Skip to content

The agent engineering platform.

[feat] Added backwards compatibility for OllamaEmbeddings initialization (migration from `langchain_community.embeddings` to `langchain_ollama.embeddings` (#29296)

Syed Baqar Abbasf1753193036d
diff --git a/libs/partners/ollama/langchain_ollama/embeddings.py b/libs/partners/ollama/langchain_ollama/embeddings.py
index 80783ec18b..6105a3ba0d 100644
--- a/libs/partners/ollama/langchain_ollama/embeddings.py
+++ b/libs/partners/ollama/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]: