langroid 0.37.3__py3-none-any.whl → 0.37.5__py3-none-any.whl

langroid/agent/chat_agent.py

@@ -1023,7 +1023,7 @@ class ChatAgent(Agent):
         all_tools: bool = False,
     ) -> List[ToolMessage]:
         """
-        Extracts messages and tracks whether any errors occured. If strict mode
+        Extracts messages and tracks whether any errors occurred. If strict mode
         was enabled, disables it for the tool, else triggers strict recovery.
         """
         self.tool_error = False

langroid/agent/special/sql/sql_chat_agent.py

@@ -427,15 +427,7 @@ class SQLChatAgent(ChatAgent):
         return error_message_template
 
     def _available_tool_names(self) -> str:
-        return ",".join(
-            tool.name()  # type: ignore
-            for tool in [
-                RunQueryTool,
-                GetTableNamesTool,
-                GetTableSchemaTool,
-                GetColumnDescriptionsTool,
-            ]
-        )
+        return ",".join(self.llm_tools_usable)
 
     def _tool_result_llm_answer_prompt(self) -> str:
         """
@@ -510,7 +502,7 @@ class SQLChatAgent(ChatAgent):
         {self._tool_result_llm_answer_prompt()}
         OTHERWISE:
              continue using one of your available TOOLs:
-             {self._available_tool_names()}
+             {",".join(self.llm_tools_usable)}
         """
         return final_message
 

langroid/language_models/openai_gpt.py

@@ -1897,7 +1897,12 @@ class OpenAIGPT(LanguageModel):
             }
         }
         """
-        message = response["choices"][0]["message"]
+        if response.get("choices") is None:
+            message = {}
+        else:
+            message = response["choices"][0].get("message", {})
+        if message is None:
+            message = {}
         msg = message.get("content", "")
         reasoning = message.get("reasoning_content", "")
 

langroid/vector_store/base.py

@@ -8,7 +8,7 @@ import pandas as pd
 
 from langroid.embedding_models.base import EmbeddingModel, EmbeddingModelsConfig
 from langroid.embedding_models.models import OpenAIEmbeddingsConfig
-from langroid.mytypes import DocMetaData, Document
+from langroid.mytypes import DocMetaData, Document, EmbeddingFunction
 from langroid.pydantic_v1 import BaseSettings
 from langroid.utils.algorithms.graph import components, topological_sort
 from langroid.utils.configuration import settings
@@ -51,6 +51,7 @@ class VectorStore(ABC):
             self.embedding_model = EmbeddingModel.create(config.embedding)
         else:
             self.embedding_model = config.embedding_model
+        self.embedding_fn: EmbeddingFunction = self.embedding_model.embedding_fn()
 
     @staticmethod
     def create(config: VectorStoreConfig) -> Optional["VectorStore"]:
@@ -86,6 +87,10 @@ class VectorStore(ABC):
             )
             return None
 
+    @property
+    def embedding_dim(self) -> int:
+        return len(self.embedding_fn(["test"])[0])
+
     @abstractmethod
     def clear_empty_collections(self) -> int:
         """Clear all empty collections in the vector store.

langroid/vector_store/chromadb.py

@@ -35,7 +35,6 @@ class ChromaDB(VectorStore):
         except ImportError:
             raise LangroidImportError("chromadb", "chromadb")
         self.config = config
-        self.embedding_fn = self.embedding_model.embedding_fn()
         self.client = chromadb.Client(
             chromadb.config.Settings(
                 # chroma_db_impl="duckdb+parquet",

langroid/vector_store/lancedb.py

@@ -26,7 +26,7 @@ from langroid.embedding_models.base import (
 )
 from langroid.embedding_models.models import OpenAIEmbeddingsConfig
 from langroid.exceptions import LangroidImportError
-from langroid.mytypes import Document, EmbeddingFunction
+from langroid.mytypes import Document
 from langroid.utils.configuration import settings
 from langroid.utils.pydantic_utils import (
     dataframe_to_document_model,
@@ -60,8 +60,6 @@ class LanceDB(VectorStore):
             raise LangroidImportError("lancedb", "lancedb")
 
         self.config: LanceDBConfig = config
-        self.embedding_fn: EmbeddingFunction = self.embedding_model.embedding_fn()
-        self.embedding_dim = self.embedding_model.embedding_dims
         self.host = config.host
         self.port = config.port
         self.is_from_dataframe = False  # were docs ingested from a dataframe?

langroid/vector_store/momento.py

@@ -37,7 +37,7 @@ from langroid.embedding_models.base import (
     EmbeddingModelsConfig,
 )
 from langroid.embedding_models.models import OpenAIEmbeddingsConfig
-from langroid.mytypes import Document, EmbeddingFunction
+from langroid.mytypes import Document
 from langroid.utils.configuration import settings
 from langroid.utils.pydantic_utils import (
     flatten_pydantic_instance,
@@ -61,8 +61,6 @@ class MomentoVI(VectorStore):
             raise LangroidImportError("momento", "momento")
         self.distance = SimilarityMetric.COSINE_SIMILARITY
         self.config: MomentoVIConfig = config
-        self.embedding_fn: EmbeddingFunction = self.embedding_model.embedding_fn()
-        self.embedding_dim = self.embedding_model.embedding_dims
         self.host = config.host
         self.port = config.port
         load_dotenv()

langroid/vector_store/qdrantdb.py

@@ -27,7 +27,7 @@ from langroid.embedding_models.base import (
     EmbeddingModelsConfig,
 )
 from langroid.embedding_models.models import OpenAIEmbeddingsConfig
-from langroid.mytypes import Document, EmbeddingFunction, Embeddings
+from langroid.mytypes import Document, Embeddings
 from langroid.utils.configuration import settings
 from langroid.vector_store.base import VectorStore, VectorStoreConfig
 
@@ -77,8 +77,6 @@ class QdrantDB(VectorStore):
     def __init__(self, config: QdrantDBConfig = QdrantDBConfig()):
         super().__init__(config)
         self.config: QdrantDBConfig = config
-        self.embedding_fn: EmbeddingFunction = self.embedding_model.embedding_fn()
-        self.embedding_dim = len(self.embedding_fn(["test"])[0])
         if self.config.use_sparse_embeddings:
             try:
                 from transformers import AutoModelForMaskedLM, AutoTokenizer

langroid/vector_store/weaviatedb.py

@@ -10,7 +10,7 @@ from langroid.embedding_models.base import (
 )
 from langroid.embedding_models.models import OpenAIEmbeddingsConfig
 from langroid.exceptions import LangroidImportError
-from langroid.mytypes import DocMetaData, Document, EmbeddingFunction
+from langroid.mytypes import DocMetaData, Document
 from langroid.utils.configuration import settings
 from langroid.vector_store.base import VectorStore, VectorStoreConfig
 
@@ -38,8 +38,6 @@ class WeaviateDB(VectorStore):
     def __init__(self, config: WeaviateDBConfig = WeaviateDBConfig()):
         super().__init__(config)
         self.config: WeaviateDBConfig = config
-        self.embedding_fn: EmbeddingFunction = self.embedding_model.embedding_fn()
-        self.embedding_dim = self.embedding_model.embedding_dims
         load_dotenv()
         key = os.getenv("WEAVIATE_API_KEY")
         url = os.getenv("WEAVIATE_API_URL")

{langroid-0.37.3.dist-info → langroid-0.37.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langroid
-Version: 0.37.3
+Version: 0.37.5
 Summary: Harness LLMs with Multi-Agent Programming
 Author-email: Prasad Chalasani <pchalasani@gmail.com>
 License: MIT

{langroid-0.37.3.dist-info → langroid-0.37.5.dist-info}/RECORD

@@ -5,7 +5,7 @@ langroid/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/agent/__init__.py,sha256=ll0Cubd2DZ-fsCMl7e10hf9ZjFGKzphfBco396IKITY,786
 langroid/agent/base.py,sha256=oThlrYygKDu1-bKjAfygldJ511gMKT8Z0qCrD52DdDM,77834
 langroid/agent/batch.py,sha256=vi1r5i1-vN80WfqHDSwjEym_KfGsqPGUtwktmiK1nuk,20635
-langroid/agent/chat_agent.py,sha256=UvcZRoQ5jIYvlei8rku0T2Ul8tMpEhCJ2FGvr5_yc5Q,82275
+langroid/agent/chat_agent.py,sha256=_7vOhTauPpPiOih2hnec8hz0rytaxGN110ja9wRCLJ0,82276
 langroid/agent/chat_document.py,sha256=xzMtrPbaW-Y-BnF7kuhr2dorsD-D5rMWzfOqJ8HAoo8,17885
 langroid/agent/openai_assistant.py,sha256=JkAcs02bIrgPNVvUWVR06VCthc5-ulla2QMBzux_q6o,34340
 langroid/agent/task.py,sha256=XrXUbSoiFasvpIsZPn_cBpdWaTCKljJPRimtLMrSZrs,90347
@@ -35,7 +35,7 @@ langroid/agent/special/neo4j/neo4j_chat_agent.py,sha256=1RMKupJra0KZ-hA7AiiR662S
 langroid/agent/special/neo4j/system_messages.py,sha256=m2jsVayey6E_88F5B_gW2WbWKBJvIeDUoVCRBbNs97o,4522
 langroid/agent/special/neo4j/tools.py,sha256=Vw3HvtDfG2c4_bUHgt4_ZbJq48lpIQstbjjwhh1BjrQ,905
 langroid/agent/special/sql/__init__.py,sha256=mWfmm1QpXCezpFOS2eI57M0L_Ok3q5_ukG8tXBnBrEA,319
-langroid/agent/special/sql/sql_chat_agent.py,sha256=CJ-vQFbtcGhmOM-GBQvG2quUmicXXW0XPK1pj52E-54,25639
+langroid/agent/special/sql/sql_chat_agent.py,sha256=X0GzKPOHoYv36M_jYYUgYKW9H1Rum87O11iFpR0yhKQ,25430
 langroid/agent/special/sql/utils/__init__.py,sha256=JFif6CRTrN-bc91uuAI4K9fe2ndIWSNMVxJ0WA68--M,446
 langroid/agent/special/sql/utils/description_extractors.py,sha256=cX8TIpmTPXZXQTMpIi3OUFwFsPywxFFdurpx717Kq0I,6529
 langroid/agent/special/sql/utils/populate_metadata.py,sha256=1J22UsyEPKzwK0XlJZtYn9r6kYc0FXIr8-lZrndYlhc,3131
@@ -69,7 +69,7 @@ langroid/language_models/azure_openai.py,sha256=zNQzzsERxNestq-hFfQZbvTzK43G2vjR
 langroid/language_models/base.py,sha256=avM_RgoTPm1Esr8KSmW-4G0YBSfabeOnTEX3hrT_vM0,24104
 langroid/language_models/config.py,sha256=9Q8wk5a7RQr8LGMT_0WkpjY8S4ywK06SalVRjXlfCiI,378
 langroid/language_models/mock_lm.py,sha256=5BgHKDVRWFbUwDT_PFgTZXz9-k8wJSA2e3PZmyDgQ1k,4022
-langroid/language_models/openai_gpt.py,sha256=1Nru0al-5i2jI4qqwteUt4mYqcBm5Cxdt19wGSnVU7s,79550
+langroid/language_models/openai_gpt.py,sha256=Bpo1CKO5WavKWJBgJqpUU7zpYVcd-dUE4D_DK_5vP-U,79698
 langroid/language_models/utils.py,sha256=L4_CbihDMTGcsg0TOG1Yd5JFEto46--h7CX_14m89sQ,5016
 langroid/language_models/prompt_formatter/__init__.py,sha256=2-5cdE24XoFDhifOLl8yiscohil1ogbP1ECkYdBlBsk,372
 langroid/language_models/prompt_formatter/base.py,sha256=eDS1sgRNZVnoajwV_ZIha6cba5Dt8xjgzdRbPITwx3Q,1221
@@ -116,14 +116,14 @@ langroid/utils/output/citations.py,sha256=mQhRXVN-uhmKd2z32UZQBE0adZGEaQJ7cVXLfk
 langroid/utils/output/printing.py,sha256=yzPJZN-8_jyOJmI9N_oLwEDfjMwVgk3IDiwnZ4eK_AE,2962
 langroid/utils/output/status.py,sha256=rzbE7mDJcgNNvdtylCseQcPGCGghtJvVq3lB-OPJ49E,1049
 langroid/vector_store/__init__.py,sha256=BcoOm1tG3y0EqjkIGmMOHkY9iTUhDHgyruknWDKgqIg,1214
-langroid/vector_store/base.py,sha256=suBanIt0iKEgnMnGdQOyWS58guG20Jyy-GK4DMMuYL0,14208
-langroid/vector_store/chromadb.py,sha256=XkpW7pnSf6Lk7Nf1BEIw-zjYGYchoWHgrhnJX7YmxD8,8725
-langroid/vector_store/lancedb.py,sha256=b3_vWkTjG8mweZ7ZNlUD-NjmQP_rLBZfyKWcxt2vosA,14855
+langroid/vector_store/base.py,sha256=69keYWkUD0fcGXC0STcdO1-jn8H4Ez-L_fnxmRvUoNw,14412
+langroid/vector_store/chromadb.py,sha256=p9mEqJwO2BrL2jSSXfa23kCPlPOwWpF3xJYd5zoWw_c,8661
+langroid/vector_store/lancedb.py,sha256=Qd20gKjWozPWfW5-D66J6U8dSrJo1yl-maj6s1lbf1c,14688
 langroid/vector_store/meilisearch.py,sha256=6frB7GFWeWmeKzRfLZIvzRjllniZ1cYj3HmhHQICXLs,11663
-langroid/vector_store/momento.py,sha256=UNHGT6jXuQtqY9f6MdqGU14bVnS0zHgIJUa30ULpUJo,10474
-langroid/vector_store/qdrantdb.py,sha256=Cen6f-y6witiR53UQ-5a605Reo0gTj3ygXpE_ehYoZo,18116
-langroid/vector_store/weaviatedb.py,sha256=S-gG5xbOx7f_VXyGACPk20TWWxORpvZPJ8kWB1ZT9WU,10772
-langroid-0.37.3.dist-info/METADATA,sha256=kuk0ka12Ezg5CEte9Sx7oc9IBvX1bT4B5ssTb2U1yBg,60524
-langroid-0.37.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-langroid-0.37.3.dist-info/licenses/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
-langroid-0.37.3.dist-info/RECORD,,
+langroid/vector_store/momento.py,sha256=xOaU7Hlyyn_5ihb0ARS5JHtmrKrTCt2IdRA-ioMM5ek,10307
+langroid/vector_store/qdrantdb.py,sha256=v7TAsIoj_vxeKDYS9tpwJLBZA8fuTweTYxHo0X_uawM,17949
+langroid/vector_store/weaviatedb.py,sha256=FOzgvqLqvdN5jJebVtJ-8tu2CeBzBfSP3ih4_ODEOOw,10605
+langroid-0.37.5.dist-info/METADATA,sha256=2wTE_fB76vBz5un3RldampCIcired_fnMIqFdYxxifY,60524
+langroid-0.37.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+langroid-0.37.5.dist-info/licenses/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
+langroid-0.37.5.dist-info/RECORD,,