langchain-timbr 2.0.0__py3-none-any.whl → 2.0.1__py3-none-any.whl

langchain_timbr/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '2.0.0'
-__version_tuple__ = version_tuple = (2, 0, 0)
+__version__ = version = '2.0.1'
+__version_tuple__ = version_tuple = (2, 0, 1)
 
 __commit_id__ = commit_id = None

langchain_timbr/config.py

@@ -20,3 +20,11 @@ llm_api_key = os.environ.get('LLM_API_KEY')
 llm_temperature = os.environ.get('LLM_TEMPERATURE', 0.0)
 llm_additional_params = os.environ.get('LLM_ADDITIONAL_PARAMS', '')
 llm_timeout = to_integer(os.environ.get('LLM_TIMEOUT', 60))  # Default 60 seconds timeout
+
+# Optional for Azure OpenAI with Service Principal authentication
+llm_tenant_id = os.environ.get('LLM_TENANT_ID', None)
+llm_client_id = os.environ.get('LLM_CLIENT_ID', None)
+llm_client_secret = os.environ.get('LLM_CLIENT_SECRET', None)
+llm_endpoint = os.environ.get('LLM_ENDPOINT', None)
+llm_api_version = os.environ.get('LLM_API_VERSION', None)
+llm_scope = os.environ.get('LLM_SCOPE', "https://cognitiveservices.azure.com/.default")  # e.g. "api://<your-client-id>/.default"

langchain_timbr/llm_wrapper/llm_wrapper.py

@@ -4,8 +4,8 @@ from langchain.llms.base import LLM
 from pydantic import Field
 
 from .timbr_llm_wrapper import TimbrLlmWrapper
-from ..utils.general import is_llm_type, is_support_temperature, get_supported_models, parse_additional_params
-from ..config import llm_temperature, llm_type as default_llm_type, llm_model as default_llm_model, llm_api_key as default_llm_api_key, llm_additional_params as default_llm_additional_params
+from ..utils.general import is_llm_type, is_support_temperature, get_supported_models, parse_additional_params, pop_param_value
+from .. import config
 
 class LlmTypes(Enum):
   OpenAI = 'openai-chat'
@@ -42,13 +42,13 @@ class LlmWrapper(LLM):
       """
       super().__init__()
       
-      selected_llm_type = llm_type or default_llm_type
-      selected_api_key = api_key or default_llm_api_key
-      selected_model = model or default_llm_model
+      selected_llm_type = llm_type or config.llm_type
+      selected_api_key = api_key or config.llm_api_key or config.llm_client_secret
+      selected_model = model or config.llm_model
       selected_additional_params = llm_params.pop('additional_params', None)
 
       # Parse additional parameters from init params or config and merge with provided params
-      default_additional_params = parse_additional_params(selected_additional_params or default_llm_additional_params or {})
+      default_additional_params = parse_additional_params(selected_additional_params or config.llm_additional_params or {})
       additional_llm_params = {**default_additional_params, **llm_params}
       
       # Validation: Ensure we have the required parameters
@@ -76,8 +76,8 @@ class LlmWrapper(LLM):
     Add temperature to the LLM parameters if the LLM model supports it.
     """
     if "temperature" not in llm_params:
-      if llm_temperature is not None and is_support_temperature(llm_type, llm_model):
-        llm_params["temperature"] = llm_temperature
+      if config.llm_temperature is not None and is_support_temperature(llm_type, llm_model):
+        llm_params["temperature"] = config.llm_temperature
     return llm_params
 
   
@@ -127,15 +127,36 @@ class LlmWrapper(LLM):
       )
     elif is_llm_type(llm_type, LlmTypes.AzureOpenAI):
       from langchain_openai import AzureChatOpenAI
-      azure_endpoint = params.pop('azure_endpoint', None)
-      azure_api_version = params.pop('azure_openai_api_version', None)
       llm_model = model or "gpt-4o-2024-11-20"
       params = self._add_temperature(LlmTypes.AzureOpenAI.name, llm_model, **llm_params)
+
+      azure_endpoint = pop_param_value(params, ['azure_endpoint', 'llm_endpoint'], default=config.llm_endpoint)
+      azure_api_version = pop_param_value(params, ['azure_api_version', 'llm_api_version'], default=config.llm_api_version)
+
+      azure_client_id = pop_param_value(params, ['azure_client_id', 'llm_client_id'], default=config.llm_client_id)
+      azure_tenant_id = pop_param_value(params, ['azure_tenant_id', 'llm_tenant_id'], default=config.llm_tenant_id)
+      if azure_tenant_id and azure_client_id:
+        from azure.identity import ClientSecretCredential, get_bearer_token_provider
+        azure_client_secret = pop_param_value(params, ['azure_client_secret', 'llm_client_secret'], default=api_key)
+        scope = pop_param_value(params, ['azure_scope', 'llm_scope'], default=config.llm_scope)
+        credential = ClientSecretCredential(
+          tenant_id=azure_tenant_id,
+          client_id=azure_client_id,
+          client_secret=azure_client_secret
+        )
+        token_provider = get_bearer_token_provider(credential, scope)
+        params['azure_ad_token_provider'] = token_provider
+      else:
+        params['open_api_key'] = api_key
+
+      if 'openai_api_version' not in params or not params['openai_api_version']:
+        params['openai_api_version'] = azure_api_version
+
+      if 'azure_endpoint' not in params or not params['azure_endpoint']:
+        params['azure_endpoint'] = azure_endpoint
+
       return AzureChatOpenAI(
-        openai_api_key=api_key,
         azure_deployment=llm_model,
-        azure_endpoint=azure_endpoint,
-        openai_api_version=azure_api_version,
         **params,
       )
     elif is_llm_type(llm_type, LlmTypes.Databricks):
@@ -174,16 +195,28 @@ class LlmWrapper(LLM):
       elif is_llm_type(self._llm_type, LlmTypes.AzureOpenAI):
         from openai import AzureOpenAI
         # Get Azure-specific attributes from the client
-        azure_endpoint = getattr(self.client, 'azure_endpoint', None)
-        api_version = getattr(self.client, 'openai_api_version', None)
-        api_key = self.client.openai_api_key._secret_value
-        
-        if azure_endpoint and api_version and api_key:
-          client = AzureOpenAI(
-            api_key=api_key,
-            azure_endpoint=azure_endpoint,
-            api_version=api_version
-          )
+        api_key = None
+        azure_ad_token_provider = None
+        azure_endpoint = getattr(self.client, 'azure_endpoint', config.llm_endpoint)
+        api_version = getattr(self.client, 'openai_api_version', config.llm_api_version)
+
+        params = {
+          "azure_endpoint": azure_endpoint,
+          "api_version": api_version,
+        }
+
+        api_key = getattr(self.client.openai_api_key, '_secret_value', None)
+        if api_key:
+          params['api_key'] = api_key
+        else:
+          azure_ad_token_provider = getattr(self.client, 'azure_ad_token_provider', None)
+          if azure_ad_token_provider:
+            params['azure_ad_token_provider'] = azure_ad_token_provider
+          else:
+            raise ValueError("Azure OpenAI requires either an API key or an Azure AD token provider for authentication.")
+
+        if azure_endpoint and api_version and (api_key or azure_ad_token_provider):
+          client = AzureOpenAI(**params)
           # For Azure, get the deployments instead of models
           try:
             models = [model.id for model in client.models.list()]
@@ -199,9 +232,10 @@ class LlmWrapper(LLM):
           "llama3.1-405b"
         ]
       elif is_llm_type(self._llm_type, LlmTypes.Databricks):
-        w = self.client.workspace_client
-        models = [ep.name for ep in w.serving_endpoints.list()]
-        
+        w = getattr(self.client, 'workspace_client', None)
+        if w:
+          models = [ep.name for ep in w.serving_endpoints.list()]
+
       # elif self._is_llm_type(self._llm_type, LlmTypes.Timbr):
         
     except Exception:
@@ -213,11 +247,9 @@ class LlmWrapper(LLM):
           if is_llm_type(self._llm_type, llm_enum):
             llm_type_name = llm_enum.name
             break
-      
-      if llm_type_name:
-        models = get_supported_models(llm_type_name)
-      else:
-        models = []
+
+    if len(models) == 0 and llm_type_name:
+      models = get_supported_models(llm_type_name)
     
     return sorted(models)
 

langchain_timbr/timbr_llm_connector.py

@@ -10,15 +10,7 @@ from .langchain import IdentifyTimbrConceptChain, GenerateTimbrSqlChain, Validat
 from .langgraph import GenerateTimbrSqlNode, ValidateSemanticSqlNode, ExecuteSemanticQueryNode, GenerateResponseNode
 
 
-from .config import (
-    url as default_url,
-    token as default_token,
-    ontology as default_ontology,
-    llm_type,
-    llm_model,
-    llm_api_key,
-    llm_temperature,
-)
+from . import config
 
 class TimbrLanggraphState(TypedDict):
     prompt: str
@@ -35,9 +27,9 @@ class TimbrLlmConnector:
     def __init__(
         self,
         llm: LLM,
-        url: Optional[str] = default_url,
-        token: Optional[str] = default_token,
-        ontology: Optional[str] = default_ontology,
+        url: Optional[str] = config.url,
+        token: Optional[str] = config.token,
+        ontology: Optional[str] = config.ontology,
         max_limit: Optional[int] = 500,
         verify_ssl: Optional[bool] = True,
         is_jwt: Optional[bool] = False,
@@ -97,15 +89,15 @@ class TimbrLlmConnector:
         
         if llm is not None:
             self._llm = llm
-        elif llm_type is not None and llm_api_key is not None:
+        elif config.llm_type is not None and config.llm_api_key is not None:
             llm_params = {}
-            if llm_temperature is not None:
-                llm_params["temperature"] = llm_temperature
+            if config.llm_temperature is not None:
+                llm_params["temperature"] = config.llm_temperature
 
             self._llm = LlmWrapper(
-                llm_type=llm_type,
-                api_key=llm_api_key,
-                model=llm_model,
+                llm_type=config.llm_type,
+                api_key=config.llm_api_key,
+                model=config.llm_model,
                 **llm_params,
             )
 

langchain_timbr/utils/general.py

@@ -1,5 +1,5 @@
 import os
-from typing import Optional
+from typing import Any, Optional, Union
 import json
 
 ### A global helper functions to use across the project
@@ -43,7 +43,7 @@ def parse_additional_params(value) -> dict:
     """
     try:
         if isinstance(value, dict):
-            return value
+            return {k.lower(): v for k, v in value.items()}
         elif isinstance(value, str) and value.strip():
             # Try to parse as JSON first
             stripped_value = value.strip()
@@ -58,10 +58,10 @@ def parse_additional_params(value) -> dict:
             for pair in (value.split('&') if '&' in value else value.split(',')):
                 if '=' in pair:
                     key, val = pair.split('=', 1)
-                    params[key.strip()] = val.strip()
+                    params[key.strip().lower()] = val.strip()
                 elif ':' in pair:
                     key, val = pair.split(':', 1)
-                    params[key.strip()] = val.strip()
+                    params[key.strip().lower()] = val.strip()
             return params
         return {}
     except Exception as e:
@@ -138,3 +138,27 @@ def get_supported_models(llm_type: str) -> list[str]:
     except (FileNotFoundError, json.JSONDecodeError):
         return []
 
+
+def pop_param_value(
+    params_dict: dict,
+    opt_keys: Union[str, list[str]],
+    default: Any=None,
+):
+    """
+    Retrieve the value for the first matching key from params_dict.
+    
+    Args:
+        params_dict (dict): Dictionary to search for keys
+        opt_keys (str or list[str]): Key or list of keys to look for
+        default: Default value to return if no keys are found
+        
+    Returns:
+        The value corresponding to the first found key, or default if none found.
+    """
+    if isinstance(opt_keys, str):
+        opt_keys = [opt_keys]
+    
+    for key in opt_keys:
+        if key in params_dict:
+            return params_dict.pop(key)
+    return default

{langchain_timbr-2.0.0.dist-info → langchain_timbr-2.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langchain-timbr
-Version: 2.0.0
+Version: 2.0.1
 Summary: LangChain & LangGraph extensions that parse LLM prompts into Timbr semantic SQL and execute them.
 Project-URL: Homepage, https://github.com/WPSemantix/langchain-timbr
 Project-URL: Documentation, https://docs.timbr.ai/doc/docs/integration/langchain-sdk/
@@ -31,6 +31,7 @@ Requires-Dist: tiktoken==0.8.0
 Requires-Dist: transformers>=4.53
 Provides-Extra: all
 Requires-Dist: anthropic==0.42.0; extra == 'all'
+Requires-Dist: azure-identity==1.16.1; extra == 'all'
 Requires-Dist: databricks-langchain==0.3.0; (python_version < '3.10') and extra == 'all'
 Requires-Dist: databricks-langchain==0.7.1; (python_version >= '3.10') and extra == 'all'
 Requires-Dist: databricks-sdk==0.64.0; extra == 'all'
@@ -49,6 +50,7 @@ Provides-Extra: anthropic
 Requires-Dist: anthropic==0.42.0; extra == 'anthropic'
 Requires-Dist: langchain-anthropic>=0.3.1; extra == 'anthropic'
 Provides-Extra: azure-openai
+Requires-Dist: azure-identity==1.16.1; extra == 'azure-openai'
 Requires-Dist: langchain-openai>=0.3.16; extra == 'azure-openai'
 Requires-Dist: openai>=1.77.0; extra == 'azure-openai'
 Provides-Extra: databricks
@@ -104,7 +106,7 @@ python -m pip install langchain-timbr
 #### One of: openai, anthropic, google, azure_openai, snowflake, databricks (or 'all')
 
 ```bash
-python -m pip install 'langchain-timbr[<your selected providers, separated by comma w/o space]'
+python -m pip install 'langchain-timbr[<your selected providers, separated by comma w/o space>]'
 ```
 
 ### Using pip from github
@@ -143,7 +145,13 @@ The SDK uses environment variables for configuration. All configurations are opt
 
 - **`LLM_TYPE`** - The type of LLM provider to use
 - **`LLM_MODEL`** - The specific model to use with the LLM provider
-- **`LLM_API_KEY`** - API key for the LLM provider
+- **`LLM_API_KEY`** - API key or client secret for the LLM provider
 - **`LLM_TEMPERATURE`** - Temperature setting for LLM responses (controls randomness)
 - **`LLM_ADDITIONAL_PARAMS`** - Additional parameters to pass to the LLM
 - **`LLM_TIMEOUT`** - Timeout for LLM requests in seconds
+- **`LLM_TENANT_ID`** - LLM provider tenant/directory ID (Used for Service Principal authentication)
+- **`LLM_CLIENT_ID`** - LLM provider client ID (Used for Service Principal authentication)
+- **`LLM_CLIENT_SECRET`** - LLM provider client secret (Used for Service Principal authentication)
+- **`LLM_ENDPOINT`** - LLM provider OpenAI endpoint URL
+- **`LLM_API_VERSION`** - LLM provider API version
+- **`LLM_SCOPE`** - LLM provider authentication scope

{langchain_timbr-2.0.0.dist-info → langchain_timbr-2.0.1.dist-info}/RECORD

@@ -1,7 +1,7 @@
 langchain_timbr/__init__.py,sha256=gxd6Y6QDmYZtPlYVdXtPIy501hMOZXHjWh2qq4qzt_s,828
-langchain_timbr/_version.py,sha256=IVJRXufGjjlpCRVrnll1svFy181ozZaXe7LKnGKKesg,704
-langchain_timbr/config.py,sha256=DT2__mjaFCh8Eynm4czQM8vKRTxYVcNX3UJNU3epJwo,934
-langchain_timbr/timbr_llm_connector.py,sha256=OXRttlEOJf-dTyilnXR6b6Cgl_cWDYrXGXQfmDV6vc8,13206
+langchain_timbr/_version.py,sha256=b81iV_6_GhhfUN6bognTzQ8RMeyOUj9vn-DmcuKf2qU,704
+langchain_timbr/config.py,sha256=PEtvNgvnA9UseZJjKgup_O6xdG-VYk3N11nH8p8W1Kg,1410
+langchain_timbr/timbr_llm_connector.py,sha256=1jDicBZkW7CKB-PvQiQ1_AMXYm9JJHaoNaPqy54nhh8,13096
 langchain_timbr/langchain/__init__.py,sha256=ejcsZKP9PK0j4WrrCCcvBXpDpP-TeRiVb21OIUJqix8,580
 langchain_timbr/langchain/execute_timbr_query_chain.py,sha256=g7VzCuywo7xlWIldjtGOV4dYsQB3KsO8VARCfKrZFHM,15461
 langchain_timbr/langchain/generate_answer_chain.py,sha256=euy8GcMOziMKpiJrmpiH-De-qKTaVV48TqTduDa5-PE,4711
@@ -15,14 +15,14 @@ langchain_timbr/langgraph/generate_response_node.py,sha256=BLmsDZfbhncRpO7PEfDpy
 langchain_timbr/langgraph/generate_timbr_sql_node.py,sha256=wkau-NajblSVzNIro9IyqawULvz3XaCYSEdYW95vWco,4911
 langchain_timbr/langgraph/identify_concept_node.py,sha256=aiLDFEcz_vM4zZ_ULe1SvJKmI-e4Fb2SibZQaEPz_eY,3649
 langchain_timbr/langgraph/validate_timbr_query_node.py,sha256=-2fuieCz1hv6ua-17zfonme8LQ_OoPnoOBTdGSXkJgs,4793
-langchain_timbr/llm_wrapper/llm_wrapper.py,sha256=XK4tcm6GGX4fZfciVN1BgwAFk0YI5FdkmtMwFuUL-Po,9701
+langchain_timbr/llm_wrapper/llm_wrapper.py,sha256=aNnXXjVewQTrhneEGXayu9W5I7wF8Q28aIn1VRVBZFw,11325
 langchain_timbr/llm_wrapper/timbr_llm_wrapper.py,sha256=sDqDOz0qu8b4WWlagjNceswMVyvEJ8yBWZq2etBh-T0,1362
-langchain_timbr/utils/general.py,sha256=UDKumpar8gPbfhBBf7-7xzuTDj5NCk4JJhctfePhOjU,4960
+langchain_timbr/utils/general.py,sha256=MtY-ZExKJrcBzV3EQNn6G1ESKpiQB2hJCp95BrUayUo,5707
 langchain_timbr/utils/prompt_service.py,sha256=QT7kiq72rQno77z1-tvGGD7HlH_wdTQAl_1teSoKEv4,11373
 langchain_timbr/utils/temperature_supported_models.json,sha256=d3UmBUpG38zDjjB42IoGpHTUaf0pHMBRSPY99ao1a3g,1832
 langchain_timbr/utils/timbr_llm_utils.py,sha256=7-nnTa1T9XOcgIb-aJP3Pgon_gOrCMnDPiIPiAT3UCg,23016
 langchain_timbr/utils/timbr_utils.py,sha256=p21DwTGhF4iKTLDQBkeBaJDFcXt-Hpu1ij8xzQt00Ng,16958
-langchain_timbr-2.0.0.dist-info/METADATA,sha256=Lq9BB4u0TNB7QouHeD7dpKIZZZWmMVUd2Oj85oUYSoY,7184
-langchain_timbr-2.0.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-langchain_timbr-2.0.0.dist-info/licenses/LICENSE,sha256=0ITGFk2alkC7-e--bRGtuzDrv62USIiVyV2Crf3_L_0,1065
-langchain_timbr-2.0.0.dist-info/RECORD,,
+langchain_timbr-2.0.1.dist-info/METADATA,sha256=nBfWOLgJwfsseoeNyhBDlTOCREJyy_Y9EWjcrCtfuoo,7771
+langchain_timbr-2.0.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+langchain_timbr-2.0.1.dist-info/licenses/LICENSE,sha256=0ITGFk2alkC7-e--bRGtuzDrv62USIiVyV2Crf3_L_0,1065
+langchain_timbr-2.0.1.dist-info/RECORD,,