langchain-ollama 0.3.3__tar.gz → 0.3.5__tar.gz

{langchain_ollama-0.3.3 → langchain_ollama-0.3.5}/PKG-INFO

@@ -1,14 +1,14 @@
 Metadata-Version: 2.1
 Name: langchain-ollama
-Version: 0.3.3
+Version: 0.3.5
 Summary: An integration package connecting Ollama and LangChain
 License: MIT
 Project-URL: Source Code, https://github.com/langchain-ai/langchain/tree/master/libs/partners/ollama
 Project-URL: Release Notes, https://github.com/langchain-ai/langchain/releases?q=tag%3A%22langchain-ollama%3D%3D0%22&expanded=true
 Project-URL: repository, https://github.com/langchain-ai/langchain
 Requires-Python: >=3.9
-Requires-Dist: ollama<1.0.0,>=0.4.8
-Requires-Dist: langchain-core<1.0.0,>=0.3.60
+Requires-Dist: ollama<1.0.0,>=0.5.1
+Requires-Dist: langchain-core<1.0.0,>=0.3.69
 Description-Content-Type: text/markdown
 
 # langchain-ollama
@@ -21,37 +21,48 @@ This package contains the LangChain integration with Ollama
 pip install -U langchain-ollama
 ```
 
-You will also need to run the Ollama server locally. 
-You can download it [here](https://ollama.com/download).
+For the package to work, you will need to install and run the Ollama server locally ([download](https://ollama.com/download)).
 
-## Chat Models
+To run integration tests (`make integration_tests`), you will need the following models installed in your Ollama server:
+
+- `llama3.1`
+- `deepseek-r1:1.5b`
+
+Install these models by running:
+
+```bash
+ollama pull <name-of-model>
+```
+
+## [Chat Models](https://python.langchain.com/api_reference/ollama/chat_models/langchain_ollama.chat_models.ChatOllama.html#chatollama)
 
 `ChatOllama` class exposes chat models from Ollama.
 
 ```python
 from langchain_ollama import ChatOllama
 
-llm = ChatOllama(model="llama3-groq-tool-use")
+llm = ChatOllama(model="llama3.1")
 llm.invoke("Sing a ballad of LangChain.")
 ```
 
-## Embeddings
+## [Embeddings](https://python.langchain.com/api_reference/ollama/embeddings/langchain_ollama.embeddings.OllamaEmbeddings.html#ollamaembeddings)
 
 `OllamaEmbeddings` class exposes embeddings from Ollama.
 
 ```python
 from langchain_ollama import OllamaEmbeddings
 
-embeddings = OllamaEmbeddings(model="llama3")
+embeddings = OllamaEmbeddings(model="llama3.1")
 embeddings.embed_query("What is the meaning of life?")
 ```
 
-## LLMs
-`OllamaLLM` class exposes LLMs from Ollama.
+## [LLMs](https://python.langchain.com/api_reference/ollama/llms/langchain_ollama.llms.OllamaLLM.html#ollamallm)
+
+`OllamaLLM` class exposes traditional LLMs from Ollama.
 
 ```python
 from langchain_ollama import OllamaLLM
 
-llm = OllamaLLM(model="llama3")
+llm = OllamaLLM(model="llama3.1")
 llm.invoke("The meaning of life is")
 ```

langchain_ollama-0.3.5/README.md

@@ -0,0 +1,55 @@
+# langchain-ollama
+
+This package contains the LangChain integration with Ollama
+
+## Installation
+
+```bash
+pip install -U langchain-ollama
+```
+
+For the package to work, you will need to install and run the Ollama server locally ([download](https://ollama.com/download)).
+
+To run integration tests (`make integration_tests`), you will need the following models installed in your Ollama server:
+
+- `llama3.1`
+- `deepseek-r1:1.5b`
+
+Install these models by running:
+
+```bash
+ollama pull <name-of-model>
+```
+
+## [Chat Models](https://python.langchain.com/api_reference/ollama/chat_models/langchain_ollama.chat_models.ChatOllama.html#chatollama)
+
+`ChatOllama` class exposes chat models from Ollama.
+
+```python
+from langchain_ollama import ChatOllama
+
+llm = ChatOllama(model="llama3.1")
+llm.invoke("Sing a ballad of LangChain.")
+```
+
+## [Embeddings](https://python.langchain.com/api_reference/ollama/embeddings/langchain_ollama.embeddings.OllamaEmbeddings.html#ollamaembeddings)
+
+`OllamaEmbeddings` class exposes embeddings from Ollama.
+
+```python
+from langchain_ollama import OllamaEmbeddings
+
+embeddings = OllamaEmbeddings(model="llama3.1")
+embeddings.embed_query("What is the meaning of life?")
+```
+
+## [LLMs](https://python.langchain.com/api_reference/ollama/llms/langchain_ollama.llms.OllamaLLM.html#ollamallm)
+
+`OllamaLLM` class exposes traditional LLMs from Ollama.
+
+```python
+from langchain_ollama import OllamaLLM
+
+llm = OllamaLLM(model="llama3.1")
+llm.invoke("The meaning of life is")
+```

langchain_ollama-0.3.5/langchain_ollama/_utils.py

@@ -0,0 +1,39 @@
+"""Utility functions for validating Ollama models."""
+
+from httpx import ConnectError
+from ollama import Client, ResponseError
+
+
+def validate_model(client: Client, model_name: str) -> None:
+    """Validate that a model exists in the Ollama instance.
+
+    Args:
+        client: The Ollama client.
+        model_name: The name of the model to validate.
+
+    Raises:
+        ValueError: If the model is not found or if there's a connection issue.
+    """
+    try:
+        response = client.list()
+
+        model_names: list[str] = [model["model"] for model in response["models"]]
+
+        if not any(
+            model_name == m or m.startswith(f"{model_name}:") for m in model_names
+        ):
+            msg = (
+                f"Model `{model_name}` not found in Ollama. Please pull the "
+                f"model (using `ollama pull {model_name}`) or specify a valid "
+                f"model name. Available local models: {', '.join(model_names)}"
+            )
+            raise ValueError(msg)
+    except ConnectError as e:
+        msg = "Failed to connect to Ollama. Please check that Ollama is downloaded, running and accessible. https://ollama.com/download"  # noqa: E501
+        raise ValueError(msg) from e
+    except ResponseError as e:
+        msg = (
+            "Received an error from the Ollama API. "
+            "Please check your Ollama server logs."
+        )
+        raise ValueError(msg) from e