Spaces:
Runtime error
Runtime error
experimenting with outputting item components
Browse files
langhchain_generate_components.py
ADDED
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
"""
|
2 |
+
#TODO: make a agent that uses HUMAMN as a tool to get:
|
3 |
+
- Purpose of science experiment
|
4 |
+
- What fields of study do they already know of
|
5 |
+
|
6 |
+
#IDEA: Platform generate more indepth experiments by generaing a data set and generate / collect scienfic data
|
7 |
+
|
8 |
+
### Chatbot
|
9 |
+
the chatbot helps the BOUNTY_BOARD_CHAIN generate science experiments
|
10 |
+
|
11 |
+
### EXPERIMENT and Provide feedback on experiments
|
12 |
+
|
13 |
+
### Interrgration
|
14 |
+
|
15 |
+
- I need to intergrate this code into the app. This includes creating an id for each post, and potentially and a comment section for each "Experiment"
|
16 |
+
- I addition i need to generate a mostly pinecone retriever to geenrate scientific experiments from the "community vectore search"
|
17 |
+
- potentially have prenium users store their private data, but i may not implement this during the hackathon
|
18 |
+
"""
|
19 |
+
|
20 |
+
# https://python.langchain.com/docs/modules/model_io/output_parsers/types/structured
|
21 |
+
from langchain.output_parsers import ResponseSchema, StructuredOutputParser
|
22 |
+
from langchain.prompts import PromptTemplate
|
23 |
+
from langchain_openai import ChatOpenAI
|
24 |
+
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
|
25 |
+
from langchain.memory import ConversationBufferMemory
|
26 |
+
from langchain_core.runnables import RunnablePassthrough
|
27 |
+
from langchain.retrievers import ArxivRetriever, pubmed
|
28 |
+
from langchain_core.output_parsers import StrOutputParser
|
29 |
+
from langchain.retrievers import ArxivRetriever
|
30 |
+
from langchain.retrievers import PubMedRetriever
|
31 |
+
from langchain.retrievers import WikipediaRetriever
|
32 |
+
from operator import itemgetter
|
33 |
+
# import dotenv
|
34 |
+
import os
|
35 |
+
from dotenv import load_dotenv
|
36 |
+
|
37 |
+
os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
|
38 |
+
|
39 |
+
|
40 |
+
# The scheme for creating experiments
|
41 |
+
experiment_schema = [
|
42 |
+
ResponseSchema(name="Material", description="list of materials need to perfrom the experiments please be specific", type="list"),
|
43 |
+
]
|
44 |
+
|
45 |
+
|
46 |
+
maker_schema = [
|
47 |
+
ResponseSchema(name="Material", description="The base components needed to create this items from scratch DIY This item must be exact and not an estimation", type="list"),
|
48 |
+
]
|
49 |
+
|
50 |
+
experiment_output_parser = StructuredOutputParser.from_response_schemas(experiment_schema)
|
51 |
+
maker_output_parser = StructuredOutputParser.from_response_schemas(maker_schema)
|
52 |
+
|
53 |
+
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
|
54 |
+
|
55 |
+
format_instructions = experiment_output_parser.get_format_instructions()
|
56 |
+
|
57 |
+
|
58 |
+
experiment_prompt = PromptTemplate(
|
59 |
+
template="You must generate well detailed science experiments.\n{format_instructions}\n{question}\n{context}",
|
60 |
+
input_variables=["question"],
|
61 |
+
partial_variables={"format_instructions": format_instructions},
|
62 |
+
memory = memory
|
63 |
+
)
|
64 |
+
|
65 |
+
maker_prompt = PromptTemplate(
|
66 |
+
template="You must generate a well detailed list of items for creating a given item from scratch.\n{format_instructions}\n{question}\n{context}",
|
67 |
+
input_variables=["question"],
|
68 |
+
partial_variables={"format_instructions": format_instructions},
|
69 |
+
memory = memory
|
70 |
+
)
|
71 |
+
|
72 |
+
|
73 |
+
def join_strings(*args: str) -> str:
|
74 |
+
"""
|
75 |
+
Join an arbitrary number of strings into one string.
|
76 |
+
|
77 |
+
Args:
|
78 |
+
*args: Variable number of strings to join.
|
79 |
+
|
80 |
+
Returns:
|
81 |
+
str: Joined string.
|
82 |
+
"""
|
83 |
+
return ''.join(args)
|
84 |
+
|
85 |
+
def format_docs(docs):
|
86 |
+
return "\n\n".join([join_strings(d.page_content, d.metadata['Entry ID'],d.metadata['Title'], ) for d in docs])
|
87 |
+
|
88 |
+
|
89 |
+
arxiv_retriever = ArxivRetriever(load_max_docs=2)
|
90 |
+
|
91 |
+
# model = ChatOpenAI(temperature=0)
|
92 |
+
model = ChatOpenAI(temperature=0,model="gpt-4")
|
93 |
+
|
94 |
+
|
95 |
+
arxiv_retriever = ArxivRetriever(load_max_docs=2)
|
96 |
+
|
97 |
+
pub_med_retriever = PubMedRetriever()
|
98 |
+
|
99 |
+
wikipedia_retriever = WikipediaRetriever()
|
100 |
+
|
101 |
+
arxiv_chain = (
|
102 |
+
{"context": arxiv_retriever, "question": RunnablePassthrough()}
|
103 |
+
| experiment_prompt
|
104 |
+
| model
|
105 |
+
| experiment_output_parser
|
106 |
+
)
|
107 |
+
|
108 |
+
pub_med_chain = (
|
109 |
+
{"context": pub_med_retriever, "question": RunnablePassthrough()}
|
110 |
+
| experiment_prompt
|
111 |
+
| model
|
112 |
+
| experiment_output_parser
|
113 |
+
)
|
114 |
+
|
115 |
+
wikipedia_chain = (
|
116 |
+
{"context": wikipedia_retriever, "question": RunnablePassthrough()}
|
117 |
+
| experiment_prompt
|
118 |
+
| model
|
119 |
+
| experiment_output_parser
|
120 |
+
)
|
121 |
+
|
122 |
+
maker_wikipedia_chain = (
|
123 |
+
{"context": wikipedia_retriever, "question": RunnablePassthrough()}
|
124 |
+
| maker_prompt
|
125 |
+
| model
|
126 |
+
| maker_output_parser
|
127 |
+
)
|
128 |
+
|
129 |
+
|
130 |
+
|
131 |
+
|
132 |
+
if __name__ == "__main__":
|
133 |
+
|
134 |
+
|
135 |
+
# query = "how to create electronoic on a cellulose subtstrate"
|
136 |
+
query = "A Microscope"
|
137 |
+
|
138 |
+
# output = wikipedia_chain.invoke(query)
|
139 |
+
output = maker_wikipedia_chain.invoke(query)
|
140 |
+
x=0
|
141 |
+
|