langchain-ollama 0.2.2__py3-none-any.whl → 0.2.3__py3-none-any.whl

langchain_ollama/chat_models.py

@@ -1085,8 +1085,16 @@ class ChatOllama(BaseChatModel):
                     "schema must be specified when method is not 'json_mode'. "
                     "Received None."
                 )
-            tool_name = convert_to_openai_tool(schema)["function"]["name"]
-            llm = self.bind_tools([schema], tool_choice=tool_name)
+            formatted_tool = convert_to_openai_tool(schema)
+            tool_name = formatted_tool["function"]["name"]
+            llm = self.bind_tools(
+                [schema],
+                tool_choice=tool_name,
+                structured_output_format={
+                    "kwargs": {"method": method},
+                    "schema": formatted_tool,
+                },
+            )
             if is_pydantic_schema:
                 output_parser: Runnable = PydanticToolsParser(
                     tools=[schema],  # type: ignore[list-item]
@@ -1097,7 +1105,13 @@ class ChatOllama(BaseChatModel):
                     key_name=tool_name, first_tool_only=True
                 )
         elif method == "json_mode":
-            llm = self.bind(format="json")
+            llm = self.bind(
+                format="json",
+                structured_output_format={
+                    "kwargs": {"method": method},
+                    "schema": schema,
+                },
+            )
             output_parser = (
                 PydanticOutputParser(pydantic_object=schema)  # type: ignore[arg-type]
                 if is_pydantic_schema
@@ -1111,7 +1125,13 @@ class ChatOllama(BaseChatModel):
                 )
             if is_pydantic_schema:
                 schema = cast(TypeBaseModel, schema)
-                llm = self.bind(format=schema.model_json_schema())
+                llm = self.bind(
+                    format=schema.model_json_schema(),
+                    structured_output_format={
+                        "kwargs": {"method": method},
+                        "schema": schema,
+                    },
+                )
                 output_parser = PydanticOutputParser(pydantic_object=schema)
             else:
                 if is_typeddict(schema):
@@ -1126,7 +1146,13 @@ class ChatOllama(BaseChatModel):
                 else:
                     # is JSON schema
                     response_format = schema
-                llm = self.bind(format=response_format)
+                llm = self.bind(
+                    format=response_format,
+                    structured_output_format={
+                        "kwargs": {"method": method},
+                        "schema": response_format,
+                    },
+                )
                 output_parser = JsonOutputParser()
         else:
             raise ValueError(

langchain_ollama/embeddings.py

@@ -1,9 +1,6 @@
 """Ollama embeddings models."""
 
-from typing import (
-    List,
-    Optional,
-)
+from typing import Any, Dict, List, Optional
 
 from langchain_core.embeddings import Embeddings
 from ollama import AsyncClient, Client
@@ -144,10 +141,89 @@ class OllamaEmbeddings(BaseModel, Embeddings):
     The async client to use for making requests.
     """
 
+    mirostat: Optional[int] = None
+    """Enable Mirostat sampling for controlling perplexity.
+    (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)"""
+
+    mirostat_eta: Optional[float] = None
+    """Influences how quickly the algorithm responds to feedback
+    from the generated text. A lower learning rate will result in
+    slower adjustments, while a higher learning rate will make
+    the algorithm more responsive. (Default: 0.1)"""
+
+    mirostat_tau: Optional[float] = None
+    """Controls the balance between coherence and diversity
+    of the output. A lower value will result in more focused and
+    coherent text. (Default: 5.0)"""
+
+    num_ctx: Optional[int] = None
+    """Sets the size of the context window used to generate the
+    next token. (Default: 2048)	"""
+
+    num_gpu: Optional[int] = None
+    """The number of GPUs to use. On macOS it defaults to 1 to
+    enable metal support, 0 to disable."""
+
+    num_thread: Optional[int] = None
+    """Sets the number of threads to use during computation.
+    By default, Ollama will detect this for optimal performance.
+    It is recommended to set this value to the number of physical
+    CPU cores your system has (as opposed to the logical number of cores)."""
+
+    repeat_last_n: Optional[int] = None
+    """Sets how far back for the model to look back to prevent
+    repetition. (Default: 64, 0 = disabled, -1 = num_ctx)"""
+
+    repeat_penalty: Optional[float] = None
+    """Sets how strongly to penalize repetitions. A higher value (e.g., 1.5)
+    will penalize repetitions more strongly, while a lower value (e.g., 0.9)
+    will be more lenient. (Default: 1.1)"""
+
+    temperature: Optional[float] = None
+    """The temperature of the model. Increasing the temperature will
+    make the model answer more creatively. (Default: 0.8)"""
+
+    stop: Optional[List[str]] = None
+    """Sets the stop tokens to use."""
+
+    tfs_z: Optional[float] = None
+    """Tail free sampling is used to reduce the impact of less probable
+    tokens from the output. A higher value (e.g., 2.0) will reduce the
+    impact more, while a value of 1.0 disables this setting. (default: 1)"""
+
+    top_k: Optional[int] = None
+    """Reduces the probability of generating nonsense. A higher value (e.g. 100)
+    will give more diverse answers, while a lower value (e.g. 10)
+    will be more conservative. (Default: 40)"""
+
+    top_p: Optional[float] = None
+    """Works together with top-k. A higher value (e.g., 0.95) will lead
+    to more diverse text, while a lower value (e.g., 0.5) will
+    generate more focused and conservative text. (Default: 0.9)"""
+
     model_config = ConfigDict(
         extra="forbid",
     )
 
+    @property
+    def _default_params(self) -> Dict[str, Any]:
+        """Get the default parameters for calling Ollama."""
+        return {
+            "mirostat": self.mirostat,
+            "mirostat_eta": self.mirostat_eta,
+            "mirostat_tau": self.mirostat_tau,
+            "num_ctx": self.num_ctx,
+            "num_gpu": self.num_gpu,
+            "num_thread": self.num_thread,
+            "repeat_last_n": self.repeat_last_n,
+            "repeat_penalty": self.repeat_penalty,
+            "temperature": self.temperature,
+            "stop": self.stop,
+            "tfs_z": self.tfs_z,
+            "top_k": self.top_k,
+            "top_p": self.top_p,
+        }
+
     @model_validator(mode="after")
     def _set_clients(self) -> Self:
         """Set clients to use for ollama."""
@@ -158,7 +234,9 @@ class OllamaEmbeddings(BaseModel, Embeddings):
 
     def embed_documents(self, texts: List[str]) -> List[List[float]]:
         """Embed search docs."""
-        embedded_docs = self._client.embed(self.model, texts)["embeddings"]
+        embedded_docs = self._client.embed(
+            self.model, texts, options=self._default_params
+        )["embeddings"]
         return embedded_docs
 
     def embed_query(self, text: str) -> List[float]:

{langchain_ollama-0.2.2.dist-info → langchain_ollama-0.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langchain-ollama
-Version: 0.2.2
+Version: 0.2.3
 Summary: An integration package connecting Ollama and LangChain
 Home-page: https://github.com/langchain-ai/langchain
 License: MIT
@@ -12,7 +12,7 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: langchain-core (>=0.3.27,<0.4.0)
+Requires-Dist: langchain-core (>=0.3.33,<0.4.0)
 Requires-Dist: ollama (>=0.4.4,<1)
 Project-URL: Repository, https://github.com/langchain-ai/langchain
 Project-URL: Release Notes, https://github.com/langchain-ai/langchain/releases?q=tag%3A%22langchain-ollama%3D%3D0%22&expanded=true

langchain_ollama-0.2.3.dist-info/RECORD

@@ -0,0 +1,9 @@
+langchain_ollama/__init__.py,sha256=SxPRrWcPayJpbwhheTtlqCaPp9ffiAAgZMM5Wc1yYpM,634
+langchain_ollama/chat_models.py,sha256=YDaHyz5t4EfQrMIGJsNFdiPH9LJUOBdrBjlr0qAC8GM,48172
+langchain_ollama/embeddings.py,sha256=rZLgMvuEVqMRo1kPr9pPPrGVpEOes76cwzkXJRged_4,8397
+langchain_ollama/llms.py,sha256=ojnYU0efhN10xhUINu1dCR2Erw79J_mYS6_l45J7Vls,12778
+langchain_ollama/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+langchain_ollama-0.2.3.dist-info/LICENSE,sha256=2btS8uNUDWD_UNjw9ba6ZJt_00aUjEw9CGyK-xIHY8c,1072
+langchain_ollama-0.2.3.dist-info/METADATA,sha256=BZ3HPeJJiDPaEhUjJIC-3SmIhQuNs6r97LS7EOVoPsE,1876
+langchain_ollama-0.2.3.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+langchain_ollama-0.2.3.dist-info/RECORD,,

langchain_ollama-0.2.2.dist-info/RECORD

@@ -1,9 +0,0 @@
-langchain_ollama/__init__.py,sha256=SxPRrWcPayJpbwhheTtlqCaPp9ffiAAgZMM5Wc1yYpM,634
-langchain_ollama/chat_models.py,sha256=_kEf5o3CGtP7JL0HKZ8sIH9xdzktnGbBVdXULR2_sdo,47323
-langchain_ollama/embeddings.py,sha256=svqdPF44qX5qbFpZmLiXrzTC-AldmMlZRS5wBfY-EmA,5056
-langchain_ollama/llms.py,sha256=ojnYU0efhN10xhUINu1dCR2Erw79J_mYS6_l45J7Vls,12778
-langchain_ollama/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-langchain_ollama-0.2.2.dist-info/LICENSE,sha256=2btS8uNUDWD_UNjw9ba6ZJt_00aUjEw9CGyK-xIHY8c,1072
-langchain_ollama-0.2.2.dist-info/METADATA,sha256=8eb8LP6TyzNBiiO60iS5ZMLKK0XW6PQUdKKQPHwYD7M,1876
-langchain_ollama-0.2.2.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-langchain_ollama-0.2.2.dist-info/RECORD,,