mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-18 16:16:33 +00:00
multiple: langchain 0.2 in master (#21191)
0.2rc migrations - [x] Move memory - [x] Move remaining retrievers - [x] graph_qa chains - [x] some dependency from evaluation code potentially on math utils - [x] Move openapi chain from `langchain.chains.api.openapi` to `langchain_community.chains.openapi` - [x] Migrate `langchain.chains.ernie_functions` to `langchain_community.chains.ernie_functions` - [x] migrate `langchain/chains/llm_requests.py` to `langchain_community.chains.llm_requests` - [x] Moving `langchain_community.cross_enoders.base:BaseCrossEncoder` -> `langchain_community.retrievers.document_compressors.cross_encoder:BaseCrossEncoder` (namespace not ideal, but it needs to be moved to `langchain` to avoid circular deps) - [x] unit tests langchain -- add pytest.mark.community to some unit tests that will stay in langchain - [x] unit tests community -- move unit tests that depend on community to community - [x] mv integration tests that depend on community to community - [x] mypy checks Other todo - [x] Make deprecation warnings not noisy (need to use warn deprecated and check that things are implemented properly) - [x] Update deprecation messages with timeline for code removal (likely we actually won't be removing things until 0.4 release) -- will give people more time to transition their code. - [ ] Add information to deprecation warning to show users how to migrate their code base using langchain-cli - [ ] Remove any unnecessary requirements in langchain (e.g., is SQLALchemy required?) --------- Co-authored-by: Erick Friis <erick@langchain.dev>
This commit is contained in:
Eugene Yurtsev
GitHub
0
libs/community/tests/unit_tests/chains/__init__.py
Normal file
0
libs/community/tests/unit_tests/chains/__init__.py
Normal file
105
libs/community/tests/unit_tests/chains/test_api.py
Normal file
105
libs/community/tests/unit_tests/chains/test_api.py
Normal file
@@ -0,0 +1,105 @@
|
||||
"""Test LLM Math functionality."""
|
||||
|
||||
import json
|
||||
from typing import Any
|
||||
|
||||
import pytest
|
||||
from langchain.chains.api.base import APIChain
|
||||
from langchain.chains.api.prompt import API_RESPONSE_PROMPT, API_URL_PROMPT
|
||||
from langchain.chains.llm import LLMChain
|
||||
|
||||
from langchain_community.utilities.requests import TextRequestsWrapper
|
||||
from tests.unit_tests.llms.fake_llm import FakeLLM
|
||||
|
||||
|
||||
class FakeRequestsChain(TextRequestsWrapper):
|
||||
"""Fake requests chain just for testing purposes."""
|
||||
|
||||
output: str
|
||||
|
||||
def get(self, url: str, **kwargs: Any) -> str:
|
||||
"""Just return the specified output."""
|
||||
return self.output
|
||||
|
||||
|
||||
def get_test_api_data() -> dict:
|
||||
"""Fake api data to use for testing."""
|
||||
api_docs = """
|
||||
This API endpoint will search the notes for a user.
|
||||
|
||||
Endpoint: https://thisapidoesntexist.com
|
||||
GET /api/notes
|
||||
|
||||
Query parameters:
|
||||
q | string | The search term for notes
|
||||
"""
|
||||
return {
|
||||
"api_docs": api_docs,
|
||||
"question": "Search for notes containing langchain",
|
||||
"api_url": "https://thisapidoesntexist.com/api/notes?q=langchain",
|
||||
"api_response": json.dumps(
|
||||
{
|
||||
"success": True,
|
||||
"results": [{"id": 1, "content": "Langchain is awesome!"}],
|
||||
}
|
||||
),
|
||||
"api_summary": "There is 1 note about langchain.",
|
||||
}
|
||||
|
||||
|
||||
def get_api_chain(**kwargs: Any) -> APIChain:
|
||||
"""Fake LLM API chain for testing."""
|
||||
data = get_test_api_data()
|
||||
test_api_docs = data["api_docs"]
|
||||
test_question = data["question"]
|
||||
test_url = data["api_url"]
|
||||
test_api_response = data["api_response"]
|
||||
test_api_summary = data["api_summary"]
|
||||
|
||||
api_url_query_prompt = API_URL_PROMPT.format(
|
||||
api_docs=test_api_docs, question=test_question
|
||||
)
|
||||
api_response_prompt = API_RESPONSE_PROMPT.format(
|
||||
api_docs=test_api_docs,
|
||||
question=test_question,
|
||||
api_url=test_url,
|
||||
api_response=test_api_response,
|
||||
)
|
||||
queries = {api_url_query_prompt: test_url, api_response_prompt: test_api_summary}
|
||||
fake_llm = FakeLLM(queries=queries)
|
||||
api_request_chain = LLMChain(llm=fake_llm, prompt=API_URL_PROMPT)
|
||||
api_answer_chain = LLMChain(llm=fake_llm, prompt=API_RESPONSE_PROMPT)
|
||||
requests_wrapper = FakeRequestsChain(output=test_api_response)
|
||||
return APIChain(
|
||||
api_request_chain=api_request_chain,
|
||||
api_answer_chain=api_answer_chain,
|
||||
requests_wrapper=requests_wrapper,
|
||||
api_docs=test_api_docs,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
|
||||
def test_api_question() -> None:
|
||||
"""Test simple question that needs API access."""
|
||||
with pytest.raises(ValueError):
|
||||
get_api_chain()
|
||||
with pytest.raises(ValueError):
|
||||
get_api_chain(limit_to_domains=tuple())
|
||||
|
||||
# All domains allowed (not advised)
|
||||
api_chain = get_api_chain(limit_to_domains=None)
|
||||
data = get_test_api_data()
|
||||
assert api_chain.run(data["question"]) == data["api_summary"]
|
||||
|
||||
# Use a domain that's allowed
|
||||
api_chain = get_api_chain(
|
||||
limit_to_domains=["https://thisapidoesntexist.com/api/notes?q=langchain"]
|
||||
)
|
||||
# Attempts to make a request against a domain that's not allowed
|
||||
assert api_chain.run(data["question"]) == data["api_summary"]
|
||||
|
||||
# Use domains that are not valid
|
||||
api_chain = get_api_chain(limit_to_domains=["h", "*"])
|
||||
with pytest.raises(ValueError):
|
||||
# Attempts to make a request against a domain that's not allowed
|
||||
assert api_chain.run(data["question"]) == data["api_summary"]
|
||||
335
libs/community/tests/unit_tests/chains/test_graph_qa.py
Normal file
335
libs/community/tests/unit_tests/chains/test_graph_qa.py
Normal file
@@ -0,0 +1,335 @@
|
||||
import pathlib
|
||||
from typing import Any, Dict, List
|
||||
|
||||
import pandas as pd
|
||||
from langchain.chains.graph_qa.prompts import CYPHER_GENERATION_PROMPT, CYPHER_QA_PROMPT
|
||||
from langchain.memory import ConversationBufferMemory, ReadOnlySharedMemory
|
||||
from langchain_core.prompts import PromptTemplate
|
||||
|
||||
from langchain_community.chains.graph_qa.cypher import (
|
||||
GraphCypherQAChain,
|
||||
construct_schema,
|
||||
extract_cypher,
|
||||
)
|
||||
from langchain_community.chains.graph_qa.cypher_utils import (
|
||||
CypherQueryCorrector,
|
||||
Schema,
|
||||
)
|
||||
from langchain_community.graphs.graph_document import GraphDocument
|
||||
from langchain_community.graphs.graph_store import GraphStore
|
||||
from tests.unit_tests.llms.fake_llm import FakeLLM
|
||||
|
||||
|
||||
class FakeGraphStore(GraphStore):
|
||||
@property
|
||||
def get_schema(self) -> str:
|
||||
"""Returns the schema of the Graph database"""
|
||||
return ""
|
||||
|
||||
@property
|
||||
def get_structured_schema(self) -> Dict[str, Any]:
|
||||
"""Returns the schema of the Graph database"""
|
||||
return {}
|
||||
|
||||
def query(self, query: str, params: dict = {}) -> List[Dict[str, Any]]:
|
||||
"""Query the graph."""
|
||||
return []
|
||||
|
||||
def refresh_schema(self) -> None:
|
||||
"""Refreshes the graph schema information."""
|
||||
pass
|
||||
|
||||
def add_graph_documents(
|
||||
self, graph_documents: List[GraphDocument], include_source: bool = False
|
||||
) -> None:
|
||||
"""Take GraphDocument as input as uses it to construct a graph."""
|
||||
pass
|
||||
|
||||
|
||||
def test_graph_cypher_qa_chain_prompt_selection_1() -> None:
|
||||
# Pass prompts directly. No kwargs is specified.
|
||||
qa_prompt_template = "QA Prompt"
|
||||
cypher_prompt_template = "Cypher Prompt"
|
||||
qa_prompt = PromptTemplate(template=qa_prompt_template, input_variables=[])
|
||||
cypher_prompt = PromptTemplate(template=cypher_prompt_template, input_variables=[])
|
||||
chain = GraphCypherQAChain.from_llm(
|
||||
llm=FakeLLM(),
|
||||
graph=FakeGraphStore(),
|
||||
verbose=True,
|
||||
return_intermediate_steps=False,
|
||||
qa_prompt=qa_prompt,
|
||||
cypher_prompt=cypher_prompt,
|
||||
)
|
||||
assert chain.qa_chain.prompt == qa_prompt
|
||||
assert chain.cypher_generation_chain.prompt == cypher_prompt
|
||||
|
||||
|
||||
def test_graph_cypher_qa_chain_prompt_selection_2() -> None:
|
||||
# Default case. Pass nothing
|
||||
chain = GraphCypherQAChain.from_llm(
|
||||
llm=FakeLLM(),
|
||||
graph=FakeGraphStore(),
|
||||
verbose=True,
|
||||
return_intermediate_steps=False,
|
||||
)
|
||||
assert chain.qa_chain.prompt == CYPHER_QA_PROMPT
|
||||
assert chain.cypher_generation_chain.prompt == CYPHER_GENERATION_PROMPT
|
||||
|
||||
|
||||
def test_graph_cypher_qa_chain_prompt_selection_3() -> None:
|
||||
# Pass non-prompt args only to sub-chains via kwargs
|
||||
memory = ConversationBufferMemory(memory_key="chat_history")
|
||||
readonlymemory = ReadOnlySharedMemory(memory=memory)
|
||||
chain = GraphCypherQAChain.from_llm(
|
||||
llm=FakeLLM(),
|
||||
graph=FakeGraphStore(),
|
||||
verbose=True,
|
||||
return_intermediate_steps=False,
|
||||
cypher_llm_kwargs={"memory": readonlymemory},
|
||||
qa_llm_kwargs={"memory": readonlymemory},
|
||||
)
|
||||
assert chain.qa_chain.prompt == CYPHER_QA_PROMPT
|
||||
assert chain.cypher_generation_chain.prompt == CYPHER_GENERATION_PROMPT
|
||||
|
||||
|
||||
def test_graph_cypher_qa_chain_prompt_selection_4() -> None:
|
||||
# Pass prompt, non-prompt args to subchains via kwargs
|
||||
qa_prompt_template = "QA Prompt"
|
||||
cypher_prompt_template = "Cypher Prompt"
|
||||
memory = ConversationBufferMemory(memory_key="chat_history")
|
||||
readonlymemory = ReadOnlySharedMemory(memory=memory)
|
||||
qa_prompt = PromptTemplate(template=qa_prompt_template, input_variables=[])
|
||||
cypher_prompt = PromptTemplate(template=cypher_prompt_template, input_variables=[])
|
||||
chain = GraphCypherQAChain.from_llm(
|
||||
llm=FakeLLM(),
|
||||
graph=FakeGraphStore(),
|
||||
verbose=True,
|
||||
return_intermediate_steps=False,
|
||||
cypher_llm_kwargs={"prompt": cypher_prompt, "memory": readonlymemory},
|
||||
qa_llm_kwargs={"prompt": qa_prompt, "memory": readonlymemory},
|
||||
)
|
||||
assert chain.qa_chain.prompt == qa_prompt
|
||||
assert chain.cypher_generation_chain.prompt == cypher_prompt
|
||||
|
||||
|
||||
def test_graph_cypher_qa_chain_prompt_selection_5() -> None:
|
||||
# Can't pass both prompt and kwargs at the same time
|
||||
qa_prompt_template = "QA Prompt"
|
||||
cypher_prompt_template = "Cypher Prompt"
|
||||
memory = ConversationBufferMemory(memory_key="chat_history")
|
||||
readonlymemory = ReadOnlySharedMemory(memory=memory)
|
||||
qa_prompt = PromptTemplate(template=qa_prompt_template, input_variables=[])
|
||||
cypher_prompt = PromptTemplate(template=cypher_prompt_template, input_variables=[])
|
||||
try:
|
||||
GraphCypherQAChain.from_llm(
|
||||
llm=FakeLLM(),
|
||||
graph=FakeGraphStore(),
|
||||
verbose=True,
|
||||
return_intermediate_steps=False,
|
||||
qa_prompt=qa_prompt,
|
||||
cypher_prompt=cypher_prompt,
|
||||
cypher_llm_kwargs={"memory": readonlymemory},
|
||||
qa_llm_kwargs={"memory": readonlymemory},
|
||||
)
|
||||
assert False
|
||||
except ValueError:
|
||||
assert True
|
||||
|
||||
|
||||
def test_graph_cypher_qa_chain() -> None:
|
||||
template = """You are a nice chatbot having a conversation with a human.
|
||||
|
||||
Schema:
|
||||
{schema}
|
||||
|
||||
Previous conversation:
|
||||
{chat_history}
|
||||
|
||||
New human question: {question}
|
||||
Response:"""
|
||||
|
||||
prompt = PromptTemplate(
|
||||
input_variables=["schema", "question", "chat_history"], template=template
|
||||
)
|
||||
|
||||
memory = ConversationBufferMemory(memory_key="chat_history")
|
||||
readonlymemory = ReadOnlySharedMemory(memory=memory)
|
||||
prompt1 = (
|
||||
"You are a nice chatbot having a conversation with a human.\n\n "
|
||||
"Schema:\n Node properties are the following:\n\nRelationship "
|
||||
"properties are the following:\n\nThe relationships are the "
|
||||
"following:\n\n\n "
|
||||
"Previous conversation:\n \n\n New human question: "
|
||||
"Test question\n Response:"
|
||||
)
|
||||
|
||||
prompt2 = (
|
||||
"You are a nice chatbot having a conversation with a human.\n\n "
|
||||
"Schema:\n Node properties are the following:\n\nRelationship "
|
||||
"properties are the following:\n\nThe relationships are the "
|
||||
"following:\n\n\n "
|
||||
"Previous conversation:\n Human: Test question\nAI: foo\n\n "
|
||||
"New human question: Test new question\n Response:"
|
||||
)
|
||||
|
||||
llm = FakeLLM(queries={prompt1: "answer1", prompt2: "answer2"})
|
||||
chain = GraphCypherQAChain.from_llm(
|
||||
cypher_llm=llm,
|
||||
qa_llm=FakeLLM(),
|
||||
graph=FakeGraphStore(),
|
||||
verbose=True,
|
||||
return_intermediate_steps=False,
|
||||
cypher_llm_kwargs={"prompt": prompt, "memory": readonlymemory},
|
||||
memory=memory,
|
||||
)
|
||||
chain.run("Test question")
|
||||
chain.run("Test new question")
|
||||
# If we get here without a key error, that means memory
|
||||
# was used properly to create prompts.
|
||||
assert True
|
||||
|
||||
|
||||
def test_no_backticks() -> None:
|
||||
"""Test if there are no backticks, so the original text should be returned."""
|
||||
query = "MATCH (n) RETURN n"
|
||||
output = extract_cypher(query)
|
||||
assert output == query
|
||||
|
||||
|
||||
def test_backticks() -> None:
|
||||
"""Test if there are backticks. Query from within backticks should be returned."""
|
||||
query = "You can use the following query: ```MATCH (n) RETURN n```"
|
||||
output = extract_cypher(query)
|
||||
assert output == "MATCH (n) RETURN n"
|
||||
|
||||
|
||||
def test_exclude_types() -> None:
|
||||
structured_schema = {
|
||||
"node_props": {
|
||||
"Movie": [{"property": "title", "type": "STRING"}],
|
||||
"Actor": [{"property": "name", "type": "STRING"}],
|
||||
"Person": [{"property": "name", "type": "STRING"}],
|
||||
},
|
||||
"rel_props": {},
|
||||
"relationships": [
|
||||
{"start": "Actor", "end": "Movie", "type": "ACTED_IN"},
|
||||
{"start": "Person", "end": "Movie", "type": "DIRECTED"},
|
||||
],
|
||||
}
|
||||
exclude_types = ["Person", "DIRECTED"]
|
||||
output = construct_schema(structured_schema, [], exclude_types)
|
||||
expected_schema = (
|
||||
"Node properties are the following:\n"
|
||||
"Movie {title: STRING},Actor {name: STRING}\n"
|
||||
"Relationship properties are the following:\n\n"
|
||||
"The relationships are the following:\n"
|
||||
"(:Actor)-[:ACTED_IN]->(:Movie)"
|
||||
)
|
||||
assert output == expected_schema
|
||||
|
||||
|
||||
def test_include_types() -> None:
|
||||
structured_schema = {
|
||||
"node_props": {
|
||||
"Movie": [{"property": "title", "type": "STRING"}],
|
||||
"Actor": [{"property": "name", "type": "STRING"}],
|
||||
"Person": [{"property": "name", "type": "STRING"}],
|
||||
},
|
||||
"rel_props": {},
|
||||
"relationships": [
|
||||
{"start": "Actor", "end": "Movie", "type": "ACTED_IN"},
|
||||
{"start": "Person", "end": "Movie", "type": "DIRECTED"},
|
||||
],
|
||||
}
|
||||
include_types = ["Movie", "Actor", "ACTED_IN"]
|
||||
output = construct_schema(structured_schema, include_types, [])
|
||||
expected_schema = (
|
||||
"Node properties are the following:\n"
|
||||
"Movie {title: STRING},Actor {name: STRING}\n"
|
||||
"Relationship properties are the following:\n\n"
|
||||
"The relationships are the following:\n"
|
||||
"(:Actor)-[:ACTED_IN]->(:Movie)"
|
||||
)
|
||||
assert output == expected_schema
|
||||
|
||||
|
||||
def test_include_types2() -> None:
|
||||
structured_schema = {
|
||||
"node_props": {
|
||||
"Movie": [{"property": "title", "type": "STRING"}],
|
||||
"Actor": [{"property": "name", "type": "STRING"}],
|
||||
"Person": [{"property": "name", "type": "STRING"}],
|
||||
},
|
||||
"rel_props": {},
|
||||
"relationships": [
|
||||
{"start": "Actor", "end": "Movie", "type": "ACTED_IN"},
|
||||
{"start": "Person", "end": "Movie", "type": "DIRECTED"},
|
||||
],
|
||||
}
|
||||
include_types = ["Movie", "Actor"]
|
||||
output = construct_schema(structured_schema, include_types, [])
|
||||
expected_schema = (
|
||||
"Node properties are the following:\n"
|
||||
"Movie {title: STRING},Actor {name: STRING}\n"
|
||||
"Relationship properties are the following:\n\n"
|
||||
"The relationships are the following:\n"
|
||||
)
|
||||
assert output == expected_schema
|
||||
|
||||
|
||||
def test_include_types3() -> None:
|
||||
structured_schema = {
|
||||
"node_props": {
|
||||
"Movie": [{"property": "title", "type": "STRING"}],
|
||||
"Actor": [{"property": "name", "type": "STRING"}],
|
||||
"Person": [{"property": "name", "type": "STRING"}],
|
||||
},
|
||||
"rel_props": {},
|
||||
"relationships": [
|
||||
{"start": "Actor", "end": "Movie", "type": "ACTED_IN"},
|
||||
{"start": "Person", "end": "Movie", "type": "DIRECTED"},
|
||||
],
|
||||
}
|
||||
include_types = ["Movie", "Actor", "ACTED_IN"]
|
||||
output = construct_schema(structured_schema, include_types, [])
|
||||
expected_schema = (
|
||||
"Node properties are the following:\n"
|
||||
"Movie {title: STRING},Actor {name: STRING}\n"
|
||||
"Relationship properties are the following:\n\n"
|
||||
"The relationships are the following:\n"
|
||||
"(:Actor)-[:ACTED_IN]->(:Movie)"
|
||||
)
|
||||
assert output == expected_schema
|
||||
|
||||
|
||||
HERE = pathlib.Path(__file__).parent
|
||||
|
||||
UNIT_TESTS_ROOT = HERE.parent
|
||||
|
||||
|
||||
def test_validating_cypher_statements() -> None:
|
||||
cypher_file = str(UNIT_TESTS_ROOT / "data/cypher_corrector.csv")
|
||||
examples = pd.read_csv(cypher_file)
|
||||
examples.fillna("", inplace=True)
|
||||
for _, row in examples.iterrows():
|
||||
schema = load_schemas(row["schema"])
|
||||
corrector = CypherQueryCorrector(schema)
|
||||
assert corrector(row["statement"]) == row["correct_query"]
|
||||
|
||||
|
||||
def load_schemas(str_schemas: str) -> List[Schema]:
|
||||
"""
|
||||
Args:
|
||||
str_schemas: string of schemas
|
||||
"""
|
||||
values = str_schemas.replace("(", "").replace(")", "").split(",")
|
||||
schemas = []
|
||||
for i in range(len(values) // 3):
|
||||
schemas.append(
|
||||
Schema(
|
||||
values[i * 3].strip(),
|
||||
values[i * 3 + 1].strip(),
|
||||
values[i * 3 + 2].strip(),
|
||||
)
|
||||
)
|
||||
return schemas
|
||||
75
libs/community/tests/unit_tests/chains/test_llm.py
Normal file
75
libs/community/tests/unit_tests/chains/test_llm.py
Normal file
@@ -0,0 +1,75 @@
|
||||
"""Test LLM chain."""
|
||||
from tempfile import TemporaryDirectory
|
||||
from typing import Dict, List, Union
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
from langchain.chains.llm import LLMChain
|
||||
from langchain_core.output_parsers import BaseOutputParser
|
||||
from langchain_core.prompts import PromptTemplate
|
||||
|
||||
from tests.unit_tests.llms.fake_llm import FakeLLM
|
||||
|
||||
|
||||
class FakeOutputParser(BaseOutputParser):
|
||||
"""Fake output parser class for testing."""
|
||||
|
||||
def parse(self, text: str) -> Union[str, List[str], Dict[str, str]]:
|
||||
"""Parse by splitting."""
|
||||
return text.split()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def fake_llm_chain() -> LLMChain:
|
||||
"""Fake LLM chain for testing purposes."""
|
||||
prompt = PromptTemplate(input_variables=["bar"], template="This is a {bar}:")
|
||||
return LLMChain(prompt=prompt, llm=FakeLLM(), output_key="text1")
|
||||
|
||||
|
||||
@patch(
|
||||
"langchain_community.llms.loading.get_type_to_cls_dict",
|
||||
lambda: {"fake": lambda: FakeLLM},
|
||||
)
|
||||
def test_serialization(fake_llm_chain: LLMChain) -> None:
|
||||
"""Test serialization."""
|
||||
from langchain.chains.loading import load_chain
|
||||
|
||||
with TemporaryDirectory() as temp_dir:
|
||||
file = temp_dir + "/llm.json"
|
||||
fake_llm_chain.save(file)
|
||||
loaded_chain = load_chain(file)
|
||||
assert loaded_chain == fake_llm_chain
|
||||
|
||||
|
||||
def test_missing_inputs(fake_llm_chain: LLMChain) -> None:
|
||||
"""Test error is raised if inputs are missing."""
|
||||
with pytest.raises(ValueError):
|
||||
fake_llm_chain({"foo": "bar"})
|
||||
|
||||
|
||||
def test_valid_call(fake_llm_chain: LLMChain) -> None:
|
||||
"""Test valid call of LLM chain."""
|
||||
output = fake_llm_chain({"bar": "baz"})
|
||||
assert output == {"bar": "baz", "text1": "foo"}
|
||||
|
||||
# Test with stop words.
|
||||
output = fake_llm_chain({"bar": "baz", "stop": ["foo"]})
|
||||
# Response should be `bar` now.
|
||||
assert output == {"bar": "baz", "stop": ["foo"], "text1": "bar"}
|
||||
|
||||
|
||||
def test_predict_method(fake_llm_chain: LLMChain) -> None:
|
||||
"""Test predict method works."""
|
||||
output = fake_llm_chain.predict(bar="baz")
|
||||
assert output == "foo"
|
||||
|
||||
|
||||
def test_predict_and_parse() -> None:
|
||||
"""Test parsing ability."""
|
||||
prompt = PromptTemplate(
|
||||
input_variables=["foo"], template="{foo}", output_parser=FakeOutputParser()
|
||||
)
|
||||
llm = FakeLLM(queries={"foo": "foo bar"})
|
||||
chain = LLMChain(prompt=prompt, llm=llm)
|
||||
output = chain.predict_and_parse(foo="foo")
|
||||
assert output == ["foo", "bar"]
|
||||
Reference in New Issue
Block a user