Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added code for JSON oriented model approach #4

Merged
merged 9 commits into from
Jun 24, 2024
Merged
Show file tree
Hide file tree
Changes from 7 commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/flake8.yml
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ jobs:
- name: flake8 Lint
uses: TrueBrain/actions-flake8@v2
with:
ignore: E203,E701
ignore: E203,E701,W503
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think W504 and go in this list too. I hadn't spotted the difference between ignore and extend-ignore so should list both W503 and W504 to match setup.cfg

max_line_length: 88
path: src
plugins: flake8-black flake8-isort flake8-quotes
Expand Down
4 changes: 2 additions & 2 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
prompts/__pycache__
rich_query_index
.DS_Store
.env
__pycache__
__pycache__
src/query_index
9 changes: 6 additions & 3 deletions .vscode/settings.json
Original file line number Diff line number Diff line change
@@ -1,11 +1,14 @@
{
"git.ignoreLimitWarning": true,
"editor.formatOnSave": true,
"flake8.args": ["--max-line-length=88"],
"flake8.args": [
"--max-line-length=88"
],
"[python]": {
"editor.codeActionsOnSave": {
"source.organizeImports.python": "explicit"
},
"editor.defaultFormatter": "ms-python.black-formatter"
"editor.defaultFormatter": "ms-python.black-formatter",
"editor.formatOnSave": true,
}
}
}
49 changes: 0 additions & 49 deletions app.py

This file was deleted.

49 changes: 0 additions & 49 deletions prompt.py

This file was deleted.

75 changes: 0 additions & 75 deletions query_reformulation.py

This file was deleted.

70 changes: 0 additions & 70 deletions rich_queries/queryV1.json

This file was deleted.

94 changes: 94 additions & 0 deletions src/app.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,94 @@
import json
import logging
import os
rjchallis marked this conversation as resolved.
Show resolved Hide resolved
import sys
import urllib

from flask import Flask, jsonify, render_template, request

from index import load_index, query_engine

app = Flask("goat_nlp")

handler = logging.StreamHandler(sys.stdout)
handler.setFormatter(
logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
)
app.logger.addHandler(handler)
app.logger.setLevel(logging.INFO)


def construct_url(json_output):
base_url = "https://goat.genomehubs.org/"
endpoint = "search?"
suffix = (
"&result=taxon&summaryValues=count&taxonomy=ncbi&offset=0"
+ "&fields=assembly_level%2Cassembly_span%2Cgenome_size%2C"
+ "chromosome_number%2Chaploid_number&names=common_name&ranks="
+ "&includeEstimates=false&size=100"
)

if json_output["intent"] == "count":
endpoint = "count?"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

for now this could be endpoint = api/v2/count? to generate valid links

elif json_output["intent"] == "record":
endpoint = "record?"

params = []

if "taxon" in json_output:
params.append(f"tax_tree(* {json_output['taxon']})")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

fine for now - for next iteration use tax_name search to replace user tax name with taxon_id

if "rank" in json_output:
params.append(f"tax_rank({json_output['rank']})")
if "field" in json_output:
params.append(f"{json_output['field']}")
if "time_frame_query" in json_output:
params.append(f"{json_output['time_frame_query']}")
suffix = (
"&result=assembly&summaryValues=count&taxonomy=ncbi&offset=0"
+ "&fields=assembly_level%2Cassembly_span%2Cgenome_size%2C"
+ "chromosome_number%2Chaploid_number&names=common_name&ranks="
+ "&includeEstimates=false&size=100"
)

query_string = " AND ".join(params)
return (
base_url + endpoint + "query=" + urllib.parse.quote_plus(query_string) + suffix
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

for API spaces need to be escaped as %20, not +

)


def chat_bot_rag(query):
# entity_taxon_map = fetch_related_taxons(query)
for _ in range(int(os.getenv("RETRY_COUNT", 3))):
try:
return construct_url(json.loads(query_engine.custom_query(query)))
except Exception as e:
app.logger.error(f"Error: {e}")
app.logger.error("Retrying...")
return construct_url(json.loads(query_engine.custom_query(query)))


@app.route("/")
def home():
return render_template("chat.html")


@app.route("/rebuildIndex")
def index():
load_index(force_reload=True)


@app.route("/chat", methods=["POST"])
def chat():
user_message = request.form["user_input"]
bot_message = chat_bot_rag(user_message)

try:
bot_message = json.loads(bot_message)["url"]
except Exception:
pass

return jsonify({"response": str(bot_message)})


if __name__ == "__main__":
app.run(debug=True)
Loading