis_cachedb",
-]
-
-
-try:
-    from . import momento_cachedb
-
-    momento_cachedb
-    __all__.append("momento_cachedb")
-except ImportError:
-    pass

langroid-0.52.4/langroid/cachedb/momento_cachedb.py

@@ -1,108 +0,0 @@
-import json
-import logging
-import os
-from datetime import timedelta
-from typing import Any, Dict, List
-
-from langroid.cachedb.base import CacheDBConfig
-from langroid.exceptions import LangroidImportError
-
-try:
-    import momento
-    from momento.responses import CacheGet
-except ImportError:
-    raise LangroidImportError(package="momento", extra="momento")
-
-from dotenv import load_dotenv
-
-from langroid.cachedb.base import CacheDB
-
-logger = logging.getLogger(__name__)
-
-
-class MomentoCacheConfig(CacheDBConfig):
-    """Configuration model for Momento Cache."""
-
-    ttl: int = 60 * 60 * 24 * 7  # 1 week
-    cachename: str = "langroid_momento_cache"
-
-
-class MomentoCache(CacheDB):
-    """Momento implementation of the CacheDB."""
-
-    def __init__(self, config: MomentoCacheConfig):
-        """
-        Initialize a MomentoCache with the given config.
-
-        Args:
-            config (MomentoCacheConfig): The configuration to use.
-        """
-        self.config = config
-        load_dotenv()
-
-        momento_token = os.getenv("MOMENTO_AUTH_TOKEN")
-        if momento_token is None:
-            raise ValueError("""MOMENTO_AUTH_TOKEN not set in .env file""")
-        else:
-            self.client = momento.CacheClient(
-                configuration=momento.Configurations.Laptop.v1(),
-                credential_provider=momento.CredentialProvider.from_environment_variable(
-                    "MOMENTO_AUTH_TOKEN"
-                ),
-                default_ttl=timedelta(seconds=self.config.ttl),
-            )
-            self.client.create_cache(self.config.cachename)
-
-    def clear(self) -> None:
-        """Clear keys from current db."""
-        self.client.flush_cache(self.config.cachename)
-
-    def store(self, key: str, value: Any) -> None:
-        """
-        Store a value associated with a key.
-
-        Args:
-            key (str): The key under which to store the value.
-            value (Any): The value to store.
-        """
-        self.client.set(self.config.cachename, key, json.dumps(value))
-
-    def retrieve(self, key: str) -> Dict[str, Any] | str | None:
-        """
-        Retrieve the value associated with a key.
-
-        Args:
-            key (str): The key to retrieve the value for.
-
-        Returns:
-            dict: The value associated with the key.
-        """
-        value = self.client.get(self.config.cachename, key)
-        if isinstance(value, CacheGet.Hit):
-            return json.loads(value.value_string)  # type: ignore
-        else:
-            return None
-
-    def delete_keys(self, keys: List[str]) -> None:
-        """
-        Delete the keys from the cache.
-
-        Args:
-            keys (List[str]): The keys to delete.
-        """
-        for key in keys:
-            self.client.delete(self.config.cachename, key)
-
-    def delete_keys_pattern(self, pattern: str) -> None:
-        """
-        Delete the keys from the cache with the given pattern.
-
-        Args:
-            prefix (str): The pattern to match.
-        """
-        raise NotImplementedError(
-            """
-            MomentoCache does not support delete_keys_pattern.
-            Please use RedisCache instead.
-            """
-        )