Compare commits

...

6 Commits

Author SHA1 Message Date
Harrison Chase
8c8eb47765 cr 2022-11-20 12:34:41 -08:00
Harrison Chase
68eaf4e5ee reorg smart chains 2022-11-20 12:32:41 -08:00
Harrison Chase
2a84d3d5ca stash 2022-11-20 12:12:07 -08:00
Harrison Chase
45ce74d0bc stash 2022-11-20 06:42:21 -08:00
Harrison Chase
2a2d3323c9 stash 2022-11-20 06:21:01 -08:00
Harrison Chase
6f55fa8ba7 establish router 2022-11-19 17:01:52 -08:00
24 changed files with 461 additions and 407 deletions

View File

@ -32,7 +32,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 2,
"id": "07e96d99",
"metadata": {},
"outputs": [],
@ -64,7 +64,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 3,
"id": "a069c4b6",
"metadata": {},
"outputs": [],
@ -74,7 +74,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 4,
"id": "e603cd7d",
"metadata": {},
"outputs": [
@ -86,32 +86,32 @@
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"What is the age of Olivia Wilde's boyfriend raised to the 0.23 power?\n",
"Thought:\u001b[102m I need to find the age of Olivia Wilde's boyfriend\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Olivia Wilde's boyfriend\n",
"Action: Search\n",
"Action Input: \"Olivia Wilde's boyfriend\"\u001b[0m\n",
"Observation: \u001b[104mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
"Thought:\u001b[102m I need to find the age of Harry Styles\n",
"Observation: \u001b[36;1m\u001b[1;3mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find the age of Harry Styles\n",
"Action: Search\n",
"Action Input: \"Harry Styles age\"\u001b[0m\n",
"Observation: \u001b[104m28 years\u001b[0m\n",
"Thought:\u001b[102m I need to calculate 28 to the 0.23 power\n",
"Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 28 to the 0.23 power\n",
"Action: Calculator\n",
"Action Input: 28^0.23\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"28^0.23\u001b[102m\n",
"28^0.23\u001b[32;1m\u001b[1;3m\n",
"\n",
"```python\n",
"print(28**0.23)\n",
"```\n",
"\u001b[0m\n",
"Answer: \u001b[103m2.1520202182226886\n",
"Answer: \u001b[33;1m\u001b[1;3m2.1520202182226886\n",
"\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[103mAnswer: 2.1520202182226886\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.1520202182226886\n",
"\u001b[0m\n",
"Thought:\u001b[102m I now know the final answer\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 2.1520202182226886\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
@ -122,7 +122,7 @@
"'2.1520202182226886'"
]
},
"execution_count": 6,
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
@ -133,7 +133,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 5,
"id": "a5c07010",
"metadata": {},
"outputs": [
@ -145,35 +145,35 @@
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"Who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\n",
"Thought:\u001b[102m I need to find an album called 'The Storm Before the Calm'\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find an album called 'The Storm Before the Calm'\n",
"Action: Search\n",
"Action Input: \"The Storm Before the Calm album\"\u001b[0m\n",
"Observation: \u001b[104mThe Storm Before the Calm (stylized in all lowercase) is the tenth (and eighth international) studio album by Canadian-American singer-songwriter Alanis ...\u001b[0m\n",
"Thought:\u001b[102m I need to check if Alanis is in the FooBar database\n",
"Observation: \u001b[36;1m\u001b[1;3mThe Storm Before the Calm (stylized in all lowercase) is the tenth (and eighth international) studio album by Canadian-American singer-songwriter Alanis ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to check if Alanis is in the FooBar database\n",
"Action: FooBar DB\n",
"Action Input: \"Does Alanis Morissette exist in the FooBar database?\"\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"Does Alanis Morissette exist in the FooBar database?\n",
"SQLQuery:\u001b[102m SELECT * FROM Artist WHERE Name = 'Alanis Morissette'\u001b[0m\n",
"SQLResult: \u001b[103m[(4, 'Alanis Morissette')]\u001b[0m\n",
"Answer:\u001b[102m Yes\u001b[0m\n",
"SQLQuery:\u001b[32;1m\u001b[1;3m SELECT * FROM Artist WHERE Name = 'Alanis Morissette'\u001b[0m\n",
"SQLResult: \u001b[33;1m\u001b[1;3m[(4, 'Alanis Morissette')]\u001b[0m\n",
"Answer:\u001b[32;1m\u001b[1;3m Yes\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[101m Yes\u001b[0m\n",
"Thought:\u001b[102m I need to find out what albums of Alanis's are in the FooBar database\n",
"Observation: \u001b[38;5;200m\u001b[1;3m Yes\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out what albums of Alanis's are in the FooBar database\n",
"Action: FooBar DB\n",
"Action Input: \"What albums by Alanis Morissette are in the FooBar database?\"\u001b[0m\n",
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"What albums by Alanis Morissette are in the FooBar database?\n",
"SQLQuery:\u001b[102m SELECT Title FROM Album WHERE ArtistId = (SELECT ArtistId FROM Artist WHERE Name = 'Alanis Morissette')\u001b[0m\n",
"SQLResult: \u001b[103m[('Jagged Little Pill',)]\u001b[0m\n",
"Answer:\u001b[102m Jagged Little Pill\u001b[0m\n",
"SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Album.Title FROM Album JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Artist.Name = 'Alanis Morissette'\u001b[0m\n",
"SQLResult: \u001b[33;1m\u001b[1;3m[('Jagged Little Pill',)]\u001b[0m\n",
"Answer:\u001b[32;1m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[101m Jagged Little Pill\u001b[0m\n",
"Thought:\u001b[102m I now know the final answer\n",
"Observation: \u001b[38;5;200m\u001b[1;3m Jagged Little Pill\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
@ -184,7 +184,7 @@
"'The album is by Alanis Morissette and the albums in the FooBar database by her are Jagged Little Pill'"
]
},
"execution_count": 10,
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}

View File

@ -37,14 +37,14 @@
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"Author David Chanoff has collaborated with a U.S. Navy admiral who served as the ambassador to the United Kingdom under which President?\n",
"Thought 1:\u001b[102m I need to search David Chanoff and find the U.S. Navy admiral he\n",
"collaborated with.\n",
"Thought 1:\u001b[32;1m\u001b[1;3m I need to search David Chanoff and find the U.S. Navy admiral he collaborated\n",
"with.\n",
"Action 1: Search[David Chanoff]\u001b[0m\n",
"Observation 1: \u001b[103mDavid Chanoff is a noted author of non-fiction work. His work has typically involved collaborations with the principal protagonist of the work concerned. His collaborators have included; Augustus A. White, Joycelyn Elders, Đoàn Văn Toại, William J. Crowe, Ariel Sharon, Kenneth Good and Felix Zandman. He has also written about a wide range of subjects including literary history, education and foreign for The Washington Post, The New Republic and The New York Times Magazine. He has published more than twelve books.\u001b[0m\n",
"Thought 2:\u001b[102m The U.S. Navy admiral David Chanoff collaborated with is William J. Crowe.\n",
"Observation 1: \u001b[33;1m\u001b[1;3mDavid Chanoff is a noted author of non-fiction work. His work has typically involved collaborations with the principal protagonist of the work concerned. His collaborators have included; Augustus A. White, Joycelyn Elders, Đoàn Văn Toại, William J. Crowe, Ariel Sharon, Kenneth Good and Felix Zandman. He has also written about a wide range of subjects including literary history, education and foreign for The Washington Post, The New Republic and The New York Times Magazine. He has published more than twelve books.\u001b[0m\n",
"Thought 2:\u001b[32;1m\u001b[1;3m The U.S. Navy admiral David Chanoff collaborated with is William J. Crowe.\n",
"Action 2: Search[William J. Crowe]\u001b[0m\n",
"Observation 2: \u001b[103mWilliam James Crowe Jr. (January 2, 1925 October 18, 2007) was a United States Navy admiral and diplomat who served as the 11th chairman of the Joint Chiefs of Staff under Presidents Ronald Reagan and George H. W. Bush, and as the ambassador to the United Kingdom and Chair of the Intelligence Oversight Board under President Bill Clinton.\u001b[0m\n",
"Thought 3:\u001b[102m William J. Crowe served as the ambassador to the United Kingdom under President Bill Clinton. So the answer is Bill Clinton.\n",
"Observation 2: \u001b[33;1m\u001b[1;3mWilliam James Crowe Jr. (January 2, 1925 October 18, 2007) was a United States Navy admiral and diplomat who served as the 11th chairman of the Joint Chiefs of Staff under Presidents Ronald Reagan and George H. W. Bush, and as the ambassador to the United Kingdom and Chair of the Intelligence Oversight Board under President Bill Clinton.\u001b[0m\n",
"Thought 3:\u001b[32;1m\u001b[1;3m William J. Crowe served as the ambassador to the United Kingdom under President Bill Clinton.\n",
"Action 3: Finish[Bill Clinton]\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
@ -68,7 +68,7 @@
{
"cell_type": "code",
"execution_count": null,
"id": "0a6bd3b4",
"id": "2d6f4b1d",
"metadata": {},
"outputs": [],
"source": []

View File

@ -24,19 +24,19 @@
"\n",
"\u001b[1m> Entering new chain...\u001b[0m\n",
"What is the hometown of the reigning men's U.S. Open champion?\n",
"Are follow up questions needed here:\u001b[102m Yes.\n",
"Are follow up questions needed here:\u001b[32;1m\u001b[1;3m Yes.\n",
"Follow up: Who is the reigning men's U.S. Open champion?\u001b[0m\n",
"Intermediate answer: \u001b[103mCarlos Alcaraz won the 2022 Men's single title while Poland's Iga Swiatek won the Women's single title defeating Tunisian's Ons Jabeur..\u001b[0m\u001b[102m\n",
"Follow up: Where is Carlos Alcaraz from?\u001b[0m\n",
"Intermediate answer: \u001b[103mEl Palmar, Murcia, Spain.\u001b[0m\u001b[102m\n",
"So the final answer is: El Palmar, Murcia, Spain\u001b[0m\n",
"Intermediate answer: \u001b[36;1m\u001b[1;3mCarlos Alcaraz\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mFollow up: Where is Carlos Alcaraz from?\u001b[0m\n",
"Intermediate answer: \u001b[36;1m\u001b[1;3mEl Palmar, Spain\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mSo the final answer is: El Palmar, Spain\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'\\nSo the final answer is: El Palmar, Murcia, Spain'"
"'El Palmar, Spain'"
]
},
"execution_count": 1,

View File

@ -8,10 +8,7 @@ with open(Path(__file__).absolute().parents[0] / "VERSION") as _f:
from langchain.chains import (
LLMChain,
LLMMathChain,
MRKLChain,
PythonChain,
ReActChain,
SelfAskWithSearchChain,
SerpAPIChain,
SQLDatabaseChain,
VectorDBQA,
@ -24,6 +21,7 @@ from langchain.prompts import (
Prompt,
PromptTemplate,
)
from langchain.smart_chains import MRKLChain, ReActChain, SelfAskWithSearchChain
from langchain.sql_database import SQLDatabase
from langchain.vectorstores import FAISS, ElasticVectorSearch

View File

@ -1,10 +1,7 @@
"""Chains are easily reusable components which can be linked together."""
from langchain.chains.llm import LLMChain
from langchain.chains.llm_math.base import LLMMathChain
from langchain.chains.mrkl.base import MRKLChain
from langchain.chains.python import PythonChain
from langchain.chains.react.base import ReActChain
from langchain.chains.self_ask_with_search.base import SelfAskWithSearchChain
from langchain.chains.serpapi import SerpAPIChain
from langchain.chains.sql_database.base import SQLDatabaseChain
from langchain.chains.vector_db_qa.base import VectorDBQA
@ -13,10 +10,7 @@ __all__ = [
"LLMChain",
"LLMMathChain",
"PythonChain",
"SelfAskWithSearchChain",
"SerpAPIChain",
"ReActChain",
"SQLDatabaseChain",
"MRKLChain",
"VectorDBQA",
]

View File

@ -1,107 +0,0 @@
"""Chain that implements the ReAct paper from https://arxiv.org/pdf/2210.03629.pdf."""
import re
from typing import Any, Dict, List, Tuple
from pydantic import BaseModel, Extra
from langchain.chains.base import Chain
from langchain.chains.llm import LLMChain
from langchain.chains.react.prompt import PROMPT
from langchain.docstore.base import Docstore
from langchain.docstore.document import Document
from langchain.input import ChainedInput
from langchain.llms.base import LLM
def predict_until_observation(
llm_chain: LLMChain, prompt: str, i: int
) -> Tuple[str, str, str]:
"""Generate text until an observation is needed."""
action_prefix = f"Action {i}: "
stop_seq = f"\nObservation {i}:"
ret_text = llm_chain.predict(input=prompt, stop=[stop_seq])
# Sometimes the LLM forgets to take an action, so we prompt it to.
while not ret_text.split("\n")[-1].startswith(action_prefix):
ret_text += f"\nAction {i}:"
new_text = llm_chain.predict(input=prompt + ret_text, stop=[stop_seq])
ret_text += new_text
# The action block should be the last line.
action_block = ret_text.split("\n")[-1]
action_str = action_block[len(action_prefix) :]
# Parse out the action and the directive.
re_matches = re.search(r"(.*?)\[(.*?)\]", action_str)
if re_matches is None:
raise ValueError(f"Could not parse action directive: {action_str}")
return ret_text, re_matches.group(1), re_matches.group(2)
class ReActChain(Chain, BaseModel):
"""Chain that implements the ReAct paper.
Example:
.. code-block:: python
from langchain import ReActChain, OpenAI
react = ReAct(llm=OpenAI())
"""
llm: LLM
"""LLM wrapper to use."""
docstore: Docstore
"""Docstore to use."""
input_key: str = "question" #: :meta private:
output_key: str = "answer" #: :meta private:
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
arbitrary_types_allowed = True
@property
def input_keys(self) -> List[str]:
"""Expect input key.
:meta private:
"""
return [self.input_key]
@property
def output_keys(self) -> List[str]:
"""Expect output key.
:meta private:
"""
return [self.output_key]
def _call(self, inputs: Dict[str, Any]) -> Dict[str, str]:
question = inputs[self.input_key]
llm_chain = LLMChain(llm=self.llm, prompt=PROMPT)
chained_input = ChainedInput(f"{question}\nThought 1:", verbose=self.verbose)
i = 1
document = None
while True:
ret_text, action, directive = predict_until_observation(
llm_chain, chained_input.input, i
)
chained_input.add(ret_text, color="green")
if action == "Search":
result = self.docstore.search(directive)
if isinstance(result, Document):
document = result
observation = document.summary
else:
document = None
observation = result
elif action == "Lookup":
if document is None:
raise ValueError("Cannot lookup without a successful search first")
observation = document.lookup(directive)
elif action == "Finish":
return {self.output_key: directive}
else:
raise ValueError(f"Got unknown action directive: {action}")
chained_input.add(f"\nObservation {i}: ")
chained_input.add(observation, color="yellow")
chained_input.add(f"\nThought {i + 1}:")
i += 1

View File

@ -1,149 +0,0 @@
"""Chain that does self ask with search."""
from typing import Any, Dict, List
from pydantic import BaseModel, Extra
from langchain.chains.base import Chain
from langchain.chains.llm import LLMChain
from langchain.chains.self_ask_with_search.prompt import PROMPT
from langchain.chains.serpapi import SerpAPIChain
from langchain.input import ChainedInput
from langchain.llms.base import LLM
def extract_answer(generated: str) -> str:
"""Extract answer from text."""
if "\n" not in generated:
last_line = generated
else:
last_line = generated.split("\n")[-1]
if ":" not in last_line:
after_colon = last_line
else:
after_colon = generated.split(":")[-1]
if " " == after_colon[0]:
after_colon = after_colon[1:]
if "." == after_colon[-1]:
after_colon = after_colon[:-1]
return after_colon
def extract_question(generated: str, followup: str) -> str:
"""Extract question from text."""
if "\n" not in generated:
last_line = generated
else:
last_line = generated.split("\n")[-1]
if followup not in last_line:
print("we probably should never get here..." + generated)
if ":" not in last_line:
after_colon = last_line
else:
after_colon = generated.split(":")[-1]
if " " == after_colon[0]:
after_colon = after_colon[1:]
if "?" != after_colon[-1]:
print("we probably should never get here..." + generated)
return after_colon
def get_last_line(generated: str) -> str:
"""Get the last line in text."""
if "\n" not in generated:
last_line = generated
else:
last_line = generated.split("\n")[-1]
return last_line
def greenify(_input: str) -> str:
"""Add green highlighting to text."""
return "\x1b[102m" + _input + "\x1b[0m"
def yellowfy(_input: str) -> str:
"""Add yellow highlighting to text."""
return "\x1b[106m" + _input + "\x1b[0m"
class SelfAskWithSearchChain(Chain, BaseModel):
"""Chain that does self ask with search.
Example:
.. code-block:: python
from langchain import SelfAskWithSearchChain, OpenAI, SerpAPIChain
search_chain = SerpAPIChain()
self_ask = SelfAskWithSearchChain(llm=OpenAI(), search_chain=search_chain)
"""
llm: LLM
"""LLM wrapper to use."""
search_chain: SerpAPIChain
"""Search chain to use."""
input_key: str = "question" #: :meta private:
output_key: str = "answer" #: :meta private:
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
arbitrary_types_allowed = True
@property
def input_keys(self) -> List[str]:
"""Expect input key.
:meta private:
"""
return [self.input_key]
@property
def output_keys(self) -> List[str]:
"""Expect output key.
:meta private:
"""
return [self.output_key]
def _call(self, inputs: Dict[str, Any]) -> Dict[str, str]:
chained_input = ChainedInput(inputs[self.input_key], verbose=self.verbose)
chained_input.add("\nAre follow up questions needed here:")
llm_chain = LLMChain(llm=self.llm, prompt=PROMPT)
intermediate = "\nIntermediate answer:"
followup = "Follow up:"
finalans = "\nSo the final answer is:"
ret_text = llm_chain.predict(input=chained_input.input, stop=[intermediate])
chained_input.add(ret_text, color="green")
while followup in get_last_line(ret_text):
question = extract_question(ret_text, followup)
external_answer = self.search_chain.run(question)
if external_answer is not None:
chained_input.add(intermediate + " ")
chained_input.add(external_answer + ".", color="yellow")
ret_text = llm_chain.predict(
input=chained_input.input, stop=["\nIntermediate answer:"]
)
chained_input.add(ret_text, color="green")
else:
# We only get here in the very rare case that Google returns no answer.
chained_input.add(intermediate + " ")
preds = llm_chain.predict(
input=chained_input.input, stop=["\n" + followup, finalans]
)
chained_input.add(preds, color="green")
if finalans not in ret_text:
chained_input.add(finalans)
ret_text = llm_chain.predict(input=chained_input.input, stop=["\n"])
chained_input.add(ret_text, color="green")
return {self.output_key: ret_text}

View File

@ -0,0 +1,6 @@
"""Smart chains."""
from langchain.smart_chains.mrkl.base import MRKLChain
from langchain.smart_chains.react.base import ReActChain
from langchain.smart_chains.self_ask_with_search.base import SelfAskWithSearchChain
__all__ = ["MRKLChain", "SelfAskWithSearchChain", "ReActChain"]

View File

@ -1,14 +1,12 @@
"""Attempt to implement MRKL systems as described in arxiv.org/pdf/2205.00445.pdf."""
from typing import Any, Callable, Dict, List, NamedTuple, Tuple
from typing import Any, Callable, List, NamedTuple, Optional, Tuple
from pydantic import BaseModel, Extra
from langchain.chains.base import Chain
from langchain.chains.llm import LLMChain
from langchain.chains.mrkl.prompt import BASE_TEMPLATE
from langchain.input import ChainedInput, get_color_mapping
from langchain.llms.base import LLM
from langchain.prompts import BasePromptTemplate, PromptTemplate
from langchain.prompts import PromptTemplate
from langchain.smart_chains.mrkl.prompt import BASE_TEMPLATE
from langchain.smart_chains.router import LLMRouterChain
from langchain.smart_chains.router_expert import ExpertConfig, RouterExpertChain
FINAL_ANSWER_ACTION = "Final Answer: "
@ -30,9 +28,9 @@ class ChainConfig(NamedTuple):
def get_action_and_input(llm_output: str) -> Tuple[str, str]:
"""Parse out the action and input from the LLM output."""
ps = [p for p in llm_output.split("\n") if p]
if ps[-1].startswith(FINAL_ANSWER_ACTION):
if ps[-1].startswith("Final Answer"):
directive = ps[-1][len(FINAL_ANSWER_ACTION) :]
return FINAL_ANSWER_ACTION, directive
return "Final Answer", directive
if not ps[-1].startswith("Action Input: "):
raise ValueError(
"The last line does not have an action input, "
@ -48,33 +46,49 @@ def get_action_and_input(llm_output: str) -> Tuple[str, str]:
return action, action_input.strip(" ").strip('"')
class MRKLChain(Chain, BaseModel):
class MRKLRouterChain(LLMRouterChain):
"""Router for the MRKL chain."""
@property
def observation_prefix(self) -> str:
"""Prefix to append the observation with."""
return "Observation: "
@property
def router_prefix(self) -> str:
"""Prefix to append the router call with."""
return "Thought:"
def __init__(self, llm: LLM, chain_configs: List[ChainConfig], **kwargs: Any):
"""Initialize with an LLM and the chain configs it has access to."""
tools = "\n".join(
[f"{c.action_name}: {c.action_description}" for c in chain_configs]
)
tool_names = ", ".join([chain.action_name for chain in chain_configs])
template = BASE_TEMPLATE.format(tools=tools, tool_names=tool_names)
prompt = PromptTemplate(template=template, input_variables=["input"])
llm_chain = LLMChain(llm=llm, prompt=prompt)
stops = ["\nObservation"]
super().__init__(llm_chain=llm_chain, stops=stops, **kwargs)
def _extract_action_and_input(self, text: str) -> Optional[Tuple[str, str]]:
return get_action_and_input(text)
class MRKLChain(RouterExpertChain):
"""Chain that implements the MRKL system.
Example:
.. code-block:: python
from langchain import OpenAI, Prompt, MRKLChain
from langchain import OpenAI, MRKLChain
from langchain.chains.mrkl.base import ChainConfig
llm = OpenAI(temperature=0)
prompt = PromptTemplate(...)
action_to_chain_map = {...}
mrkl = MRKLChain(
llm=llm,
prompt=prompt,
action_to_chain_map=action_to_chain_map
)
chains = [...]
mrkl = MRKLChain.from_chains(llm=llm, prompt=prompt)
"""
llm: LLM
"""LLM wrapper to use as router."""
prompt: BasePromptTemplate
"""Prompt to use as router."""
action_to_chain_map: Dict[str, Callable]
"""Mapping from action name to chain to execute."""
input_key: str = "question" #: :meta private:
output_key: str = "answer" #: :meta private:
@classmethod
def from_chains(
cls, llm: LLM, chains: List[ChainConfig], **kwargs: Any
@ -114,57 +128,8 @@ class MRKLChain(Chain, BaseModel):
]
mrkl = MRKLChain.from_chains(llm, chains)
"""
tools = "\n".join(
[f"{chain.action_name}: {chain.action_description}" for chain in chains]
)
tool_names = ", ".join([chain.action_name for chain in chains])
template = BASE_TEMPLATE.format(tools=tools, tool_names=tool_names)
prompt = PromptTemplate(template=template, input_variables=["input"])
action_to_chain_map = {chain.action_name: chain.action for chain in chains}
return cls(
llm=llm, prompt=prompt, action_to_chain_map=action_to_chain_map, **kwargs
)
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
arbitrary_types_allowed = True
@property
def input_keys(self) -> List[str]:
"""Expect input key.
:meta private:
"""
return [self.input_key]
@property
def output_keys(self) -> List[str]:
"""Expect output key.
:meta private:
"""
return [self.output_key]
def _call(self, inputs: Dict[str, str]) -> Dict[str, str]:
llm_chain = LLMChain(llm=self.llm, prompt=self.prompt)
chained_input = ChainedInput(
f"{inputs[self.input_key]}\nThought:", verbose=self.verbose
)
color_mapping = get_color_mapping(
list(self.action_to_chain_map.keys()), excluded_colors=["green"]
)
while True:
thought = llm_chain.predict(
input=chained_input.input, stop=["\nObservation"]
)
chained_input.add(thought, color="green")
action, action_input = get_action_and_input(thought)
if action == FINAL_ANSWER_ACTION:
return {self.output_key: action_input}
chain = self.action_to_chain_map[action]
ca = chain(action_input)
chained_input.add("\nObservation: ")
chained_input.add(ca, color=color_mapping[action])
chained_input.add("\nThought:")
router_chain = MRKLRouterChain(llm, chains)
expert_configs = [
ExpertConfig(expert_name=c.action_name, expert=c.action) for c in chains
]
return cls(router_chain=router_chain, expert_configs=expert_configs, **kwargs)

View File

@ -0,0 +1,106 @@
"""Chain that implements the ReAct paper from https://arxiv.org/pdf/2210.03629.pdf."""
import re
from typing import Any, Optional, Tuple
from pydantic import BaseModel
from langchain.chains.llm import LLMChain
from langchain.docstore.base import Docstore
from langchain.docstore.document import Document
from langchain.llms.base import LLM
from langchain.smart_chains.react.prompt import PROMPT
from langchain.smart_chains.router import LLMRouterChain
from langchain.smart_chains.router_expert import ExpertConfig, RouterExpertChain
class ReActRouterChain(LLMRouterChain, BaseModel):
"""Router for the ReAct chin."""
i: int = 1
def __init__(self, llm: LLM, **kwargs: Any):
"""Initialize with the language model."""
llm_chain = LLMChain(llm=llm, prompt=PROMPT)
stops = ["\nObservation 1:"]
super().__init__(llm_chain=llm_chain, stops=stops, **kwargs)
def _fix_text(self, text: str) -> str:
return text + f"\nAction {self.i}:"
def _extract_action_and_input(self, text: str) -> Optional[Tuple[str, str]]:
action_prefix = f"Action {self.i}: "
if not text.split("\n")[-1].startswith(action_prefix):
return None
self.i += 1
self.stops = [f"\nObservation {self.i}:"]
action_block = text.split("\n")[-1]
action_str = action_block[len(action_prefix) :]
# Parse out the action and the directive.
re_matches = re.search(r"(.*?)\[(.*?)\]", action_str)
if re_matches is None:
raise ValueError(f"Could not parse action directive: {action_str}")
return re_matches.group(1), re_matches.group(2)
@property
def finish_action_name(self) -> str:
"""Name of the action of when to finish the chain."""
return "Finish"
@property
def observation_prefix(self) -> str:
"""Prefix to append the observation with."""
return f"Observation {self.i - 1}: "
@property
def router_prefix(self) -> str:
"""Prefix to append the router call with."""
return f"Thought {self.i}:"
class DocstoreExplorer:
"""Class to assist with exploration of a document store."""
def __init__(self, docstore: Docstore):
"""Initialize with a docstore, and set initial document to None."""
self.docstore = docstore
self.document: Optional[Document] = None
def search(self, term: str) -> str:
"""Search for a term in the docstore, and if found save."""
result = self.docstore.search(term)
if isinstance(result, Document):
self.document = result
return self.document.summary
else:
self.document = None
return result
def lookup(self, term: str) -> str:
"""Lookup a term in document (if saved)."""
if self.document is None:
raise ValueError("Cannot lookup without a successful search first")
return self.document.lookup(term)
class ReActChain(RouterExpertChain):
"""Chain that implements the ReAct paper.
Example:
.. code-block:: python
from langchain import ReActChain, OpenAI
react = ReAct(llm=OpenAI())
"""
def __init__(self, llm: LLM, docstore: Docstore, **kwargs: Any):
"""Initialize with the LLM and a docstore."""
router_chain = ReActRouterChain(llm)
docstore_explorer = DocstoreExplorer(docstore)
expert_configs = [
ExpertConfig(expert_name="Search", expert=docstore_explorer.search),
ExpertConfig(expert_name="Lookup", expert=docstore_explorer.lookup),
]
super().__init__(
router_chain=router_chain, expert_configs=expert_configs, **kwargs
)

View File

@ -0,0 +1,90 @@
"""Chain that takes in an input and produces an action and action input."""
from abc import ABC, abstractmethod
from typing import Dict, List, Optional, Tuple
from pydantic import BaseModel
from langchain.chains.base import Chain
from langchain.chains.llm import LLMChain
class RouterChain(Chain, BaseModel, ABC):
"""Chain responsible for deciding the action to take."""
input_key: str = "input_text" #: :meta private:
action_key: str = "action" #: :meta private:
action_input_key: str = "action_input" #: :meta private:
log_key: str = "log" #: :meta private:
@property
def input_keys(self) -> List[str]:
"""Will be the input key.
:meta private:
"""
return [self.input_key]
@property
def output_keys(self) -> List[str]:
"""Return three keys: the action, the action input, and the log.
:meta private:
"""
return [self.action_key, self.action_input_key, self.log_key]
@abstractmethod
def get_action_and_input(self, text: str) -> Tuple[str, str, str]:
"""Return action, action input, and log (in that order)."""
@property
@abstractmethod
def observation_prefix(self) -> str:
"""Prefix to append the observation with."""
@property
@abstractmethod
def router_prefix(self) -> str:
"""Prefix to append the router call with."""
@property
def finish_action_name(self) -> str:
"""Name of the action of when to finish the chain."""
return "Final Answer"
def _call(self, inputs: Dict[str, str]) -> Dict[str, str]:
action, action_input, log = self.get_action_and_input(inputs[self.input_key])
return {
self.action_key: action,
self.action_input_key: action_input,
self.log_key: log,
}
class LLMRouterChain(RouterChain, BaseModel, ABC):
"""RouterChain that uses an LLM."""
llm_chain: LLMChain
stops: Optional[List[str]]
@abstractmethod
def _extract_action_and_input(self, text: str) -> Optional[Tuple[str, str]]:
"""Extract action and action input from llm output."""
def _fix_text(self, text: str) -> str:
"""Fix the text."""
raise ValueError("fix_text not implemented for this router.")
def get_action_and_input(self, text: str) -> Tuple[str, str, str]:
"""Return action, action input, and log (in that order)."""
input_key = self.llm_chain.input_keys[0]
inputs = {input_key: text, "stop": self.stops}
full_output = self.llm_chain.predict(**inputs)
parsed_output = self._extract_action_and_input(full_output)
while parsed_output is None:
full_output = self._fix_text(full_output)
inputs = {input_key: text + full_output, "stop": self.stops}
output = self.llm_chain.predict(**inputs)
full_output += output
parsed_output = self._extract_action_and_input(full_output)
action, action_input = parsed_output
return action, action_input, full_output

View File

@ -0,0 +1,77 @@
"""Router-Expert framework."""
from typing import Callable, Dict, List, NamedTuple
from pydantic import BaseModel, Extra
from langchain.chains.base import Chain
from langchain.input import ChainedInput, get_color_mapping
from langchain.smart_chains.router import RouterChain
class ExpertConfig(NamedTuple):
"""Configuration for experts."""
expert_name: str
expert: Callable[[str], str]
class RouterExpertChain(Chain, BaseModel):
"""Chain that implements the Router/Expert system."""
router_chain: RouterChain
"""Router chain."""
expert_configs: List[ExpertConfig]
"""Expert configs this chain has access to."""
starter_string: str = "\n"
"""String to put after user input but before first router."""
input_key: str = "question" #: :meta private:
output_key: str = "answer" #: :meta private:
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
arbitrary_types_allowed = True
@property
def input_keys(self) -> List[str]:
"""Expect input key.
:meta private:
"""
return [self.input_key]
@property
def output_keys(self) -> List[str]:
"""Expect output key.
:meta private:
"""
return [self.output_key]
def _call(self, inputs: Dict[str, str]) -> Dict[str, str]:
action_to_chain_map = {e.expert_name: e.expert for e in self.expert_configs}
starter_string = (
inputs[self.input_key]
+ self.starter_string
+ self.router_chain.router_prefix
)
chained_input = ChainedInput(
starter_string,
verbose=self.verbose,
)
color_mapping = get_color_mapping(
[c.expert_name for c in self.expert_configs], excluded_colors=["green"]
)
while True:
action, action_input, log = self.router_chain.get_action_and_input(
chained_input.input
)
chained_input.add(log, color="green")
if action == self.router_chain.finish_action_name:
return {self.output_key: action_input}
chain = action_to_chain_map[action]
ca = chain(action_input)
chained_input.add(f"\n{self.router_chain.observation_prefix}")
chained_input.add(ca, color=color_mapping[action])
chained_input.add(f"\n{self.router_chain.router_prefix}")

View File

@ -0,0 +1,79 @@
"""Chain that does self ask with search."""
from typing import Any, Tuple
from langchain.chains.llm import LLMChain
from langchain.chains.serpapi import SerpAPIChain
from langchain.llms.base import LLM
from langchain.smart_chains.router import LLMRouterChain
from langchain.smart_chains.router_expert import ExpertConfig, RouterExpertChain
from langchain.smart_chains.self_ask_with_search.prompt import PROMPT
class SelfAskWithSearchRouter(LLMRouterChain):
"""Router for the self-ask-with-search paper."""
def __init__(self, llm: LLM, **kwargs: Any):
"""Initialize with an LLM."""
llm_chain = LLMChain(llm=llm, prompt=PROMPT)
super().__init__(llm_chain=llm_chain, **kwargs)
def _extract_action_and_input(self, text: str) -> Tuple[str, str]:
followup = "Follow up:"
if "\n" not in text:
last_line = text
else:
last_line = text.split("\n")[-1]
if followup not in last_line:
finish_string = "So the final answer is: "
if finish_string not in last_line:
raise ValueError("We should probably never get here")
return "Final Answer", text[len(finish_string) :]
if ":" not in last_line:
after_colon = last_line
else:
after_colon = text.split(":")[-1]
if " " == after_colon[0]:
after_colon = after_colon[1:]
if "?" != after_colon[-1]:
print("we probably should never get here..." + text)
return "Intermediate Answer", after_colon
@property
def observation_prefix(self) -> str:
"""Prefix to append the observation with."""
return "Intermediate answer: "
@property
def router_prefix(self) -> str:
"""Prefix to append the router call with."""
return ""
class SelfAskWithSearchChain(RouterExpertChain):
"""Chain that does self ask with search.
Example:
.. code-block:: python
from langchain import SelfAskWithSearchChain, OpenAI, SerpAPIChain
search_chain = SerpAPIChain()
self_ask = SelfAskWithSearchChain(llm=OpenAI(), search_chain=search_chain)
"""
def __init__(self, llm: LLM, search_chain: SerpAPIChain, **kwargs: Any):
"""Initialize with just an LLM and a search chain."""
intermediate = "\nIntermediate answer:"
router = SelfAskWithSearchRouter(llm, stops=[intermediate])
expert_configs = [
ExpertConfig(expert_name="Intermediate Answer", expert=search_chain.run)
]
super().__init__(
router_chain=router,
expert_configs=expert_configs,
starter_string="\nAre follow up questions needed here:",
**kwargs
)

View File

@ -1,8 +1,8 @@
"""Integration test for self ask with search."""
from langchain.chains.react.base import ReActChain
from langchain.docstore.wikipedia import Wikipedia
from langchain.llms.openai import OpenAI
from langchain.smart_chains.react.base import ReActChain
def test_react() -> None:

View File

@ -1,7 +1,7 @@
"""Integration test for self ask with search."""
from langchain.chains.self_ask_with_search.base import SelfAskWithSearchChain
from langchain.chains.serpapi import SerpAPIChain
from langchain.llms.openai import OpenAI
from langchain.smart_chains.self_ask_with_search.base import SelfAskWithSearchChain
def test_self_ask_with_search() -> None:

View File

@ -0,0 +1 @@
"""Test smart chain functionality."""

View File

@ -2,9 +2,13 @@
import pytest
from langchain.chains.mrkl.base import ChainConfig, MRKLChain, get_action_and_input
from langchain.chains.mrkl.prompt import BASE_TEMPLATE
from langchain.prompts import PromptTemplate
from langchain.smart_chains.mrkl.base import (
ChainConfig,
MRKLRouterChain,
get_action_and_input,
)
from langchain.smart_chains.mrkl.prompt import BASE_TEMPLATE
from tests.unit_tests.llms.fake_llm import FakeLLM
@ -59,12 +63,12 @@ def test_from_chains() -> None:
action_name="bar", action=lambda x: "bar", action_description="foobar2"
),
]
mrkl_chain = MRKLChain.from_chains(FakeLLM(), chain_configs)
router_chain = MRKLRouterChain(FakeLLM(), chain_configs)
expected_tools_prompt = "foo: foobar1\nbar: foobar2"
expected_tool_names = "foo, bar"
expected_template = BASE_TEMPLATE.format(
tools=expected_tools_prompt, tool_names=expected_tool_names
)
prompt = mrkl_chain.prompt
prompt = router_chain.llm_chain.prompt
assert isinstance(prompt, PromptTemplate)
assert prompt.template == expected_template

View File

@ -4,12 +4,11 @@ from typing import Any, List, Mapping, Optional, Union
import pytest
from langchain.chains.llm import LLMChain
from langchain.chains.react.base import ReActChain, predict_until_observation
from langchain.docstore.base import Docstore
from langchain.docstore.document import Document
from langchain.llms.base import LLM
from langchain.prompts.prompt import PromptTemplate
from langchain.smart_chains.react.base import ReActChain, ReActRouterChain
_PAGE_CONTENT = """This is a page about LangChain.
@ -53,8 +52,8 @@ def test_predict_until_observation_normal() -> None:
"""Test predict_until_observation when observation is made normally."""
outputs = ["foo\nAction 1: search[foo]"]
fake_llm = FakeListLLM(outputs)
fake_llm_chain = LLMChain(llm=fake_llm, prompt=_FAKE_PROMPT)
ret_text, action, directive = predict_until_observation(fake_llm_chain, "", 1)
router_chain = ReActRouterChain(llm=fake_llm)
action, directive, ret_text = router_chain.get_action_and_input("")
assert ret_text == outputs[0]
assert action == "search"
assert directive == "foo"
@ -64,22 +63,13 @@ def test_predict_until_observation_repeat() -> None:
"""Test when no action is generated initially."""
outputs = ["foo", " search[foo]"]
fake_llm = FakeListLLM(outputs)
fake_llm_chain = LLMChain(llm=fake_llm, prompt=_FAKE_PROMPT)
ret_text, action, directive = predict_until_observation(fake_llm_chain, "", 1)
router_chain = ReActRouterChain(llm=fake_llm)
action, directive, ret_text = router_chain.get_action_and_input("")
assert ret_text == "foo\nAction 1: search[foo]"
assert action == "search"
assert directive == "foo"
def test_predict_until_observation_error() -> None:
"""Test handling of generation of text that cannot be parsed."""
outputs = ["foo\nAction 1: foo"]
fake_llm = FakeListLLM(outputs)
fake_llm_chain = LLMChain(llm=fake_llm, prompt=_FAKE_PROMPT)
with pytest.raises(ValueError):
predict_until_observation(fake_llm_chain, "", 1)
def test_react_chain() -> None:
"""Test react chain."""
responses = [