Implement saving and loading of RetrievalQA chain (langchain-ai#5818)

<!--
Thank you for contributing to LangChain! Your PR will appear in our
release under the title you set. Please make sure it highlights your
valuable contribution.

Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.

After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.

Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->

<!-- Remove if not applicable -->

Fixes langchain-ai#3983
Mimicing what we do for saving and loading VectorDBQA chain, I added the
logic for RetrievalQA chain.
Also added a unit test. I did not find how we test other chains for
their saving and loading functionality, so I just added a file with one
test case. Let me know if there are recommended ways to test it.

#### Before submitting

<!-- If you're adding a new integration, please include:

1. a test for the integration - favor unit tests that does not rely on
network access.
2. an example notebook showing its use


See contribution guidelines for more information on how to write tests,
lint
etc:


https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->

#### Who can review?

Tag maintainers/contributors who might be interested:
@dev2049
<!-- For a quicker response, figure out the right person to tag with @

  @hwchase17 - project lead

  Tracing / Callbacks
  - @agola11

  Async
  - @agola11

  DataLoaders
  - @eyurtsev

  Models
  - @hwchase17
  - @agola11

  Agents / Tools / Toolkits
  - @vowelparrot

  VectorStores / Retrievers / Memory
  - @dev2049

 -->

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>

langchain/chains/loading.py

@@ -20,7 +20,7 @@
 from langchain.chains.pal.base import PALChain
 from langchain.chains.qa_with_sources.base import QAWithSourcesChain
 from langchain.chains.qa_with_sources.vector_db import VectorDBQAWithSourcesChain
-from langchain.chains.retrieval_qa.base import VectorDBQA
+from langchain.chains.retrieval_qa.base import RetrievalQA, VectorDBQA
 from langchain.chains.sql_database.base import SQLDatabaseChain
 from langchain.llms.loading import load_llm, load_llm_from_config
 from langchain.prompts.loading import load_prompt, load_prompt_from_config
@@ -372,6 +372,28 @@ def _load_vector_db_qa_with_sources_chain(
     )
 
 
+def _load_retrieval_qa(config: dict, **kwargs: Any) -> RetrievalQA:
+    if "retriever" in kwargs:
+        retriever = kwargs.pop("retriever")
+    else:
+        raise ValueError("`retriever` must be present.")
+    if "combine_documents_chain" in config:
+        combine_documents_chain_config = config.pop("combine_documents_chain")
+        combine_documents_chain = load_chain_from_config(combine_documents_chain_config)
+    elif "combine_documents_chain_path" in config:
+        combine_documents_chain = load_chain(config.pop("combine_documents_chain_path"))
+    else:
+        raise ValueError(
+            "One of `combine_documents_chain` or "
+            "`combine_documents_chain_path` must be present."
+        )
+    return RetrievalQA(
+        combine_documents_chain=combine_documents_chain,
+        retriever=retriever,
+        **config,
+    )
+
+
 def _load_vector_db_qa(config: dict, **kwargs: Any) -> VectorDBQA:
     if "vectorstore" in kwargs:
         vectorstore = kwargs.pop("vectorstore")
@@ -459,6 +481,7 @@ def _load_llm_requests_chain(config: dict, **kwargs: Any) -> LLMRequestsChain:
     "sql_database_chain": _load_sql_database_chain,
     "vector_db_qa_with_sources_chain": _load_vector_db_qa_with_sources_chain,
     "vector_db_qa": _load_vector_db_qa,
+    "retrieval_qa": _load_retrieval_qa,
 }
 
 

langchain/chains/retrieval_qa/base.py

@@ -183,6 +183,11 @@ def _get_docs(self, question: str) -> List[Document]:
     async def _aget_docs(self, question: str) -> List[Document]:
         return await self.retriever.aget_relevant_documents(question)
 
+    @property
+    def _chain_type(self) -> str:
+        """Return the chain type."""
+        return "retrieval_qa"
+
 
 class VectorDBQA(BaseRetrievalQA):
     """Chain for question-answering against a vector database."""

tests/integration_tests/chains/test_retrieval_qa.py

@@ -0,0 +1,27 @@
+"""Test RetrievalQA functionality."""
+from pathlib import Path
+
+from langchain.chains import RetrievalQA
+from langchain.chains.loading import load_chain
+from langchain.document_loaders import TextLoader
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.llms import OpenAI
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import Chroma
+
+
+def test_retrieval_qa_saving_loading(tmp_path: Path) -> None:
+    """Test saving and loading."""
+    loader = TextLoader("docs/modules/state_of_the_union.txt")
+    documents = loader.load()
+    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+    texts = text_splitter.split_documents(documents)
+    embeddings = OpenAIEmbeddings()
+    docsearch = Chroma.from_documents(texts, embeddings)
+    qa = RetrievalQA.from_llm(llm=OpenAI(), retriever=docsearch.as_retriever())
+
+    file_path = tmp_path / "RetrievalQA_chain.yaml"
+    qa.save(file_path=file_path)
+    qa_loaded = load_chain(file_path, retriever=docsearch.as_retriever())
+
+    assert qa_loaded == qa