ChatPromptTemplate.from_template returns serialized object from vectorstore retriever

[gpt-partners]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

from operator import itemgetter

from langchain_community.vectorstores import FAISS
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI, OpenAIEmbeddings

vectorstore = FAISS.from_texts(
["harrison worked at kensho"], embedding=OpenAIEmbeddings()
)
retriever = vectorstore.as_retriever()

template = """Answer the question based only on the following context:
{context}

Question: {question}

Answer in the following language: {language}
"""
prompt = ChatPromptTemplate.from_template(template)

chain = (
{
"context": itemgetter("question") | retriever,
"question": itemgetter("question"),
"language": itemgetter("language"),
}
| prompt
)

chain.invoke({"question": "where did harrison work", "language": "italian"})

Error Message and Stack Trace (if applicable)

ChatPromptValue(messages=[HumanMessage(content="Answer the question based only on the following context:\n[Document(page_content='harrison worked at kensho')]\n\nQuestion: where did harrison work\n\nAnswer in the following language: italian\n")])

Description

• When I build a prompt the content property of HumanMessage includes the serialized form of the Document
• Instead I expect only the page_content to be included as context information, such as

ChatPromptValue(messages=[HumanMessage(content="Answer the question based only on the following context:\n"""\nharrison worked at kensho\n"""\n\nQuestion: where did harrison work\n\nAnswer in the following language: italian\n")])

• I wonder if this behaviour is on purpose (can the LLM read the serialized object well, is it of any help for the answer) or is it a bug?

System Info

pip install --upgrade --quiet langchain langchain-openai