langchain 0.2.6__py3-none-any.whl → 0.2.8__py3-none-any.whl

langchain/chains/combine_documents/base.py

@@ -3,6 +3,7 @@
 from abc import ABC, abstractmethod
 from typing import Any, Dict, List, Optional, Tuple, Type
 
+from langchain_core._api import deprecated
 from langchain_core.callbacks import (
     AsyncCallbackManagerForChainRun,
     CallbackManagerForChainRun,
@@ -157,12 +158,70 @@ class BaseCombineDocumentsChain(Chain, ABC):
         return extra_return_dict
 
 
+@deprecated(
+    since="0.2.7",
+    alternative=(
+        "example in API reference with more detail: "
+        "https://api.python.langchain.com/en/latest/chains/langchain.chains.combine_documents.base.AnalyzeDocumentChain.html"  # noqa: E501
+    ),
+    removal="1.0",
+)
 class AnalyzeDocumentChain(Chain):
     """Chain that splits documents, then analyzes it in pieces.
 
     This chain is parameterized by a TextSplitter and a CombineDocumentsChain.
     This chain takes a single document as input, and then splits it up into chunks
     and then passes those chucks to the CombineDocumentsChain.
+
+    This class is deprecated. See below for alternative implementations which
+    supports async and streaming modes of operation.
+
+    If the underlying combine documents chain takes one ``input_documents`` argument
+    (e.g., chains generated by ``load_summarize_chain``):
+
+        .. code-block:: python
+
+            split_text = lambda x: text_splitter.create_documents([x])
+
+            summarize_document_chain = split_text | chain
+
+    If the underlying chain takes additional arguments (e.g., ``load_qa_chain``, which
+    takes an additional ``question`` argument), we can use the following:
+
+        .. code-block:: python
+
+            from operator import itemgetter
+            from langchain_core.runnables import RunnableLambda, RunnableParallel
+
+            split_text = RunnableLambda(
+                lambda x: text_splitter.create_documents([x])
+            )
+            summarize_document_chain = RunnableParallel(
+                question=itemgetter("question"),
+                input_documents=itemgetter("input_document") | split_text,
+            ) | chain.pick("output_text")
+
+    To additionally return the input parameters, as ``AnalyzeDocumentChain`` does,
+    we can wrap this construction with ``RunnablePassthrough``:
+
+        .. code-block:: python
+
+            from operator import itemgetter
+            from langchain_core.runnables import (
+                RunnableLambda,
+                RunnableParallel,
+                RunnablePassthrough,
+            )
+
+            split_text = RunnableLambda(
+                lambda x: text_splitter.create_documents([x])
+            )
+            summarize_document_chain = RunnablePassthrough.assign(
+                output_text=RunnableParallel(
+                    question=itemgetter("question"),
+                    input_documents=itemgetter("input_document") | split_text,
+                ) | chain.pick("output_text")
+            )
     """
 
     input_key: str = "input_document"  #: :meta private:

langchain/chains/combine_documents/map_reduce.py

@@ -166,8 +166,11 @@ class MapReduceDocumentsChain(BaseCombineDocumentsChain):
     @root_validator(pre=True)
     def get_default_document_variable_name(cls, values: Dict) -> Dict:
         """Get default document variable name, if not provided."""
+        if "llm_chain" not in values:
+            raise ValueError("llm_chain must be provided")
+
+        llm_chain_variables = values["llm_chain"].prompt.input_variables
         if "document_variable_name" not in values:
-            llm_chain_variables = values["llm_chain"].prompt.input_variables
             if len(llm_chain_variables) == 1:
                 values["document_variable_name"] = llm_chain_variables[0]
             else:
@@ -176,7 +179,6 @@ class MapReduceDocumentsChain(BaseCombineDocumentsChain):
                     "multiple llm_chain input_variables"
                 )
         else:
-            llm_chain_variables = values["llm_chain"].prompt.input_variables
             if values["document_variable_name"] not in llm_chain_variables:
                 raise ValueError(
                     f"document_variable_name {values['document_variable_name']} was "

langchain/chains/combine_documents/map_rerank.py

@@ -106,7 +106,7 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
             _output_keys += self.metadata_keys
         return _output_keys
 
-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
     def validate_llm_output(cls, values: Dict) -> Dict:
         """Validate that the combine chain outputs a dictionary."""
         output_parser = values["llm_chain"].prompt.output_parser
@@ -131,8 +131,11 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
     @root_validator(pre=True)
     def get_default_document_variable_name(cls, values: Dict) -> Dict:
         """Get default document variable name, if not provided."""
+        if "llm_chain" not in values:
+            raise ValueError("llm_chain must be provided")
+
+        llm_chain_variables = values["llm_chain"].prompt.input_variables
         if "document_variable_name" not in values:
-            llm_chain_variables = values["llm_chain"].prompt.input_variables
             if len(llm_chain_variables) == 1:
                 values["document_variable_name"] = llm_chain_variables[0]
             else:
@@ -141,7 +144,6 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
                     "multiple llm_chain input_variables"
                 )
         else:
-            llm_chain_variables = values["llm_chain"].prompt.input_variables
             if values["document_variable_name"] not in llm_chain_variables:
                 raise ValueError(
                     f"document_variable_name {values['document_variable_name']} was "

langchain/chains/combine_documents/refine.py

@@ -115,8 +115,11 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
     @root_validator(pre=True)
     def get_default_document_variable_name(cls, values: Dict) -> Dict:
         """Get default document variable name, if not provided."""
+        if "initial_llm_chain" not in values:
+            raise ValueError("initial_llm_chain must be provided")
+
+        llm_chain_variables = values["initial_llm_chain"].prompt.input_variables
         if "document_variable_name" not in values:
-            llm_chain_variables = values["initial_llm_chain"].prompt.input_variables
             if len(llm_chain_variables) == 1:
                 values["document_variable_name"] = llm_chain_variables[0]
             else:
@@ -125,7 +128,6 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
                     "multiple llm_chain input_variables"
                 )
         else:
-            llm_chain_variables = values["initial_llm_chain"].prompt.input_variables
             if values["document_variable_name"] not in llm_chain_variables:
                 raise ValueError(
                     f"document_variable_name {values['document_variable_name']} was "

langchain/chains/combine_documents/stuff.py

@@ -1,4 +1,5 @@
 """Chain that combines documents by stuffing into context."""
+
 from typing import Any, Dict, List, Optional, Tuple
 
 from langchain_core.callbacks import Callbacks
@@ -26,13 +27,14 @@ def create_stuff_documents_chain(
     output_parser: Optional[BaseOutputParser] = None,
     document_prompt: Optional[BasePromptTemplate] = None,
     document_separator: str = DEFAULT_DOCUMENT_SEPARATOR,
+    document_variable_name: str = DOCUMENTS_KEY,
 ) -> Runnable[Dict[str, Any], Any]:
     """Create a chain for passing a list of Documents to a model.
 
     Args:
         llm: Language model.
-        prompt: Prompt template. Must contain input variable "context", which will be
-            used for passing in the formatted documents.
+        prompt: Prompt template. Must contain input variable "context" (override by
+            setting document_variable), which will be used for passing in the formatted documents.
         output_parser: Output parser. Defaults to StrOutputParser.
         document_prompt: Prompt used for formatting each document into a string. Input
             variables can be "page_content" or any metadata keys that are in all
@@ -41,6 +43,8 @@ def create_stuff_documents_chain(
             automatically retrieved from the `Document.metadata` dictionary. Default to
             a prompt that only contains `Document.page_content`.
         document_separator: String separator to use between formatted document strings.
+        document_variable_name: Variable name to use for the formatted documents in the prompt.
+            Defaults to "context".
 
     Returns:
         An LCEL Runnable. The input is a dictionary that must have a "context" key that
@@ -77,11 +81,12 @@ def create_stuff_documents_chain(
 
     def format_docs(inputs: dict) -> str:
         return document_separator.join(
-            format_document(doc, _document_prompt) for doc in inputs[DOCUMENTS_KEY]
+            format_document(doc, _document_prompt)
+            for doc in inputs[document_variable_name]
         )
 
     return (
-        RunnablePassthrough.assign(**{DOCUMENTS_KEY: format_docs}).with_config(
+        RunnablePassthrough.assign(**{document_variable_name: format_docs}).with_config(
             run_name="format_inputs"
         )
         | prompt

langchain/chains/constitutional_ai/base.py

@@ -1,4 +1,5 @@
 """Chain for applying constitutional principles to the outputs of another chain."""
+
 from typing import Any, Dict, List, Optional
 
 from langchain_core.callbacks import CallbackManagerForChainRun

langchain/chains/constitutional_ai/models.py

@@ -1,4 +1,5 @@
 """Models for the Constitutional AI chain."""
+
 from langchain_core.pydantic_v1 import BaseModel
 
 

langchain/chains/constitutional_ai/principles.py

@@ -1,6 +1,7 @@
 """Constitutional principles from https://arxiv.org/pdf/2212.08073.pdf (Bai et al. 2022)
 UnifiedObjectives v0.2 principles ("uo-*") adapted from https://examine.dev/docs/Unified_objectives.pdf (Samwald et al. 2023)
 """
+
 # flake8: noqa
 from typing import Dict
 

langchain/chains/conversation/base.py

@@ -1,6 +1,8 @@
 """Chain that carries on a conversation and calls an LLM."""
+
 from typing import Dict, List
 
+from langchain_core._api import deprecated
 from langchain_core.memory import BaseMemory
 from langchain_core.prompts import BasePromptTemplate
 from langchain_core.pydantic_v1 import Extra, Field, root_validator
@@ -10,9 +12,87 @@ from langchain.chains.llm import LLMChain
 from langchain.memory.buffer import ConversationBufferMemory
 
 
+@deprecated(
+    since="0.2.7",
+    alternative=(
+        "RunnableWithMessageHistory: "
+        "https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html"  # noqa: E501
+    ),
+    removal="1.0",
+)
 class ConversationChain(LLMChain):
     """Chain to have a conversation and load context from memory.
 
+    This class is deprecated in favor of ``RunnableWithMessageHistory``. Please refer
+    to this tutorial for more detail: https://python.langchain.com/v0.2/docs/tutorials/chatbot/
+
+    ``RunnableWithMessageHistory`` offers several benefits, including:
+
+    - Stream, batch, and async support;
+    - More flexible memory handling, including the ability to manage memory
+      outside the chain;
+    - Support for multiple threads.
+
+    Below is a minimal implementation, analogous to using ``ConversationChain`` with
+    the default ``ConversationBufferMemory``:
+
+        .. code-block:: python
+
+            from langchain_core.chat_history import InMemoryChatMessageHistory
+            from langchain_core.runnables.history import RunnableWithMessageHistory
+            from langchain_openai import ChatOpenAI
+
+
+            store = {}  # memory is maintained outside the chain
+
+            def get_session_history(session_id: str) -> InMemoryChatMessageHistory:
+                if session_id not in store:
+                    store[session_id] = InMemoryChatMessageHistory()
+                return store[session_id]
+
+            llm = ChatOpenAI(model="gpt-3.5-turbo-0125")
+
+            chain = RunnableWithMessageHistory(llm, get_session_history)
+            chain.invoke(
+                "Hi I'm Bob.",
+                config={"configurable": {"session_id": "1"}},
+            )  # session_id determines thread
+    Memory objects can also be incorporated into the ``get_session_history`` callable:
+
+        .. code-block:: python
+
+            from langchain.memory import ConversationBufferWindowMemory
+            from langchain_core.chat_history import InMemoryChatMessageHistory
+            from langchain_core.runnables.history import RunnableWithMessageHistory
+            from langchain_openai import ChatOpenAI
+
+
+            store = {}  # memory is maintained outside the chain
+
+            def get_session_history(session_id: str) -> InMemoryChatMessageHistory:
+                if session_id not in store:
+                    store[session_id] = InMemoryChatMessageHistory()
+                    return store[session_id]
+
+                memory = ConversationBufferWindowMemory(
+                    chat_memory=store[session_id],
+                    k=3,
+                    return_messages=True,
+                )
+                assert len(memory.memory_variables) == 1
+                key = memory.memory_variables[0]
+                messages = memory.load_memory_variables({})[key]
+                store[session_id] = InMemoryChatMessageHistory(messages=messages)
+                return store[session_id]
+
+            llm = ChatOpenAI(model="gpt-3.5-turbo-0125")
+
+            chain = RunnableWithMessageHistory(llm, get_session_history)
+            chain.invoke(
+                "Hi I'm Bob.",
+                config={"configurable": {"session_id": "1"}},
+            )  # session_id determines thread
+
     Example:
         .. code-block:: python
 
@@ -45,7 +125,7 @@ class ConversationChain(LLMChain):
         """Use this since so some prompt vars come from history."""
         return [self.input_key]
 
-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
     def validate_prompt_input_variables(cls, values: Dict) -> Dict:
         """Validate that prompt input variables are consistent."""
         memory_keys = values["memory"].memory_variables

langchain/chains/conversational_retrieval/base.py

@@ -1,4 +1,5 @@
 """Chain for chatting with a vector database."""
+
 from __future__ import annotations
 
 import inspect
@@ -480,7 +481,7 @@ class ChatVectorDBChain(BaseConversationalRetrievalChain):
     def _chain_type(self) -> str:
         return "chat-vector-db"
 
-    @root_validator()
+    @root_validator(pre=True)
     def raise_deprecation(cls, values: Dict) -> Dict:
         warnings.warn(
             "`ChatVectorDBChain` is deprecated - "

langchain/chains/elasticsearch_database/base.py

@@ -1,4 +1,5 @@
 """Chain for interacting with Elasticsearch Database."""
+
 from __future__ import annotations
 
 from typing import TYPE_CHECKING, Any, Dict, List, Optional
@@ -56,7 +57,7 @@ class ElasticsearchDatabaseChain(Chain):
         extra = Extra.forbid
         arbitrary_types_allowed = True
 
-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
     def validate_indices(cls, values: dict) -> dict:
         if values["include_indices"] and values["ignore_indices"]:
             raise ValueError(

langchain/chains/hyde/base.py

@@ -2,6 +2,7 @@
 
 https://arxiv.org/abs/2212.10496
 """
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Optional

langchain/chains/llm.py

@@ -1,4 +1,5 @@
 """Chain that just formats a prompt and calls an LLM."""
+
 from __future__ import annotations
 
 import warnings

langchain/chains/llm_checker/base.py

@@ -1,4 +1,5 @@
 """Chain for question-answering with self-verification."""
+
 from __future__ import annotations
 
 import warnings
@@ -118,9 +119,9 @@ class LLMCheckerChain(Chain):
                         values.get("revised_answer_prompt", REVISED_ANSWER_PROMPT),
                     )
                 )
-                values[
-                    "question_to_checked_assertions_chain"
-                ] = question_to_checked_assertions_chain
+                values["question_to_checked_assertions_chain"] = (
+                    question_to_checked_assertions_chain
+                )
         return values
 
     @property

langchain/chains/llm_math/base.py

@@ -1,4 +1,5 @@
 """Chain that interprets a prompt and executes python code to do math."""
+
 from __future__ import annotations
 
 import math

langchain/chains/loading.py

@@ -1,4 +1,5 @@
 """Functionality for loading chains."""
+
 from __future__ import annotations
 
 import json
@@ -408,7 +409,7 @@ def _load_sql_database_chain(config: dict, **kwargs: Any) -> Any:
     if "llm_chain" in config:
         llm_chain_config = config.pop("llm_chain")
         chain = load_chain_from_config(llm_chain_config, **kwargs)
-        return SQLDatabaseChain(llm_chain=chain, database=database, **config)
+        return SQLDatabaseChain(llm_chain=chain, database=database, **config)  # type: ignore[arg-type]
     if "llm" in config:
         llm_config = config.pop("llm")
         llm = load_llm_from_config(llm_config, **kwargs)

langchain/chains/mapreduce.py

@@ -3,6 +3,7 @@
 Splits up a document, sends the smaller parts to the LLM with one prompt,
 then combines the results with another one.
 """
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Mapping, Optional

langchain/chains/moderation.py

@@ -40,7 +40,7 @@ class OpenAIModerationChain(Chain):
     openai_organization: Optional[str] = None
     _openai_pre_1_0: bool = Field(default=None)
 
-    @root_validator()
+    @root_validator(pre=True)
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that api key and python package exists in environment."""
         openai_api_key = get_from_dict_or_env(

langchain/chains/natbot/base.py

@@ -1,4 +1,5 @@
 """Implement an LLM driven browser."""
+
 from __future__ import annotations
 
 import warnings

langchain/chains/openai_functions/base.py

@@ -1,4 +1,5 @@
 """Methods for creating chains that use OpenAI function-calling APIs."""
+
 from typing import (
     Any,
     Callable,

langchain/chains/qa_generation/base.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import json
 from typing import Any, Dict, List, Optional
 
+from langchain_core._api import deprecated
 from langchain_core.callbacks import CallbackManagerForChainRun
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.prompts import BasePromptTemplate
@@ -14,8 +15,53 @@ from langchain.chains.llm import LLMChain
 from langchain.chains.qa_generation.prompt import PROMPT_SELECTOR
 
 
+@deprecated(
+    since="0.2.7",
+    alternative=(
+        "example in API reference with more detail: "
+        "https://api.python.langchain.com/en/latest/chains/langchain.chains.qa_generation.base.QAGenerationChain.html"  # noqa: E501
+    ),
+    removal="1.0",
+)
 class QAGenerationChain(Chain):
-    """Base class for question-answer generation chains."""
+    """Base class for question-answer generation chains.
+
+    This class is deprecated. See below for an alternative implementation.
+
+    Advantages of this implementation include:
+
+    - Supports async and streaming;
+    - Surfaces prompt and text splitter for easier customization;
+    - Use of JsonOutputParser supports JSONPatch operations in streaming mode,
+      as well as robustness to markdown.
+
+        .. code-block:: python
+
+            from langchain.chains.qa_generation.prompt import CHAT_PROMPT as prompt
+            # Note: import PROMPT if using a legacy non-chat model.
+            from langchain_core.output_parsers import JsonOutputParser
+            from langchain_core.runnables import (
+                RunnableLambda,
+                RunnableParallel,
+                RunnablePassthrough,
+            )
+            from langchain_core.runnables.base import RunnableEach
+            from langchain_openai import ChatOpenAI
+            from langchain_text_splitters import RecursiveCharacterTextSplitter
+
+            llm = ChatOpenAI()
+            text_splitter = RecursiveCharacterTextSplitter(chunk_overlap=500)
+            split_text = RunnableLambda(
+                lambda x: text_splitter.create_documents([x])
+            )
+
+            chain = RunnableParallel(
+                text=RunnablePassthrough(),
+                questions=(
+                    split_text | RunnableEach(bound=prompt | llm | JsonOutputParser())
+                )
+            )
+    """
 
     llm_chain: LLMChain
     """LLM Chain that generates responses from user input and context."""

langchain/chains/qa_with_sources/__init__.py

@@ -1,4 +1,5 @@
 """Load question answering with sources chains."""
+
 from langchain.chains.qa_with_sources.loading import load_qa_with_sources_chain
 
 __all__ = ["load_qa_with_sources_chain"]

langchain/chains/qa_with_sources/loading.py

@@ -1,4 +1,5 @@
 """Load question answering with sources chains."""
+
 from __future__ import annotations
 
 from typing import Any, Mapping, Optional, Protocol

langchain/chains/qa_with_sources/vector_db.py

@@ -61,7 +61,7 @@ class VectorDBQAWithSourcesChain(BaseQAWithSourcesChain):
     ) -> List[Document]:
         raise NotImplementedError("VectorDBQAWithSourcesChain does not support async")
 
-    @root_validator()
+    @root_validator(pre=True)
     def raise_deprecation(cls, values: Dict) -> Dict:
         warnings.warn(
             "`VectorDBQAWithSourcesChain` is deprecated - "

langchain/chains/query_constructor/base.py

@@ -1,4 +1,5 @@
 """LLM Chain for turning a user text query into a structured query."""
+
 from __future__ import annotations
 
 import json

langchain/chains/query_constructor/ir.py

@@ -1,4 +1,5 @@
 """Internal representation of a structured query language."""
+
 from langchain_core.structured_query import (
     Comparator,
     Comparison,

langchain/chains/question_answering/chain.py

@@ -1,4 +1,5 @@
 """Load question answering chains."""
+
 from typing import Any, Mapping, Optional, Protocol
 
 from langchain_core.callbacks import BaseCallbackManager, Callbacks

langchain/chains/retrieval_qa/base.py

@@ -1,4 +1,5 @@
 """Chain for question-answering against a vector database."""
+
 from __future__ import annotations
 
 import inspect
@@ -284,7 +285,7 @@ class VectorDBQA(BaseRetrievalQA):
     search_kwargs: Dict[str, Any] = Field(default_factory=dict)
     """Extra search args."""
 
-    @root_validator()
+    @root_validator(pre=True)
     def raise_deprecation(cls, values: Dict) -> Dict:
         warnings.warn(
             "`VectorDBQA` is deprecated - "
@@ -292,7 +293,7 @@ class VectorDBQA(BaseRetrievalQA):
         )
         return values
 
-    @root_validator()
+    @root_validator(pre=True)
     def validate_search_type(cls, values: Dict) -> Dict:
         """Validate search type."""
         if "search_type" in values:

langchain/chains/router/base.py

@@ -1,4 +1,5 @@
 """Base classes for chain routing."""
+
 from __future__ import annotations
 
 from abc import ABC

langchain/chains/router/llm_router.py

@@ -1,4 +1,5 @@
 """Base classes for LLM-powered router chains."""
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Optional, Type, cast
@@ -24,7 +25,7 @@ class LLMRouterChain(RouterChain):
     llm_chain: LLMChain
     """LLM chain used to perform routing"""
 
-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
     def validate_prompt(cls, values: dict) -> dict:
         prompt = values["llm_chain"].prompt
         if prompt.output_parser is None:

langchain/chains/router/multi_prompt.py

@@ -1,4 +1,5 @@
 """Use a single chain to route an input to one of multiple llm chains."""
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Optional

langchain/chains/router/multi_retrieval_qa.py

@@ -1,4 +1,5 @@
 """Use a single chain to route an input to one of multiple retrieval qa chains."""
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Mapping, Optional

langchain/chains/sequential.py

@@ -1,4 +1,5 @@
 """Chain pipeline where the outputs of one step feed directly into next."""
+
 from typing import Any, Dict, List, Optional
 
 from langchain_core.callbacks import (
@@ -152,7 +153,7 @@ class SimpleSequentialChain(Chain):
         """
         return [self.output_key]
 
-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
     def validate_chains(cls, values: Dict) -> Dict:
         """Validate that chains are all single input/output."""
         for chain in values["chains"]: