feat: support langchain v1

docs/user-guides/configuration-guide/custom-initialization.md

@@ -37,56 +37,65 @@ def init(app: LLMRails):
 
 ## Custom LLM Provider Registration
 
-To register a custom LLM provider, you need to create a class that inherits from `BaseLanguageModel` and register it using `register_llm_provider`.
+NeMo Guardrails supports two types of custom LLM providers:
+1. **Text Completion Models** (`BaseLLM`) - For models that work with string prompts
+2. **Chat Models** (`BaseChatModel`) - For models that work with message-based conversations
 
-It is important to implement the following methods:
+### Custom Text Completion LLM (BaseLLM)
 
-**Required**:
+To register a custom text completion LLM provider, create a class that inherits from `BaseLLM` and register it using `register_llm_provider`.
 
-- `_call`
-- `_llm_type`
+**Required methods:**
+- `_call` - Synchronous text completion
+- `_llm_type` - Returns the LLM type identifier
 
-**Optional**:
-
-- `_acall`
-- `_astream`
-- `_stream`
-- `_identifying_params`
-
-In other words, to create your custom LLM provider, you need to implement the following interface methods: `_call`, `_llm_type`, and optionally `_acall`, `_astream`, `_stream`, and `_identifying_params`. Here's how you can do it:
+**Optional methods:**
+- `_acall` - Asynchronous text completion (recommended)
+- `_stream` - Streaming text completion
+- `_astream` - Async streaming text completion
+- `_identifying_params` - Returns parameters for model identification
 
 ```python
 from typing import Any, Iterator, List, Optional
 
-from langchain.base_language import BaseLanguageModel
 from langchain_core.callbacks.manager import (
-    CallbackManagerForLLMRun,
     AsyncCallbackManagerForLLMRun,
+    CallbackManagerForLLMRun,
 )
+from langchain_core.language_models import BaseLLM
 from langchain_core.outputs import GenerationChunk
 
 from nemoguardrails.llm.providers import register_llm_provider
 
 
-class MyCustomLLM(BaseLanguageModel):
+class MyCustomTextLLM(BaseLLM):
+    """Custom text completion LLM."""
+
+    @property
+    def _llm_type(self) -> str:
+        return "custom_text_llm"
 
     def _call(
         self,
         prompt: str,
         stop: Optional[List[str]] = None,
         run_manager: Optional[CallbackManagerForLLMRun] = None,
-        **kwargs,
+        **kwargs: Any,
     ) -> str:
-        pass
+        """Synchronous text completion."""
+        # Your implementation here
+        return "Generated text response"
 
     async def _acall(
         self,
         prompt: str,
         stop: Optional[List[str]] = None,
         run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
-        **kwargs,
+        **kwargs: Any,
     ) -> str:
-        pass
+        """Asynchronous text completion (recommended)."""
+        # Your async implementation here
+        return "Generated text response"
 
     def _stream(
         self,
@@ -95,22 +104,122 @@ class MyCustomLLM(BaseLanguageModel):
         run_manager: Optional[CallbackManagerForLLMRun] = None,
         **kwargs: Any,
     ) -> Iterator[GenerationChunk]:
-        pass
+        """Optional: Streaming text completion."""
+        # Yield chunks of text
+        yield GenerationChunk(text="chunk1")
+        yield GenerationChunk(text="chunk2")
+
+
+register_llm_provider("custom_text_llm", MyCustomTextLLM)
+```
+
+### Custom Chat Model (BaseChatModel)
+
+To register a custom chat model, create a class that inherits from `BaseChatModel` and register it using `register_chat_provider`.
+
+**Required methods:**
+- `_generate` - Synchronous chat completion
+- `_llm_type` - Returns the LLM type identifier
+
+**Optional methods:**
+- `_agenerate` - Asynchronous chat completion (recommended)
+- `_stream` - Streaming chat completion
+- `_astream` - Async streaming chat completion
+
+```python
+from typing import Any, Iterator, List, Optional
+
+from langchain_core.callbacks.manager import (
+    AsyncCallbackManagerForLLMRun,
+    CallbackManagerForLLMRun,
+)
+from langchain_core.language_models import BaseChatModel
+from langchain_core.messages import AIMessage, AIMessageChunk, BaseMessage
+from langchain_core.outputs import ChatGeneration, ChatGenerationChunk, ChatResult
+
+from nemoguardrails.llm.providers import register_chat_provider
+
+
+class MyCustomChatModel(BaseChatModel):
+    """Custom chat model."""
 
-    # rest of the implementation
-    ...
+    @property
+    def _llm_type(self) -> str:
+        return "custom_chat_model"
 
-register_llm_provider("custom_llm", MyCustomLLM)
+    def _generate(
+        self,
+        messages: List[BaseMessage],
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[CallbackManagerForLLMRun] = None,
+        **kwargs: Any,
+    ) -> ChatResult:
+        """Synchronous chat completion."""
+        # Convert messages to your model's format and generate response
+        response_text = "Generated chat response"
+
+        message = AIMessage(content=response_text)
+        generation = ChatGeneration(message=message)
+        return ChatResult(generations=[generation])
+
+    async def _agenerate(
+        self,
+        messages: List[BaseMessage],
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
+        **kwargs: Any,
+    ) -> ChatResult:
+        """Asynchronous chat completion (recommended)."""
+        # Your async implementation
+        response_text = "Generated chat response"
+
+        message = AIMessage(content=response_text)
+        generation = ChatGeneration(message=message)
+        return ChatResult(generations=[generation])
+
+    def _stream(
+        self,
+        messages: List[BaseMessage],
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[CallbackManagerForLLMRun] = None,
+        **kwargs: Any,
+    ) -> Iterator[ChatGenerationChunk]:
+        """Optional: Streaming chat completion."""
+        # Yield chunks
+        chunk = ChatGenerationChunk(message=AIMessageChunk(content="chunk1"))
+        yield chunk
+
+
+register_chat_provider("custom_chat_model", MyCustomChatModel)
 ```
 
-You can then use the custom LLM provider in your configuration:
+### Using Custom LLM Providers
+
+After registering your custom provider, you can use it in your configuration:
 
 ```yaml
 models:
   - type: main
-    engine: custom_llm
+    engine: custom_text_llm  # or custom_chat_model
 ```
 
+### Important Notes
+
+1. **Import from langchain-core:** Always import base classes from `langchain_core.language_models`:
+   ```python
+   from langchain_core.language_models import BaseLLM, BaseChatModel
+   ```
+
+2. **Implement async methods:** For better performance, always implement `_acall` (for BaseLLM) or `_agenerate` (for BaseChatModel).
+
+3. **Choose the right base class:**
+   - Use `BaseLLM` for text completion models (prompt → text)
+   - Use `BaseChatModel` for chat models (messages → message)
+
+4. **Registration functions:**
+   - Use `register_llm_provider()` for `BaseLLM` subclasses
+   - Use `register_chat_provider()` for `BaseChatModel` subclasses
+
 ## Custom Embedding Provider Registration
 
 You can also register a custom embedding provider by using the `LLMRails.register_embedding_provider` function.

docs/user-guides/python-api.md

@@ -132,6 +132,8 @@ For convenience, this toolkit also includes a selection of LangChain tools, wrap
 
 ### Chains as Actions
 
+> **⚠️ DEPRECATED**: Chain support is deprecated and will be removed in a future release. Please use [Runnable](https://python.langchain.com/docs/expression_language/) instead. See the [Runnable as Action Guide](langchain/runnable-as-action/README.md) for examples.
+
 You can register a Langchain chain as an action using the [LLMRails.register_action](../api/nemoguardrails.rails.llm.llmrails.md#method-llmrailsregister_action) method:
 
 ```python

examples/configs/rag/custom_rag_output_rails/config.py

@@ -13,9 +13,9 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from langchain.prompts import PromptTemplate
 from langchain_core.language_models.llms import BaseLLM
 from langchain_core.output_parsers import StrOutputParser
+from langchain_core.prompts import PromptTemplate
 
 from nemoguardrails import LLMRails
 from nemoguardrails.actions.actions import ActionResult

examples/configs/rag/multi_kb/config.py

@@ -21,10 +21,19 @@
 import pandas as pd
 import torch
 from gpt4pandas import GPT4Pandas
-from langchain.chains import RetrievalQA
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.vectorstores import FAISS
+
+try:
+    from langchain.chains import RetrievalQA
+    from langchain.embeddings import HuggingFaceEmbeddings
+    from langchain.text_splitter import CharacterTextSplitter
+    from langchain.vectorstores import FAISS
+except ImportError as e:
+    raise ImportError(
+        "Failed to import required LangChain modules. "
+        "Ensure you have installed the correct version of langchain and its dependencies. "
+        f"Original error: {e}"
+    ) from e
+
 from langchain_core.language_models.llms import BaseLLM
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 

examples/configs/rag/multi_kb/tabular_llm.py

@@ -13,14 +13,13 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import asyncio
 from typing import Any, Dict, List, Optional
 
-from langchain.callbacks.manager import (
+from langchain_core.callbacks.manager import (
     AsyncCallbackManagerForLLMRun,
     CallbackManagerForLLMRun,
 )
-from langchain.llms.base import LLM
+from langchain_core.language_models.llms import BaseLLM
 
 
 def query_tabular_data(usr_query: str, gpt: any, raw_data_frame: any):
@@ -58,7 +57,7 @@ def query_tabular_data(usr_query: str, gpt: any, raw_data_frame: any):
     return out, d2.to_string()
 
 
-class TabularLLM(LLM):
+class TabularLLM(BaseLLM):
     """LLM wrapping for GPT4Pandas."""
 
     model: str = ""

examples/configs/rag/pinecone/config.py

@@ -18,11 +18,19 @@
 from typing import Optional
 
 import pinecone
-from langchain.chains import RetrievalQA
-from langchain.docstore.document import Document
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.vectorstores import Pinecone
-from langchain_core.language_models.llms import BaseLLM
+
+try:
+    from langchain.chains import RetrievalQA
+    from langchain.embeddings.openai import OpenAIEmbeddings
+    from langchain.vectorstores import Pinecone
+except ImportError as e:
+    raise ImportError(
+        "Failed to import required LangChain modules. "
+        "Ensure you have installed the correct version of langchain and its dependencies. "
+        f"Original error: {e}"
+    ) from e
+
+from langchain_core.language_models import BaseLLM
 
 from nemoguardrails import LLMRails
 from nemoguardrails.actions import action
@@ -31,7 +39,6 @@
 
 OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
 PINECONE_API_KEY = os.environ.get("PINECONE_API_KEY")
-PINECONE_ENVIRONMENT = os.environ.get("PINECONE_ENVIRONMENT")
 index_name = "nemoguardrailsindex"
 
 LOG_FILENAME = datetime.now().strftime("logs/mylogfile_%H_%M_%d_%m_%Y.log")

examples/scripts/langchain/experiments.py

@@ -15,8 +15,16 @@
 
 import os
 
-from langchain.chains import LLMMathChain
-from langchain.prompts import ChatPromptTemplate
+try:
+    from langchain.chains import LLMMathChain
+except ImportError as e:
+    raise ImportError(
+        "Failed to import required LangChain modules. "
+        "If you're using LangChain >= 1.0.0, ensure langchain-classic is installed. "
+        f"Original error: {e}"
+    ) from e
+
+from langchain_core.prompts import ChatPromptTemplate
 from langchain_core.tools import Tool
 from langchain_openai.chat_models import ChatOpenAI
 from pydantic import BaseModel, Field

nemoguardrails/actions/action_dispatcher.py

@@ -23,12 +23,10 @@
 from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional, Tuple, Type, Union, cast
 
-from langchain.chains.base import Chain
 from langchain_core.runnables import Runnable
 
 from nemoguardrails import utils
 from nemoguardrails.actions.llm.utils import LLMCallException
-from nemoguardrails.logging.callbacks import logging_callbacks
 
 log = logging.getLogger(__name__)
 
@@ -228,27 +226,6 @@ async def execute_action(
                                 f"Synchronous action `{action_name}` has been called."
                             )
 
-                    elif isinstance(fn, Chain):
-                        try:
-                            chain = fn
-
-                            # For chains with only one output key, we use the `arun` function
-                            # to return directly the result.
-                            if len(chain.output_keys) == 1:
-                                result = await chain.arun(
-                                    **params, callbacks=logging_callbacks
-                                )
-                            else:
-                                # Otherwise, we return the dict with the output keys.
-                                result = await chain.acall(
-                                    inputs=params,
-                                    return_only_outputs=True,
-                                    callbacks=logging_callbacks,
-                                )
-                        except NotImplementedError:
-                            # Not ideal, but for now we fall back to sync execution
-                            # if the async is not available
-                            result = fn.run(**params)
                     elif isinstance(fn, Runnable):
                         # If it's a Runnable, we invoke it as well
                         runnable = fn

nemoguardrails/actions/llm/generation.py

@@ -28,8 +28,7 @@
 
 from jinja2 import meta
 from jinja2.sandbox import SandboxedEnvironment
-from langchain_core.language_models import BaseChatModel
-from langchain_core.language_models.llms import BaseLLM
+from langchain_core.language_models import BaseChatModel, BaseLLM
 
 from nemoguardrails.actions.actions import ActionResult, action
 from nemoguardrails.actions.llm.utils import (