Merge pull request #96 from arc53/chat-memory

memory done
pull/98/head
Alex 1 year ago committed by GitHub
commit bc961f9b18
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -1,4 +1,5 @@
import os
import json
import dotenv
import requests
@ -47,6 +48,9 @@ dotenv.load_dotenv()
with open("combine_prompt.txt", "r") as f:
template = f.read()
with open("combine_prompt_hist.txt", "r") as f:
template_hist = f.read()
if os.getenv("API_KEY") is not None:
api_key_set = True
else:
@ -69,6 +73,7 @@ def home():
def api_answer():
data = request.get_json()
question = data["question"]
history = data["history"]
if not api_key_set:
api_key = data["api_key"]
else:
@ -99,7 +104,12 @@ def api_answer():
docsearch = FAISS.load_local(vectorstore, CohereEmbeddings(cohere_api_key=embeddings_key))
# create a prompt template
c_prompt = PromptTemplate(input_variables=["summaries", "question"], template=template)
if history:
history = json.loads(history)
template_temp = template_hist.replace("{historyquestion}", history[0]).replace("{historyanswer}", history[1])
c_prompt = PromptTemplate(input_variables=["summaries", "question"], template=template_temp)
else:
c_prompt = PromptTemplate(input_variables=["summaries", "question"], template=template)
if llm_choice == "openai":
llm = OpenAI(openai_api_key=api_key, temperature=0)

@ -0,0 +1,27 @@
You are a DocsGPT bot assistant by Arc53 that provides help with programming libraries. You give thorough answers with code examples.
Given the following extracted parts of a long document and a question, create a final answer with references ("SOURCES").
ALWAYS return a "SOURCES" part in your answer. You can also remeber things from previous questions and use them in your answer.
QUESTION: How to merge tables in pandas?
=========
Content: pandas provides various facilities for easily combining together Series or DataFrame with various kinds of set logic for the indexes and relational algebra functionality in the case of join / merge-type operations.
Source: 28-pl
Content: pandas provides a single function, merge(), as the entry point for all standard database join operations between DataFrame or named Series objects: \n\npandas.merge(left, right, how='inner', on=None, left_on=None, right_on=None, left_index=False, right_index=False, sort=False, suffixes=('_x', '_y'), copy=True, indicator=False, validate=None)
Source: 30-pl
=========
FINAL ANSWER: To merge two tables in pandas, you can use the pd.merge() function. The basic syntax is: \n\npd.merge(left, right, on, how) \n\nwhere left and right are the two tables to merge, on is the column to merge on, and how is the type of merge to perform. \n\nFor example, to merge the two tables df1 and df2 on the column 'id', you can use: \n\npd.merge(df1, df2, on='id', how='inner')
SOURCES: 28-pl 30-pl
QUESTION: {historyquestion}
=========
CONTENT:
SOURCE:
=========
FINAL ANSWER: {historyanswer}
SOURCES:
QUESTION: {question}
=========
{summaries}
=========
FINAL ANSWER:

@ -26,6 +26,7 @@ if (el) {
body: JSON.stringify({question: message,
api_key: localStorage.getItem('apiKey'),
embeddings_key: localStorage.getItem('apiKey'),
history: localStorage.getItem('chatHistory'),
active_docs: localStorage.getItem('activeDocs')}),
})
.then(response => response.json())
@ -39,9 +40,12 @@ if (el) {
chatWindow.scrollTop = chatWindow.scrollHeight;
document.getElementById("button-submit").innerHTML = 'Send';
document.getElementById("button-submit").disabled = false;
let chatHistory = [message, data.answer];
localStorage.setItem('chatHistory', JSON.stringify(chatHistory));
})
.catch((error) => {
console.error('Error:', error);
console.log(error);
document.getElementById("button-submit").innerHTML = 'Send';
document.getElementById("button-submit").disabled = false;
});

Loading…
Cancel
Save