mirror of
https://github.com/Canner/WrenAI.git
synced 2026-10-24 02:25:59 +08:00
feat(wren-ai-service): evaluation dataset curation app (#398)
* fix * fix conflict * add data curation app boilerplate * update * update * update * WIP: update * reoslve conflict * add context for question sql pairs * resolve conflict * fix widget callback issue * add candidate dataset * fix bug and add generate_by_user * update * resolve conflicts * update * update * WIP: add modify dataset * finish modify eval dataset * refine wording * refine failure output * fix sql validation * update usage guide * add categories to curation app * allow edit context * fix conflicts * sleep for waiting wren-ai-service to restart * fix wording * update * fix * fix unchoose file error * update * fix * fix dry run endpoint * fix version * use wren-engine sql analysis for contexts generation * add LOG_LEVEL: DEBUG to ibis * update * allow users to choose which openai llm to use * allow users to enter custom instructions for llm * add data preview for data curation app * add preview data for user generated sqls and add timeout for openai client * refactor * remove unused * fix imports * refactor functions * refactor * fix bug * skip installing unneeded packages * update
This commit is contained in:
Chih-Yu Yeh
@@ -44,8 +44,7 @@ DOCUMENT_STORE_PROVIDER=qdrant
|
||||
|
||||
QDRANT_HOST=http://localhost:6333
|
||||
|
||||
## ENGINE
|
||||
ENGINE=wren_ui
|
||||
ENGINE=wren_ui # wren_ui, wren_ibis, wren_engine
|
||||
|
||||
## when using wren_ui as the engine
|
||||
WREN_UI_ENDPOINT=http://localhost:3000
|
||||
@@ -56,7 +55,10 @@ WREN_IBIS_SOURCE=bigquery
|
||||
### this is a base64 encoded string of the MDL
|
||||
WREN_IBIS_MANIFEST=
|
||||
### this is a base64 encode string of the connection info
|
||||
WREN_IBIS_CONNECTION_INFO=e30=
|
||||
WREN_IBIS_CONNECTION_INFO=
|
||||
|
||||
## when using wren_engine as the engine
|
||||
WREN_ENGINE_ENDPOINT=http://localhost:8080
|
||||
|
||||
# Evaluation
|
||||
DATASET_NAME=book_2
|
||||
|
||||
@@ -30,7 +30,10 @@ eval:
|
||||
make dev-down
|
||||
|
||||
demo:
|
||||
cd demo; poetry run streamlit run app.py
|
||||
poetry run streamlit run demo/app.py
|
||||
|
||||
data_curation_app:
|
||||
poetry run streamlit run eval/data_curation/app.py
|
||||
## utilities related ##
|
||||
|
||||
|
||||
|
||||
@@ -28,16 +28,11 @@ The following commands can quickly start the service for development:
|
||||
|
||||
## Others
|
||||
|
||||
### Pipeline Evaluation(Deprecated, will introduce new way to evaluate the speed in the future)
|
||||
### Pipeline Evaluation
|
||||
|
||||
- install `psql`
|
||||
- fill in environment variables: `.env.dev` in the src folder and `config.properties` in the src/eval/wren-engine/etc folder
|
||||
- start the docker service
|
||||
- evaluation
|
||||
- `make eval pipeline=ask args="--help"`
|
||||
- `make eval pipeline=ask_details args="--help"`
|
||||
- `make eval_visualzation` to compare between the evaluation results
|
||||
- to run individual pipeline: `poetry run python -m src.pipelines.ask.[pipeline_name]` (e.g. `poetry run python -m src.pipelines.ask.retrieval_pipeline`)
|
||||
- evaluation dataset curation
|
||||
- copy `.env.example` file to `.env` in the `eval/data_curation` folder and fill in the environment variables
|
||||
- execute the command under the `wren-ai-service` folder: `make data_curation_app`
|
||||
|
||||
### Speed Evaluation(Deprecated, will introduce new way to evaluate the speed in the future)
|
||||
|
||||
|
||||
@@ -1,6 +1,8 @@
|
||||
bigquery.project-id=wrenai
|
||||
bigquery.project-id=
|
||||
bigquery.dataset-id=
|
||||
bigquery.credentials-key=
|
||||
bigquery.location=asia-east1
|
||||
postgres.host=
|
||||
postgres.port=
|
||||
postgres.database=
|
||||
postgres.user=
|
||||
postgres.password=
|
||||
postgres.jdbc.url=jdbc:postgresql://localhost:5432/<database_name>
|
||||
postgres.password=
|
||||
@@ -7,10 +7,8 @@ from utils import (
|
||||
DATA_SOURCES,
|
||||
ask,
|
||||
ask_details,
|
||||
get_current_manifest,
|
||||
get_mdl_json,
|
||||
get_new_mdl_json,
|
||||
is_current_manifest_available,
|
||||
prepare_duckdb,
|
||||
prepare_semantics,
|
||||
rerun_wren_engine,
|
||||
@@ -59,11 +57,7 @@ if __name__ == "__main__":
|
||||
col1, col2 = st.columns([2, 4])
|
||||
|
||||
with col1:
|
||||
with st.expander("Current Deployed Model", expanded=True):
|
||||
manifest_name, models, relationships = get_current_manifest()
|
||||
st.markdown(f"Current Deployed Model: {manifest_name}")
|
||||
show_er_diagram(models, relationships)
|
||||
with st.expander("Deploy New Model"):
|
||||
with st.expander("Deploy New Model", expanded=True):
|
||||
uploaded_file = st.file_uploader(
|
||||
f"Upload an MDL json file, and the file name must be [xxx]_[datasource]_mdl.json, now we support these datasources: {DATA_SOURCES}",
|
||||
type="json",
|
||||
@@ -154,8 +148,7 @@ if __name__ == "__main__":
|
||||
|
||||
query = st.chat_input(
|
||||
"Ask a question about the database",
|
||||
disabled=(not is_current_manifest_available())
|
||||
and st.session_state["semantics_preparation_status"] != "finished",
|
||||
disabled=st.session_state["semantics_preparation_status"] != "finished",
|
||||
)
|
||||
|
||||
with col2:
|
||||
|
||||
@@ -1,21 +0,0 @@
|
||||
[tool.poetry]
|
||||
name = "wren-ai-service-demo"
|
||||
version = "0.1.0"
|
||||
description = ""
|
||||
authors = ["Jimmy Yeh <jimmy.yeh@cannerdata.com>"]
|
||||
license = "AGPL-3.0"
|
||||
readme = "README.md"
|
||||
|
||||
[tool.poetry.dependencies]
|
||||
python = "^3.12"
|
||||
requests = "^2.31.0"
|
||||
sqlparse = "^0.5.0"
|
||||
streamlit = "^1.32.2"
|
||||
watchdog = "^4.0.0"
|
||||
python-dotenv = "^1.0.1"
|
||||
orjson = "^3.10.3"
|
||||
|
||||
|
||||
[build-system]
|
||||
requires = ["poetry-core"]
|
||||
build-backend = "poetry.core.masonry.api"
|
||||
+120
-78
@@ -1,3 +1,4 @@
|
||||
import base64
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
@@ -14,43 +15,13 @@ from dotenv import load_dotenv
|
||||
|
||||
WREN_AI_SERVICE_BASE_URL = "http://localhost:5556"
|
||||
WREN_ENGINE_API_URL = "http://localhost:8080"
|
||||
WREN_IBIS_API_URL = "http://localhost:8000"
|
||||
POLLING_INTERVAL = 0.5
|
||||
DATA_SOURCES = ["duckdb", "bigquery", "postgres"]
|
||||
|
||||
load_dotenv()
|
||||
|
||||
|
||||
def get_current_manifest():
|
||||
response = requests.get(
|
||||
f"{WREN_ENGINE_API_URL}/v1/mdl",
|
||||
)
|
||||
|
||||
assert response.status_code == 200
|
||||
|
||||
manifest = response.json()
|
||||
|
||||
if manifest["schema"] == "test_schema" and manifest["catalog"] == "test_catalog":
|
||||
return "None", [], []
|
||||
|
||||
return (
|
||||
f"{manifest['catalog']}.{manifest['schema']}",
|
||||
manifest["models"],
|
||||
manifest["relationships"],
|
||||
)
|
||||
|
||||
|
||||
def is_current_manifest_available():
|
||||
response = requests.get(
|
||||
f"{WREN_ENGINE_API_URL}/v1/mdl",
|
||||
)
|
||||
|
||||
assert response.status_code == 200
|
||||
|
||||
manifest = response.json()
|
||||
|
||||
return manifest["catalog"] != "text_catalog" and manifest["schema"] != "test_schema"
|
||||
|
||||
|
||||
def _update_wren_engine_configs(configs: list[dict]):
|
||||
response = requests.patch(
|
||||
f"{WREN_ENGINE_API_URL}/v1/config",
|
||||
@@ -63,50 +34,78 @@ def _update_wren_engine_configs(configs: list[dict]):
|
||||
def rerun_wren_engine(mdl_json: Dict, dataset_type: str):
|
||||
assert dataset_type in DATA_SOURCES
|
||||
|
||||
if dataset_type == "bigquery":
|
||||
BIGQUERY_CREDENTIALS = os.getenv("bigquery.credentials-key")
|
||||
assert (
|
||||
BIGQUERY_CREDENTIALS is not None
|
||||
), "bigquery.credentials-key is not set in .env"
|
||||
if dataset_type == "duckdb":
|
||||
# replace the values of ENGINE to wren-ui in ../.env.dev
|
||||
with open(".env.dev", "r") as f:
|
||||
lines = f.readlines()
|
||||
for i, line in enumerate(lines):
|
||||
if line.startswith("ENGINE"):
|
||||
lines[i] = "ENGINE=wren_engine\n"
|
||||
break
|
||||
with open(".env.dev", "w") as f:
|
||||
f.writelines(lines)
|
||||
|
||||
_update_wren_engine_configs(
|
||||
[
|
||||
{"name": "wren.datasource.type", "value": "bigquery"},
|
||||
{
|
||||
"name": "bigquery.project-id",
|
||||
"value": os.getenv("bigquery.project-id"),
|
||||
},
|
||||
{"name": "bigquery.location", "value": os.getenv("bigquery.location")},
|
||||
{"name": "bigquery.credentials-key", "value": BIGQUERY_CREDENTIALS},
|
||||
]
|
||||
)
|
||||
elif dataset_type == "duckdb":
|
||||
_update_wren_engine_configs(
|
||||
[{"name": "wren.datasource.type", "value": "duckdb"}]
|
||||
)
|
||||
elif dataset_type == "postgresql":
|
||||
_update_wren_engine_configs(
|
||||
[
|
||||
{"name": "wren.datasource.type", "value": "postgres"},
|
||||
{"name": "postgres.user", "value": os.getenv("postgres.user")},
|
||||
{"name": "postgres.password", "value": os.getenv("postgres.password")},
|
||||
{"name": "postgres.jdbc.url", "value": os.getenv("postgres.jdbc.url")},
|
||||
]
|
||||
st.toast("Wren Engine is being re-run", icon="⏳")
|
||||
|
||||
response = requests.post(
|
||||
f"{WREN_ENGINE_API_URL}/v1/mdl/deploy",
|
||||
json={
|
||||
"manifest": mdl_json,
|
||||
"version": "latest",
|
||||
},
|
||||
)
|
||||
|
||||
st.toast("Wren Engine is being re-run", icon="⏳")
|
||||
assert response.status_code == 202, response.json()
|
||||
|
||||
response = requests.post(
|
||||
f"{WREN_ENGINE_API_URL}/v1/mdl/deploy",
|
||||
json={
|
||||
"manifest": mdl_json,
|
||||
"version": "latest",
|
||||
},
|
||||
)
|
||||
st.toast("Wren Engine is ready", icon="🎉")
|
||||
else:
|
||||
WREN_IBIS_SOURCE = dataset_type
|
||||
WREN_IBIS_MANIFEST = base64.b64encode(orjson.dumps(mdl_json)).decode()
|
||||
if dataset_type == "bigquery":
|
||||
WREN_IBIS_CONNECTION_INFO = base64.b64encode(
|
||||
orjson.dumps(
|
||||
{
|
||||
"project_id": os.getenv("bigquery.project-id"),
|
||||
"dataset_id": os.getenv("bigquery.dataset-id"),
|
||||
"credentials": os.getenv("bigquery.credentials-key"),
|
||||
}
|
||||
)
|
||||
).decode()
|
||||
elif dataset_type == "postgres":
|
||||
WREN_IBIS_CONNECTION_INFO = base64.b64encode(
|
||||
orjson.dumps(
|
||||
{
|
||||
"host": os.getenv("postgres.host"),
|
||||
"port": int(os.getenv("postgres.port")),
|
||||
"database": os.getenv("postgres.database"),
|
||||
"user": os.getenv("postgres.user"),
|
||||
"password": os.getenv("postgres.password"),
|
||||
}
|
||||
)
|
||||
).decode()
|
||||
|
||||
assert response.status_code == 202
|
||||
# replace the values of WREN_IBIS_xxx to ../.env.dev
|
||||
with open(".env.dev", "r") as f:
|
||||
lines = f.readlines()
|
||||
for i, line in enumerate(lines):
|
||||
if line.startswith("ENGINE"):
|
||||
lines[i] = "ENGINE=wren-ibis\n"
|
||||
elif line.startswith("WREN_IBIS_SOURCE"):
|
||||
lines[i] = f"WREN_IBIS_SOURCE={WREN_IBIS_SOURCE}\n"
|
||||
elif line.startswith("WREN_IBIS_MANIFEST"):
|
||||
lines[i] = f"WREN_IBIS_MANIFEST={WREN_IBIS_MANIFEST}\n"
|
||||
elif line.startswith("WREN_IBIS_CONNECTION_INFO"):
|
||||
lines[
|
||||
i
|
||||
] = f"WREN_IBIS_CONNECTION_INFO={WREN_IBIS_CONNECTION_INFO}\n"
|
||||
with open(".env.dev", "w") as f:
|
||||
f.writelines(lines)
|
||||
|
||||
st.toast("Wren Engine is ready", icon="🎉")
|
||||
# wait for wren-ai-service to restart
|
||||
time.sleep(5)
|
||||
|
||||
|
||||
def save_mdl_json_file(file_name: str, mdl_json: Dict):
|
||||
@@ -120,7 +119,7 @@ def save_mdl_json_file(file_name: str, mdl_json: Dict):
|
||||
def get_mdl_json(database_name: str):
|
||||
assert database_name in ["music", "nba", "ecommerce"]
|
||||
|
||||
with open(f"sample_dataset/{database_name}_duckdb_mdl.json", "r") as f:
|
||||
with open(f"demo/sample_dataset/{database_name}_duckdb_mdl.json", "r") as f:
|
||||
mdl_json = json.load(f)
|
||||
|
||||
return mdl_json
|
||||
@@ -146,20 +145,62 @@ def get_new_mdl_json(chosen_models: List[str]):
|
||||
|
||||
|
||||
@st.cache_data
|
||||
def get_data_from_wren_engine(sql: str):
|
||||
response = requests.get(
|
||||
f"{WREN_ENGINE_API_URL}/v1/mdl/preview",
|
||||
json={
|
||||
"sql": sql,
|
||||
},
|
||||
)
|
||||
def get_data_from_wren_engine(sql: str, dataset_type: str):
|
||||
assert dataset_type in DATA_SOURCES
|
||||
|
||||
assert response.status_code == 200
|
||||
if dataset_type == "duckdb":
|
||||
response = requests.get(
|
||||
f"{WREN_ENGINE_API_URL}/v1/mdl/preview",
|
||||
json={
|
||||
"sql": sql,
|
||||
},
|
||||
)
|
||||
|
||||
data = response.json()
|
||||
column_names = [f'{i}_{col["name"]}' for i, col in enumerate(data["columns"])]
|
||||
if response.status_code != 200:
|
||||
st.error(response.json())
|
||||
st.stop()
|
||||
|
||||
return pd.DataFrame(data["data"], columns=column_names)
|
||||
data = response.json()
|
||||
column_names = [f'{i}_{col["name"]}' for i, col in enumerate(data["columns"])]
|
||||
|
||||
return pd.DataFrame(data["data"], columns=column_names)
|
||||
else:
|
||||
connection_info = {
|
||||
"bigquery": {
|
||||
"project_id": os.getenv("bigquery.project-id"),
|
||||
"dataset_id": os.getenv("bigquery.dataset-id"),
|
||||
"credentials": os.getenv("bigquery.credentials-key"),
|
||||
},
|
||||
"postgres": {
|
||||
"host": os.getenv("postgres.host"),
|
||||
"port": int(os.getenv("postgres.port"))
|
||||
if os.getenv("postgres.port")
|
||||
else 5432,
|
||||
"database": os.getenv("postgres.database"),
|
||||
"user": os.getenv("postgres.user"),
|
||||
"password": os.getenv("postgres.password"),
|
||||
},
|
||||
}
|
||||
|
||||
response = requests.post(
|
||||
f"{WREN_IBIS_API_URL}/v2/ibis/{dataset_type}/query",
|
||||
json={
|
||||
"sql": sql,
|
||||
"manifestStr": base64.b64encode(
|
||||
orjson.dumps(st.session_state["mdl_json"])
|
||||
).decode(),
|
||||
"connectionInfo": connection_info[dataset_type],
|
||||
},
|
||||
)
|
||||
|
||||
if response.status_code != 200:
|
||||
st.error(response.json())
|
||||
st.stop()
|
||||
|
||||
data = response.json()
|
||||
column_names = [f"{i}_{col}" for i, col in enumerate(data["columns"])]
|
||||
|
||||
return pd.DataFrame(data["data"], columns=column_names)
|
||||
|
||||
|
||||
# ui related
|
||||
@@ -319,6 +360,7 @@ def show_asks_details_results():
|
||||
st.dataframe(
|
||||
get_data_from_wren_engine(
|
||||
st.session_state["preview_sql"],
|
||||
st.session_state["dataset_type"],
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@@ -12,7 +12,7 @@ WORKDIR /app
|
||||
|
||||
COPY pyproject.toml ./
|
||||
|
||||
RUN poetry install --without dev --no-root && rm -rf $POETRY_CACHE_DIR
|
||||
RUN poetry install --without dev,eval,demo --no-root && rm -rf $POETRY_CACHE_DIR
|
||||
|
||||
FROM python:3.12.0-slim-bookworm as runtime
|
||||
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
.env
|
||||
@@ -0,0 +1,6 @@
|
||||
OPENAI_API_KEY=
|
||||
WREN_IBIS_ENDPOINT=http://localhost:8000
|
||||
WREN_ENGINE_ENDPOINT=http://localhost:8080
|
||||
bigquery.project-id=
|
||||
bigquery.dataset-id=
|
||||
bigquery.credentials-key=
|
||||
@@ -0,0 +1,461 @@
|
||||
import asyncio
|
||||
import os
|
||||
import re
|
||||
import uuid
|
||||
from datetime import datetime
|
||||
|
||||
import orjson
|
||||
import pandas as pd
|
||||
import streamlit as st
|
||||
import tomlkit
|
||||
from openai import AsyncClient
|
||||
from streamlit_tags import st_tags
|
||||
from utils import (
|
||||
DATA_SOURCES,
|
||||
get_contexts_from_sqls,
|
||||
get_data_from_wren_engine,
|
||||
get_eval_dataset_in_toml_string,
|
||||
get_openai_client,
|
||||
get_question_sql_pairs,
|
||||
is_sql_valid,
|
||||
prettify_sql,
|
||||
)
|
||||
|
||||
st.set_page_config(layout="wide")
|
||||
st.title("WrenAI Data Curation App")
|
||||
|
||||
|
||||
LLM_OPTIONS = ["gpt-3.5-turbo", "gpt-4-turbo", "gpt-4o"]
|
||||
|
||||
llm_client = get_openai_client()
|
||||
|
||||
|
||||
# session states
|
||||
if "llm_model" not in st.session_state:
|
||||
st.session_state["llm_model"] = LLM_OPTIONS[0]
|
||||
if "deployment_id" not in st.session_state:
|
||||
st.session_state["deployment_id"] = str(uuid.uuid4())
|
||||
if "mdl_json" not in st.session_state:
|
||||
st.session_state["mdl_json"] = None
|
||||
if "custom_instructions_for_llm" not in st.session_state:
|
||||
st.session_state["custom_instructions_for_llm"] = ""
|
||||
if "llm_question_sql_pairs" not in st.session_state:
|
||||
st.session_state["llm_question_sql_pairs"] = []
|
||||
if "user_question_sql_pair" not in st.session_state:
|
||||
st.session_state["user_question_sql_pair"] = {}
|
||||
if "candidate_dataset" not in st.session_state:
|
||||
st.session_state["candidate_dataset"] = []
|
||||
if "data_source" not in st.session_state:
|
||||
st.session_state["data_source"] = None
|
||||
if "connection_info" not in st.session_state:
|
||||
st.session_state["connection_info"] = None
|
||||
|
||||
|
||||
# widget callbacks
|
||||
def on_change_upload_eval_dataset():
|
||||
doc = tomlkit.parse(st.session_state.uploaded_eval_file.getvalue().decode("utf-8"))
|
||||
assert (
|
||||
doc["mdl"] == st.session_state["mdl_json"]
|
||||
), "The model in the uploaded dataset is different from the deployed model"
|
||||
st.session_state["candidate_dataset"] = doc["eval_dataset"]
|
||||
|
||||
|
||||
def on_change_custom_instructions_for_llm():
|
||||
st.session_state["custom_instructions_for_llm"] = st.session_state[
|
||||
"custom_instructions_text_area"
|
||||
]
|
||||
|
||||
|
||||
def on_click_generate_question_sql_pairs(llm_client: AsyncClient):
|
||||
st.toast("Generating question-sql-pairs...")
|
||||
st.session_state["llm_question_sql_pairs"] = asyncio.run(
|
||||
get_question_sql_pairs(
|
||||
llm_client,
|
||||
st.session_state["llm_model"],
|
||||
st.session_state["mdl_json"],
|
||||
st.session_state["custom_instructions_for_llm"],
|
||||
st.session_state["data_source"],
|
||||
st.session_state["connection_info"],
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
def on_click_setup_uploaded_file():
|
||||
uploaded_file = st.session_state.get("uploaded_mdl_file")
|
||||
if uploaded_file:
|
||||
match = re.match(
|
||||
r".+_(" + "|".join(DATA_SOURCES) + r")_mdl\.json$",
|
||||
uploaded_file.name,
|
||||
)
|
||||
if not match:
|
||||
st.error(
|
||||
f"the file name must be [xxx]_[datasource]_mdl.json, now we support these datasources: {DATA_SOURCES}"
|
||||
)
|
||||
st.stop()
|
||||
|
||||
data_source = match.group(1)
|
||||
st.session_state["data_source"] = data_source
|
||||
st.session_state["mdl_json"] = orjson.loads(
|
||||
uploaded_file.getvalue().decode("utf-8")
|
||||
)
|
||||
|
||||
st.session_state["connection_info"] = {
|
||||
"project_id": os.getenv("bigquery.project-id"),
|
||||
"dataset_id": os.getenv("bigquery.dataset-id"),
|
||||
"credentials": os.getenv("bigquery.credentials-key"),
|
||||
}
|
||||
else:
|
||||
st.session_state["data_source"] = None
|
||||
st.session_state["mdl_json"] = None
|
||||
st.session_state["connection_info"] = None
|
||||
|
||||
|
||||
def on_change_llm_model():
|
||||
st.toast(f"Switching LLM model to {st.session_state["select_llm_model"]}")
|
||||
st.session_state["llm_model"] = st.session_state["select_llm_model"]
|
||||
|
||||
|
||||
def on_change_sql(i: int, key: str):
|
||||
sql = st.session_state[key]
|
||||
|
||||
valid, error = asyncio.run(
|
||||
is_sql_valid(
|
||||
sql,
|
||||
st.session_state["data_source"],
|
||||
st.session_state["mdl_json"],
|
||||
st.session_state["connection_info"],
|
||||
)
|
||||
)
|
||||
if valid:
|
||||
new_context = asyncio.run(
|
||||
get_contexts_from_sqls([sql], st.session_state["mdl_json"])
|
||||
)
|
||||
if i != -1:
|
||||
st.session_state["llm_question_sql_pairs"][i]["sql"] = sql
|
||||
st.session_state["llm_question_sql_pairs"][i]["is_valid"] = valid
|
||||
st.session_state["llm_question_sql_pairs"][i]["error"] = error
|
||||
if valid:
|
||||
st.session_state["llm_question_sql_pairs"][i]["context"] = new_context
|
||||
else:
|
||||
st.session_state["user_question_sql_pair"]["sql"] = sql
|
||||
st.session_state["user_question_sql_pair"]["is_valid"] = valid
|
||||
st.session_state["user_question_sql_pair"]["error"] = error
|
||||
if valid:
|
||||
st.session_state["user_question_sql_pair"]["context"] = new_context
|
||||
|
||||
|
||||
def on_click_add_candidate_dataset(i: int, categories: list):
|
||||
if i != -1:
|
||||
dataset_to_add = {
|
||||
"categories": categories,
|
||||
"question": st.session_state["llm_question_sql_pairs"][i]["question"],
|
||||
"context": st.session_state["llm_question_sql_pairs"][i]["context"],
|
||||
"sql": st.session_state["llm_question_sql_pairs"][i]["sql"],
|
||||
}
|
||||
else:
|
||||
dataset_to_add = {
|
||||
"categories": categories,
|
||||
"question": st.session_state["user_question_sql_pair"]["question"],
|
||||
"context": st.session_state["user_question_sql_pair"]["context"],
|
||||
"sql": st.session_state["user_question_sql_pair"]["sql"],
|
||||
}
|
||||
|
||||
# reset input for user question sql pair
|
||||
st.session_state["user_question_sql_pair"] = {}
|
||||
st.session_state["user_question"] = ""
|
||||
st.session_state["user_sql"] = ""
|
||||
|
||||
should_add = True
|
||||
for dataset in st.session_state["candidate_dataset"]:
|
||||
if dataset == dataset_to_add:
|
||||
should_add = False
|
||||
break
|
||||
|
||||
if should_add:
|
||||
st.session_state["candidate_dataset"].append(dataset_to_add)
|
||||
|
||||
|
||||
def on_change_user_question():
|
||||
if not st.session_state["user_question_sql_pair"]:
|
||||
st.session_state["user_question_sql_pair"] = {
|
||||
"question": st.session_state["user_question"],
|
||||
"context": [],
|
||||
"sql": "",
|
||||
"is_valid": False,
|
||||
"error": "",
|
||||
}
|
||||
else:
|
||||
st.session_state["user_question_sql_pair"] = {
|
||||
**st.session_state["user_question_sql_pair"],
|
||||
"question": st.session_state["user_question"],
|
||||
}
|
||||
|
||||
|
||||
def on_click_remove_candidate_dataset_button(i: int):
|
||||
st.session_state["candidate_dataset"].pop(i)
|
||||
|
||||
|
||||
st.file_uploader(
|
||||
f"Upload an MDL json file, and the file name must be [xxx]_[datasource]_mdl.json, now we support these datasources: {DATA_SOURCES}",
|
||||
type="json",
|
||||
key="uploaded_mdl_file",
|
||||
on_change=on_click_setup_uploaded_file,
|
||||
)
|
||||
|
||||
st.selectbox(
|
||||
label="Select which LLM model you want to use",
|
||||
options=LLM_OPTIONS,
|
||||
index=0,
|
||||
key="select_llm_model",
|
||||
on_change=on_change_llm_model,
|
||||
)
|
||||
|
||||
tab_create_dataset, tab_modify_dataset = st.tabs(
|
||||
["Create New Evaluation Dataset", "Modify Saved Evaluation Dataset"]
|
||||
)
|
||||
with tab_create_dataset:
|
||||
st.markdown(
|
||||
"""
|
||||
### Usage Guide
|
||||
1. Upload an MDL json file first
|
||||
2. Get question-sql-pairs given by LLM or you manually enter question and corresponding sql
|
||||
3. Do validation on each group of question, context and SQL, and move it to the candidate dataset if you think it's valid
|
||||
3. Save the candidate dataset by clicking the "Save as Evaluation Dataset" button.
|
||||
"""
|
||||
)
|
||||
|
||||
with tab_modify_dataset:
|
||||
st.markdown(
|
||||
"""
|
||||
### Usage Guide
|
||||
1. Upload an MDL json file first
|
||||
2. Upload the evaluation dataset(`.toml` file) you want to modify, and please make sure the model in the dataset is the same as the deployed model
|
||||
3. Modify the evaluation dataset the same as you create a new one
|
||||
4. Save the candidate dataset by clicking the "Save as Evaluation Dataset" button.
|
||||
"""
|
||||
)
|
||||
|
||||
st.warning(
|
||||
"WARNING: Uploading the evaluation dataset will overwrite the current candidate dataset"
|
||||
)
|
||||
st.file_uploader(
|
||||
"Upload Evaluation Dataset",
|
||||
type="toml",
|
||||
key="uploaded_eval_file",
|
||||
on_change=on_change_upload_eval_dataset,
|
||||
disabled=st.session_state["mdl_json"] is None,
|
||||
)
|
||||
|
||||
if st.session_state["mdl_json"] is not None:
|
||||
col1, col2 = st.columns(2)
|
||||
with col1:
|
||||
st.markdown("### Question SQL Pairs")
|
||||
tab_generated_by_llm, tab_generated_by_user = st.tabs(
|
||||
["Generated by LLM", "Generated by User"]
|
||||
)
|
||||
|
||||
with tab_generated_by_llm:
|
||||
st.text_area(
|
||||
"Custom Instructions for generating question-sql-pairs (Optional)",
|
||||
key="custom_instructions_text_area",
|
||||
value=st.session_state["custom_instructions_for_llm"],
|
||||
placeholder="You can specify the custom instructions on how LLM should generate question-sql-pairs here, for example: what type of questions you want to generate.",
|
||||
on_change=on_change_custom_instructions_for_llm,
|
||||
)
|
||||
|
||||
st.button(
|
||||
"Generate 10 question-sql-pairs",
|
||||
key="generate_question_sql_pairs",
|
||||
on_click=on_click_generate_question_sql_pairs,
|
||||
args=(llm_client,),
|
||||
)
|
||||
|
||||
with st.container(border=True, height=550):
|
||||
for i, question_sql_pair in enumerate(
|
||||
st.session_state["llm_question_sql_pairs"]
|
||||
):
|
||||
st.text_input(
|
||||
f"Question {i}",
|
||||
question_sql_pair["question"],
|
||||
disabled=True,
|
||||
key=f"question_{i}",
|
||||
)
|
||||
categories = st_tags(
|
||||
label=f"Categories {i}",
|
||||
text="Press enter to add more",
|
||||
value=[],
|
||||
key=f"categories_{i}",
|
||||
)
|
||||
st.multiselect(
|
||||
label=f"Context {i}",
|
||||
options=question_sql_pair["context"],
|
||||
default=question_sql_pair["context"],
|
||||
key=f"context_{i}",
|
||||
help="Contexts are automatically generated based on the SQL once you save the changes of the it(ctrl+enter or command+enter)",
|
||||
disabled=True,
|
||||
)
|
||||
st.text_area(
|
||||
f"SQL {i}",
|
||||
prettify_sql(question_sql_pair["sql"]),
|
||||
key=f"sql_{i}",
|
||||
height=250,
|
||||
on_change=on_change_sql,
|
||||
args=(i, f"sql_{i}"),
|
||||
)
|
||||
if st.session_state["llm_question_sql_pairs"][i]["is_valid"]:
|
||||
st.success("SQL is valid")
|
||||
st.dataframe(
|
||||
pd.DataFrame(
|
||||
question_sql_pair["data"]["data"],
|
||||
columns=question_sql_pair["data"]["columns"],
|
||||
)
|
||||
)
|
||||
else:
|
||||
st.error(
|
||||
f"SQL is invalid: {st.session_state["llm_question_sql_pairs"][i]["error"]}"
|
||||
)
|
||||
|
||||
st.button(
|
||||
"Move it to the candidate dataset",
|
||||
key=f"move_to_dataset_{i}",
|
||||
disabled=(
|
||||
not st.session_state["llm_question_sql_pairs"][i][
|
||||
"is_valid"
|
||||
]
|
||||
or not st.session_state[f"context_{i}"]
|
||||
or not categories
|
||||
),
|
||||
on_click=on_click_add_candidate_dataset,
|
||||
args=(
|
||||
i,
|
||||
categories,
|
||||
),
|
||||
)
|
||||
|
||||
st.markdown("---")
|
||||
|
||||
with tab_generated_by_user:
|
||||
with st.container(border=True, height=550):
|
||||
st.text_input(
|
||||
"Question",
|
||||
disabled=False,
|
||||
key="user_question",
|
||||
on_change=on_change_user_question,
|
||||
)
|
||||
categories = st_tags(
|
||||
label="Categories",
|
||||
text="Press enter to add more",
|
||||
value=[],
|
||||
key="user_categories",
|
||||
)
|
||||
st.multiselect(
|
||||
label="Context",
|
||||
options=st.session_state.get("user_question_sql_pair", {}).get(
|
||||
"context", []
|
||||
),
|
||||
default=st.session_state.get("user_question_sql_pair", {}).get(
|
||||
"context", []
|
||||
),
|
||||
key="user_context",
|
||||
help="Contexts are automatically generated based on the SQL once you save the changes of the it(ctrl+enter or command+enter)",
|
||||
disabled=True,
|
||||
)
|
||||
st.text_area(
|
||||
"SQL",
|
||||
key="user_sql",
|
||||
height=250,
|
||||
on_change=on_change_sql,
|
||||
args=(-1, "user_sql"),
|
||||
)
|
||||
|
||||
if st.session_state.get("user_question_sql_pair", {}).get(
|
||||
"is_valid", False
|
||||
):
|
||||
st.success("SQL is valid")
|
||||
data = asyncio.run(
|
||||
get_data_from_wren_engine(
|
||||
[st.session_state["user_question_sql_pair"]["sql"]],
|
||||
st.session_state["data_source"],
|
||||
)
|
||||
)[0]
|
||||
st.dataframe(
|
||||
pd.DataFrame(
|
||||
data["data"],
|
||||
columns=data["columns"],
|
||||
)
|
||||
)
|
||||
else:
|
||||
st.error(
|
||||
f"SQL is invalid: {st.session_state.get("user_question_sql_pair", {}).get('error', '')}"
|
||||
)
|
||||
|
||||
st.button(
|
||||
"Move it to the candidate dataset",
|
||||
key="move_to_dataset",
|
||||
disabled=(
|
||||
not st.session_state.get("user_question_sql_pair", {}).get(
|
||||
"is_valid", False
|
||||
)
|
||||
or not st.session_state["user_context"]
|
||||
or not st.session_state["user_question"]
|
||||
or not categories
|
||||
),
|
||||
on_click=on_click_add_candidate_dataset,
|
||||
args=(
|
||||
-1,
|
||||
categories,
|
||||
),
|
||||
)
|
||||
with col2:
|
||||
st.markdown("### Candidate Dataset")
|
||||
|
||||
with st.container(border=True, height=600):
|
||||
for i, dataset in enumerate(st.session_state["candidate_dataset"]):
|
||||
st.text_input(
|
||||
f"Question {i}",
|
||||
dataset["question"],
|
||||
disabled=True,
|
||||
key=f"candidate_dataset_question_{i}",
|
||||
)
|
||||
st.multiselect(
|
||||
f"Categories {i}",
|
||||
options=dataset["categories"],
|
||||
default=dataset["categories"],
|
||||
disabled=True,
|
||||
key=f"candidate_dataset_categories_{i}",
|
||||
)
|
||||
st.multiselect(
|
||||
f"Context {i}",
|
||||
options=dataset["context"],
|
||||
default=dataset["context"],
|
||||
disabled=True,
|
||||
key=f"candidate_dataset_context_{i}",
|
||||
)
|
||||
st.markdown(f"SQL {i}")
|
||||
st.code(prettify_sql(dataset["sql"]), language="sql", line_numbers=True)
|
||||
st.button(
|
||||
"Remove",
|
||||
key=f"remove_{i}",
|
||||
on_click=on_click_remove_candidate_dataset_button,
|
||||
args=(i,),
|
||||
)
|
||||
st.markdown("---")
|
||||
|
||||
with st.popover("Save as Evaluation Dataset", use_container_width=True):
|
||||
file_name = st.text_input(
|
||||
"File Name",
|
||||
f'eval_dataset_{datetime.today().strftime("%Y_%m_%d")}.toml',
|
||||
key="eval_dataset_file_name",
|
||||
)
|
||||
download_btn = st.download_button(
|
||||
"Download",
|
||||
get_eval_dataset_in_toml_string(
|
||||
st.session_state["mdl_json"],
|
||||
st.session_state["candidate_dataset"],
|
||||
),
|
||||
file_name=file_name,
|
||||
key="download_eval_dataset_confirmed",
|
||||
disabled=not st.session_state["candidate_dataset"],
|
||||
)
|
||||
if download_btn:
|
||||
st.toast("Downloading the evaluation dataset...")
|
||||
@@ -0,0 +1,326 @@
|
||||
import asyncio
|
||||
import base64
|
||||
import os
|
||||
import sys
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import List, Tuple
|
||||
|
||||
import aiohttp
|
||||
import orjson
|
||||
import sqlglot
|
||||
import sqlparse
|
||||
import streamlit as st
|
||||
import tomlkit
|
||||
from dotenv import load_dotenv
|
||||
from openai import AsyncClient
|
||||
|
||||
# in order to import the DDLConverter class from the indexing module
|
||||
sys.path.append(f"{Path().parent.parent.resolve()}")
|
||||
from src.pipelines.indexing.indexing import DDLConverter
|
||||
|
||||
load_dotenv()
|
||||
|
||||
WREN_IBIS_ENDPOINT = os.getenv("WREN_IBIS_ENDPOINT", "http://localhost:8000")
|
||||
WREN_ENGINE_ENDPOINT = os.getenv("WREN_ENGINE_ENDPOINT", "http://localhost:8080")
|
||||
DATA_SOURCES = ["bigquery"]
|
||||
TIMEOUT_SECONDS = 60
|
||||
ddl_converter = DDLConverter()
|
||||
|
||||
|
||||
def get_openai_client(
|
||||
api_key: str = os.getenv("OPENAI_API_KEY"), timeout: float = TIMEOUT_SECONDS
|
||||
) -> AsyncClient:
|
||||
return AsyncClient(
|
||||
api_key=api_key,
|
||||
timeout=timeout,
|
||||
)
|
||||
|
||||
|
||||
def add_quotes(sql: str) -> str:
|
||||
return sqlglot.transpile(sql, read="trino", identify=True)[0]
|
||||
|
||||
|
||||
async def is_sql_valid(
|
||||
sql: str,
|
||||
data_source: str,
|
||||
mdl_json: dict,
|
||||
connection_info: dict,
|
||||
api_endpoint: str = WREN_IBIS_ENDPOINT,
|
||||
timeout: float = TIMEOUT_SECONDS,
|
||||
) -> Tuple[bool, str]:
|
||||
sql = sql[:-1] if sql.endswith(";") else sql
|
||||
async with aiohttp.request(
|
||||
"POST",
|
||||
f"{api_endpoint}/v2/connector/{data_source}/query?dryRun=true",
|
||||
json={
|
||||
"sql": add_quotes(sql),
|
||||
"manifestStr": base64.b64encode(orjson.dumps(mdl_json)).decode(),
|
||||
"connectionInfo": connection_info,
|
||||
},
|
||||
timeout=aiohttp.ClientTimeout(total=timeout),
|
||||
) as response:
|
||||
if response.status == 204:
|
||||
return True, None
|
||||
res = await response.text()
|
||||
|
||||
return False, res
|
||||
|
||||
|
||||
async def get_validated_question_sql_pairs(
|
||||
question_sql_pairs: list[dict],
|
||||
data_source: str,
|
||||
mdl_json: dict,
|
||||
connection_info: dict,
|
||||
) -> list[dict]:
|
||||
tasks = []
|
||||
|
||||
async with aiohttp.ClientSession():
|
||||
for question_sql_pair in question_sql_pairs:
|
||||
task = asyncio.ensure_future(
|
||||
is_sql_valid(
|
||||
question_sql_pair["sql"],
|
||||
data_source,
|
||||
mdl_json,
|
||||
connection_info,
|
||||
)
|
||||
)
|
||||
tasks.append(task)
|
||||
|
||||
results = await asyncio.gather(*tasks)
|
||||
return [
|
||||
{
|
||||
**question_sql_pairs[i],
|
||||
"context": [],
|
||||
"is_valid": valid,
|
||||
"error": error,
|
||||
}
|
||||
for i, (valid, error) in enumerate(results)
|
||||
]
|
||||
|
||||
|
||||
async def get_sql_analysis(
|
||||
sql: str,
|
||||
mdl_json: dict,
|
||||
api_endpoint: str = WREN_ENGINE_ENDPOINT,
|
||||
timeout: float = TIMEOUT_SECONDS,
|
||||
) -> List[dict]:
|
||||
sql = sql[:-1] if sql.endswith(";") else sql
|
||||
async with aiohttp.request(
|
||||
"GET",
|
||||
f"{api_endpoint}/v1/analysis/sql",
|
||||
json={
|
||||
"sql": add_quotes(sql),
|
||||
"manifest": mdl_json,
|
||||
},
|
||||
timeout=aiohttp.ClientTimeout(total=timeout),
|
||||
) as response:
|
||||
return await response.json()
|
||||
|
||||
|
||||
async def get_contexts_from_sqls(
|
||||
sqls: list[str],
|
||||
mdl_json: dict,
|
||||
) -> list[str]:
|
||||
def _compose_contexts_of_select_type(select_items: list[dict]):
|
||||
return [
|
||||
f'{expr_source['sourceDataset']}.{expr_source['expression']}'
|
||||
for select_item in select_items
|
||||
for expr_source in select_item["exprSources"]
|
||||
]
|
||||
|
||||
def _compose_contexts_of_filter_type(filter: dict):
|
||||
contexts = []
|
||||
if filter["type"] == "EXPR":
|
||||
contexts += [
|
||||
f'{expr_source["sourceDataset"]}.{expr_source["expression"]}'
|
||||
for expr_source in filter["exprSources"]
|
||||
]
|
||||
elif filter["type"] in ("AND", "OR"):
|
||||
contexts += _compose_contexts_of_filter_type(filter["left"])
|
||||
contexts += _compose_contexts_of_filter_type(filter["right"])
|
||||
|
||||
return contexts
|
||||
|
||||
def _compose_contexts_of_groupby_type(groupby_keys: list[list[dict]]):
|
||||
contexts = []
|
||||
for groupby_key_list in groupby_keys:
|
||||
contexts += [
|
||||
f'{expr_source["sourceDataset"]}.{expr_source["expression"]}'
|
||||
for groupby_key in groupby_key_list
|
||||
for expr_source in groupby_key["exprSources"]
|
||||
]
|
||||
return contexts
|
||||
|
||||
def _compose_contexts_of_sorting_type(sortings: list[dict]):
|
||||
return [
|
||||
f'{expr_source["sourceDataset"]}.{expr_source["expression"]}'
|
||||
for sorting in sortings
|
||||
for expr_source in sorting["exprSources"]
|
||||
]
|
||||
|
||||
def _get_contexts_from_sql_analysis_results(sql_analysis_results: list[dict]):
|
||||
contexts = []
|
||||
for result in sql_analysis_results:
|
||||
if "selectItems" in result:
|
||||
contexts += _compose_contexts_of_select_type(result["selectItems"])
|
||||
if "filter" in result:
|
||||
contexts += _compose_contexts_of_filter_type(result["filter"])
|
||||
if "groupByKeys" in result:
|
||||
contexts += _compose_contexts_of_groupby_type(result["groupByKeys"])
|
||||
if "sortings" in result:
|
||||
contexts += _compose_contexts_of_sorting_type(result["sortings"])
|
||||
|
||||
# print(
|
||||
# f'SQL ANALYSIS RESULTS: {orjson.dumps(sql_analysis_results, option=orjson.OPT_INDENT_2).decode("utf-8")}'
|
||||
# )
|
||||
# print(f"CONTEXTS: {sorted(set(contexts))}")
|
||||
# print("\n\n")
|
||||
|
||||
return sorted(set(contexts))
|
||||
|
||||
async with aiohttp.ClientSession():
|
||||
tasks = []
|
||||
for sql in sqls:
|
||||
task = asyncio.ensure_future(get_sql_analysis(sql, mdl_json))
|
||||
tasks.append(task)
|
||||
|
||||
results = await asyncio.gather(*tasks)
|
||||
|
||||
return [_get_contexts_from_sql_analysis_results(result) for result in results]
|
||||
|
||||
|
||||
async def get_question_sql_pairs(
|
||||
llm_client: AsyncClient,
|
||||
llm_model: str,
|
||||
mdl_json: dict,
|
||||
custom_instructions: str,
|
||||
data_source: str,
|
||||
connection_info: dict,
|
||||
num_pairs: int = 10,
|
||||
) -> list[dict]:
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "",
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": f"""
|
||||
### TASK ###
|
||||
Given the database DDL, generate {num_pairs} of the questions and corresponding SQL queries.
|
||||
|
||||
### Output Format ###
|
||||
{{
|
||||
"results": [
|
||||
{{
|
||||
"question": <question_string>,
|
||||
"sql": <sql_query_string>
|
||||
}},
|
||||
{{
|
||||
"question": <question_string>,
|
||||
"sql": <sql_query_string>
|
||||
}},
|
||||
...
|
||||
]
|
||||
}}
|
||||
|
||||
### Custom Instructions ###
|
||||
|
||||
{custom_instructions}
|
||||
|
||||
### Input ###
|
||||
Data Model: {"\n\n".join(ddl_converter.get_ddl_commands(mdl_json))}
|
||||
|
||||
Generate {num_pairs} of the questions and corresponding SQL queries according to the Output Format in JSON
|
||||
Think step by step
|
||||
""",
|
||||
},
|
||||
]
|
||||
|
||||
try:
|
||||
response = await llm_client.chat.completions.create(
|
||||
model=llm_model,
|
||||
messages=messages,
|
||||
response_format={"type": "json_object"},
|
||||
max_tokens=4096,
|
||||
temperature=0,
|
||||
)
|
||||
|
||||
results = orjson.loads(response.choices[0].message.content)["results"]
|
||||
question_sql_pairs = await get_validated_question_sql_pairs(
|
||||
results,
|
||||
data_source=data_source,
|
||||
mdl_json=mdl_json,
|
||||
connection_info=connection_info,
|
||||
)
|
||||
sqls = [question_sql_pair["sql"] for question_sql_pair in question_sql_pairs]
|
||||
contexts = await get_contexts_from_sqls(sqls, mdl_json)
|
||||
sqls_data = await get_data_from_wren_engine(sqls, data_source)
|
||||
return [
|
||||
{**quesiton_sql_pair, "context": context, "data": sql_data}
|
||||
for quesiton_sql_pair, context, sql_data in zip(
|
||||
question_sql_pairs, contexts, sqls_data
|
||||
)
|
||||
]
|
||||
except Exception as e:
|
||||
st.error(f"Error generating question-sql-pairs: {e}")
|
||||
return []
|
||||
|
||||
|
||||
def prettify_sql(sql: str) -> str:
|
||||
return sqlparse.format(
|
||||
sql,
|
||||
reindent=True,
|
||||
keyword_case="upper",
|
||||
)
|
||||
|
||||
|
||||
async def get_data_from_wren_engine(
|
||||
sqls: List[str],
|
||||
data_source: str,
|
||||
api_endpoint: str = WREN_IBIS_ENDPOINT,
|
||||
data_sources: list[str] = DATA_SOURCES,
|
||||
timeout: float = TIMEOUT_SECONDS,
|
||||
) -> List[dict]:
|
||||
assert data_source in data_sources, f"Invalid data source: {data_source}"
|
||||
|
||||
async def _get_data(sql: str, data_source: str):
|
||||
async with aiohttp.request(
|
||||
"POST",
|
||||
f"{api_endpoint}/v2/connector/{data_source}/query",
|
||||
json={
|
||||
"sql": add_quotes(sql),
|
||||
"manifestStr": base64.b64encode(
|
||||
orjson.dumps(st.session_state["mdl_json"])
|
||||
).decode(),
|
||||
"connectionInfo": st.session_state["connection_info"],
|
||||
},
|
||||
timeout=aiohttp.ClientTimeout(total=timeout),
|
||||
) as response:
|
||||
if response.status != 200:
|
||||
return {"data": [], "columns": []}
|
||||
|
||||
data = await response.json()
|
||||
column_names = [f"{i}_{col}" for i, col in enumerate(data["columns"])]
|
||||
|
||||
return {"data": data["data"], "columns": column_names}
|
||||
|
||||
async with aiohttp.ClientSession():
|
||||
tasks = []
|
||||
for sql in sqls:
|
||||
task = asyncio.ensure_future(_get_data(sql, data_source))
|
||||
tasks.append(task)
|
||||
|
||||
return await asyncio.gather(*tasks)
|
||||
|
||||
|
||||
@st.cache_data
|
||||
def get_eval_dataset_in_toml_string(mdl: dict, dataset: list) -> str:
|
||||
doc = tomlkit.document()
|
||||
|
||||
doc.add("date", datetime.today().strftime("%Y_%m_%d"))
|
||||
doc.add("mdl", mdl)
|
||||
doc.add("eval_dataset", dataset)
|
||||
|
||||
return tomlkit.dumps(doc)
|
||||
Generated
+212
-78
@@ -1,5 +1,19 @@
|
||||
# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
|
||||
|
||||
[[package]]
|
||||
name = "aiodns"
|
||||
version = "3.2.0"
|
||||
description = "Simple DNS resolver for asyncio"
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
files = [
|
||||
{file = "aiodns-3.2.0-py3-none-any.whl", hash = "sha256:e443c0c27b07da3174a109fd9e736d69058d808f144d3c9d56dbd1776964c5f5"},
|
||||
{file = "aiodns-3.2.0.tar.gz", hash = "sha256:62869b23409349c21b072883ec8998316b234c9a9e36675756e8e317e8768f72"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
pycares = ">=4.0.0"
|
||||
|
||||
[[package]]
|
||||
name = "aiohttp"
|
||||
version = "3.9.5"
|
||||
@@ -86,8 +100,11 @@ files = [
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
aiodns = {version = "*", optional = true, markers = "(sys_platform == \"linux\" or sys_platform == \"darwin\") and extra == \"speedups\""}
|
||||
aiosignal = ">=1.1.2"
|
||||
attrs = ">=17.3.0"
|
||||
Brotli = {version = "*", optional = true, markers = "platform_python_implementation == \"CPython\" and extra == \"speedups\""}
|
||||
brotlicffi = {version = "*", optional = true, markers = "platform_python_implementation != \"CPython\" and extra == \"speedups\""}
|
||||
frozenlist = ">=1.1.1"
|
||||
multidict = ">=4.5,<7.0"
|
||||
yarl = ">=1.0,<2.0"
|
||||
@@ -340,15 +357,54 @@ files = [
|
||||
{file = "Brotli-1.1.0.tar.gz", hash = "sha256:81de08ac11bcb85841e440c13611c00b67d3bf82698314928d0b676362546724"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "brotlicffi"
|
||||
version = "1.1.0.0"
|
||||
description = "Python CFFI bindings to the Brotli library"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
files = [
|
||||
{file = "brotlicffi-1.1.0.0-cp37-abi3-macosx_10_9_x86_64.whl", hash = "sha256:9b7ae6bd1a3f0df532b6d67ff674099a96d22bc0948955cb338488c31bfb8851"},
|
||||
{file = "brotlicffi-1.1.0.0-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:19ffc919fa4fc6ace69286e0a23b3789b4219058313cf9b45625016bf7ff996b"},
|
||||
{file = "brotlicffi-1.1.0.0-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9feb210d932ffe7798ee62e6145d3a757eb6233aa9a4e7db78dd3690d7755814"},
|
||||
{file = "brotlicffi-1.1.0.0-cp37-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:84763dbdef5dd5c24b75597a77e1b30c66604725707565188ba54bab4f114820"},
|
||||
{file = "brotlicffi-1.1.0.0-cp37-abi3-win32.whl", hash = "sha256:1b12b50e07c3911e1efa3a8971543e7648100713d4e0971b13631cce22c587eb"},
|
||||
{file = "brotlicffi-1.1.0.0-cp37-abi3-win_amd64.whl", hash = "sha256:994a4f0681bb6c6c3b0925530a1926b7a189d878e6e5e38fae8efa47c5d9c613"},
|
||||
{file = "brotlicffi-1.1.0.0-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:2e4aeb0bd2540cb91b069dbdd54d458da8c4334ceaf2d25df2f4af576d6766ca"},
|
||||
{file = "brotlicffi-1.1.0.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4b7b0033b0d37bb33009fb2fef73310e432e76f688af76c156b3594389d81391"},
|
||||
{file = "brotlicffi-1.1.0.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:54a07bb2374a1eba8ebb52b6fafffa2afd3c4df85ddd38fcc0511f2bb387c2a8"},
|
||||
{file = "brotlicffi-1.1.0.0-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7901a7dc4b88f1c1475de59ae9be59799db1007b7d059817948d8e4f12e24e35"},
|
||||
{file = "brotlicffi-1.1.0.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:ce01c7316aebc7fce59da734286148b1d1b9455f89cf2c8a4dfce7d41db55c2d"},
|
||||
{file = "brotlicffi-1.1.0.0-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:246f1d1a90279bb6069de3de8d75a8856e073b8ff0b09dcca18ccc14cec85979"},
|
||||
{file = "brotlicffi-1.1.0.0-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cc4bc5d82bc56ebd8b514fb8350cfac4627d6b0743382e46d033976a5f80fab6"},
|
||||
{file = "brotlicffi-1.1.0.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:37c26ecb14386a44b118ce36e546ce307f4810bc9598a6e6cb4f7fca725ae7e6"},
|
||||
{file = "brotlicffi-1.1.0.0-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ca72968ae4eaf6470498d5c2887073f7efe3b1e7d7ec8be11a06a79cc810e990"},
|
||||
{file = "brotlicffi-1.1.0.0-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:add0de5b9ad9e9aa293c3aa4e9deb2b61e99ad6c1634e01d01d98c03e6a354cc"},
|
||||
{file = "brotlicffi-1.1.0.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:9b6068e0f3769992d6b622a1cd2e7835eae3cf8d9da123d7f51ca9c1e9c333e5"},
|
||||
{file = "brotlicffi-1.1.0.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8557a8559509b61e65083f8782329188a250102372576093c88930c875a69838"},
|
||||
{file = "brotlicffi-1.1.0.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2a7ae37e5d79c5bdfb5b4b99f2715a6035e6c5bf538c3746abc8e26694f92f33"},
|
||||
{file = "brotlicffi-1.1.0.0-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:391151ec86bb1c683835980f4816272a87eaddc46bb91cbf44f62228b84d8cca"},
|
||||
{file = "brotlicffi-1.1.0.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:2f3711be9290f0453de8eed5275d93d286abe26b08ab4a35d7452caa1fef532f"},
|
||||
{file = "brotlicffi-1.1.0.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:1a807d760763e398bbf2c6394ae9da5815901aa93ee0a37bca5efe78d4ee3171"},
|
||||
{file = "brotlicffi-1.1.0.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fa8ca0623b26c94fccc3a1fdd895be1743b838f3917300506d04aa3346fd2a14"},
|
||||
{file = "brotlicffi-1.1.0.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3de0cf28a53a3238b252aca9fed1593e9d36c1d116748013339f0949bfc84112"},
|
||||
{file = "brotlicffi-1.1.0.0-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6be5ec0e88a4925c91f3dea2bb0013b3a2accda6f77238f76a34a1ea532a1cb0"},
|
||||
{file = "brotlicffi-1.1.0.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:d9eb71bb1085d996244439154387266fd23d6ad37161f6f52f1cd41dd95a3808"},
|
||||
{file = "brotlicffi-1.1.0.0.tar.gz", hash = "sha256:b77827a689905143f87915310b93b273ab17888fd43ef350d4832c4a71083c13"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
cffi = ">=1.0.0"
|
||||
|
||||
[[package]]
|
||||
name = "cachetools"
|
||||
version = "5.3.3"
|
||||
version = "5.4.0"
|
||||
description = "Extensible memoizing collections and decorators"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
files = [
|
||||
{file = "cachetools-5.3.3-py3-none-any.whl", hash = "sha256:0abad1021d3f8325b2fc1d2e9c8b9c9d57b04c3932657a72465447332c24d945"},
|
||||
{file = "cachetools-5.3.3.tar.gz", hash = "sha256:ba29e2dfa0b8b556606f097407ed1aa62080ee108ab0dc5ec9d6a723a007d105"},
|
||||
{file = "cachetools-5.4.0-py3-none-any.whl", hash = "sha256:3ae3b49a3d5e28a77a0be2b37dbcb89005058959cb2323858c2657c4a8cab474"},
|
||||
{file = "cachetools-5.4.0.tar.gz", hash = "sha256:b8adc2e7c07f105ced7bc56dbb6dfbe7c4a00acce20e2227b3f355be89bc6827"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -657,37 +713,37 @@ typing-inspect = ">=0.4.0,<1"
|
||||
|
||||
[[package]]
|
||||
name = "datasets"
|
||||
version = "2.20.0"
|
||||
version = "2.19.1"
|
||||
description = "HuggingFace community-driven open-source library of datasets"
|
||||
optional = false
|
||||
python-versions = ">=3.8.0"
|
||||
files = [
|
||||
{file = "datasets-2.20.0-py3-none-any.whl", hash = "sha256:76ac02e3bdfff824492e20678f0b6b1b6d080515957fe834b00c2ba8d6b18e5e"},
|
||||
{file = "datasets-2.20.0.tar.gz", hash = "sha256:3c4dbcd27e0f642b9d41d20ff2efa721a5e04b32b2ca4009e0fc9139e324553f"},
|
||||
{file = "datasets-2.19.1-py3-none-any.whl", hash = "sha256:f7a78d15896f45004ccac1c298f3c7121f92f91f6f2bfbd4e4f210f827e6e411"},
|
||||
{file = "datasets-2.19.1.tar.gz", hash = "sha256:0df9ef6c5e9138cdb996a07385220109ff203c204245578b69cca905eb151d3a"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
aiohttp = "*"
|
||||
dill = ">=0.3.0,<0.3.9"
|
||||
filelock = "*"
|
||||
fsspec = {version = ">=2023.1.0,<=2024.5.0", extras = ["http"]}
|
||||
fsspec = {version = ">=2023.1.0,<=2024.3.1", extras = ["http"]}
|
||||
huggingface-hub = ">=0.21.2"
|
||||
multiprocess = "*"
|
||||
numpy = ">=1.17"
|
||||
packaging = "*"
|
||||
pandas = "*"
|
||||
pyarrow = ">=15.0.0"
|
||||
pyarrow = ">=12.0.0"
|
||||
pyarrow-hotfix = "*"
|
||||
pyyaml = ">=5.1"
|
||||
requests = ">=2.32.2"
|
||||
tqdm = ">=4.66.3"
|
||||
requests = ">=2.19.0"
|
||||
tqdm = ">=4.62.1"
|
||||
xxhash = "*"
|
||||
|
||||
[package.extras]
|
||||
apache-beam = ["apache-beam (>=2.26.0)"]
|
||||
audio = ["librosa", "soundfile (>=0.12.1)"]
|
||||
benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
|
||||
dev = ["Pillow (>=9.4.0)", "absl-py", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
|
||||
dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
|
||||
docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
|
||||
jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
|
||||
metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
|
||||
@@ -695,9 +751,9 @@ quality = ["ruff (>=0.3.0)"]
|
||||
s3 = ["s3fs"]
|
||||
tensorflow = ["tensorflow (>=2.6.0)"]
|
||||
tensorflow-gpu = ["tensorflow (>=2.6.0)"]
|
||||
tests = ["Pillow (>=9.4.0)", "absl-py", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
|
||||
tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
|
||||
torch = ["torch"]
|
||||
vision = ["Pillow (>=9.4.0)"]
|
||||
vision = ["Pillow (>=6.2.1)"]
|
||||
|
||||
[[package]]
|
||||
name = "dill"
|
||||
@@ -910,13 +966,13 @@ files = [
|
||||
|
||||
[[package]]
|
||||
name = "fsspec"
|
||||
version = "2024.5.0"
|
||||
version = "2024.3.1"
|
||||
description = "File-system specification"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
files = [
|
||||
{file = "fsspec-2024.5.0-py3-none-any.whl", hash = "sha256:e0fdbc446d67e182f49a70b82cf7889028a63588fde6b222521f10937b2b670c"},
|
||||
{file = "fsspec-2024.5.0.tar.gz", hash = "sha256:1d021b0b0f933e3b3029ed808eb400c08ba101ca2de4b3483fbc9ca23fcee94a"},
|
||||
{file = "fsspec-2024.3.1-py3-none-any.whl", hash = "sha256:918d18d41bf73f0e2b261824baeb1b124bcf771767e3a26425cd7dec3332f512"},
|
||||
{file = "fsspec-2024.3.1.tar.gz", hash = "sha256:f39780e282d7d117ffb42bb96992f8a90795e4d0fb0f661a70ca39fe9c43ded9"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@@ -927,7 +983,7 @@ abfs = ["adlfs"]
|
||||
adl = ["adlfs"]
|
||||
arrow = ["pyarrow (>=1)"]
|
||||
dask = ["dask", "distributed"]
|
||||
dev = ["pre-commit", "ruff"]
|
||||
devel = ["pytest", "pytest-cov"]
|
||||
dropbox = ["dropbox", "dropboxdrivefs", "requests"]
|
||||
full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "dask", "distributed", "dropbox", "dropboxdrivefs", "fusepy", "gcsfs", "libarchive-c", "ocifs", "panel", "paramiko", "pyarrow (>=1)", "pygit2", "requests", "s3fs", "smbprotocol", "tqdm"]
|
||||
fuse = ["fusepy"]
|
||||
@@ -944,9 +1000,6 @@ s3 = ["s3fs"]
|
||||
sftp = ["paramiko"]
|
||||
smb = ["smbprotocol"]
|
||||
ssh = ["paramiko"]
|
||||
test = ["aiohttp (!=4.0.0a0,!=4.0.0a1)", "numpy", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "requests"]
|
||||
test-downstream = ["aiobotocore (>=2.5.4,<3.0.0)", "dask-expr", "dask[dataframe,test]", "moto[server] (>4,<5)", "pytest-timeout", "xarray"]
|
||||
test-full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "cloudpickle", "dask", "distributed", "dropbox", "dropboxdrivefs", "fastparquet", "fusepy", "gcsfs", "jinja2", "kerchunk", "libarchive-c", "lz4", "notebook", "numpy", "ocifs", "pandas", "panel", "paramiko", "pyarrow", "pyarrow (>=1)", "pyftpdlib", "pygit2", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "python-snappy", "requests", "smbprotocol", "tqdm", "urllib3", "zarr", "zstandard"]
|
||||
tqdm = ["tqdm"]
|
||||
|
||||
[[package]]
|
||||
@@ -1536,13 +1589,13 @@ socks = ["socksio (==1.*)"]
|
||||
|
||||
[[package]]
|
||||
name = "huggingface-hub"
|
||||
version = "0.23.4"
|
||||
version = "0.23.5"
|
||||
description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
|
||||
optional = false
|
||||
python-versions = ">=3.8.0"
|
||||
files = [
|
||||
{file = "huggingface_hub-0.23.4-py3-none-any.whl", hash = "sha256:3a0b957aa87150addf0cc7bd71b4d954b78e749850e1e7fb29ebbd2db64ca037"},
|
||||
{file = "huggingface_hub-0.23.4.tar.gz", hash = "sha256:35d99016433900e44ae7efe1c209164a5a81dbbcd53a52f99c281dcd7ce22431"},
|
||||
{file = "huggingface_hub-0.23.5-py3-none-any.whl", hash = "sha256:d7a7d337615e11a45cc14a0ce5a605db6b038dc24af42866f731684825226e90"},
|
||||
{file = "huggingface_hub-0.23.5.tar.gz", hash = "sha256:67a9caba79b71235be3752852ca27da86bd54311d2424ca8afdb8dda056edf98"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@@ -1705,18 +1758,18 @@ referencing = ">=0.31.0"
|
||||
|
||||
[[package]]
|
||||
name = "langchain"
|
||||
version = "0.2.7"
|
||||
version = "0.2.8"
|
||||
description = "Building applications with LLMs through composability"
|
||||
optional = false
|
||||
python-versions = "<4.0,>=3.8.1"
|
||||
files = [
|
||||
{file = "langchain-0.2.7-py3-none-any.whl", hash = "sha256:98e79e0b9a60a9c740b44d5b0135c85f649219308f30d373cf5f10d0efe18b87"},
|
||||
{file = "langchain-0.2.7.tar.gz", hash = "sha256:8742f363d2890854501e0075af04fcb470600f201dec251c9bd5841e1990e73d"},
|
||||
{file = "langchain-0.2.8-py3-none-any.whl", hash = "sha256:53e7dfe50294a14200f33bec22b4e14cb63857ccf0a5500b0d18b0fd51285d58"},
|
||||
{file = "langchain-0.2.8.tar.gz", hash = "sha256:7fecb309e3558cde4e5cf7e9ffb7c1ab3f07121c40a7ff3b0c27135f8120c296"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
aiohttp = ">=3.8.3,<4.0.0"
|
||||
langchain-core = ">=0.2.12,<0.3.0"
|
||||
langchain-core = ">=0.2.19,<0.3.0"
|
||||
langchain-text-splitters = ">=0.2.0,<0.3.0"
|
||||
langsmith = ">=0.1.17,<0.2.0"
|
||||
numpy = {version = ">=1.26.0,<2.0.0", markers = "python_version >= \"3.12\""}
|
||||
@@ -1751,13 +1804,13 @@ tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
|
||||
|
||||
[[package]]
|
||||
name = "langchain-core"
|
||||
version = "0.2.17"
|
||||
version = "0.2.20"
|
||||
description = "Building applications with LLMs through composability"
|
||||
optional = false
|
||||
python-versions = "<4.0,>=3.8.1"
|
||||
files = [
|
||||
{file = "langchain_core-0.2.17-py3-none-any.whl", hash = "sha256:f8b4f64c95b381bd3ac4322bafa9ecee3ca3970aa0aa2829ef11175bcad27249"},
|
||||
{file = "langchain_core-0.2.17.tar.gz", hash = "sha256:f9b8d0f7b5f339ac62e11c417181e87f54e9282af82d1a64c8a7427f3d5d9118"},
|
||||
{file = "langchain_core-0.2.20-py3-none-any.whl", hash = "sha256:16cc4da6f7ebf33accea7af45a70480733dc852ab291030fb6924865bd7caf76"},
|
||||
{file = "langchain_core-0.2.20.tar.gz", hash = "sha256:a66c439e085d8c75f822f7650a5551d17bada4003521173c763d875d949e4ed5"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@@ -1827,13 +1880,13 @@ openai = ["openai (>=0.27.8)"]
|
||||
|
||||
[[package]]
|
||||
name = "langsmith"
|
||||
version = "0.1.85"
|
||||
version = "0.1.88"
|
||||
description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
|
||||
optional = false
|
||||
python-versions = "<4.0,>=3.8.1"
|
||||
files = [
|
||||
{file = "langsmith-0.1.85-py3-none-any.whl", hash = "sha256:c1f94384f10cea96f7b4d33fd3db7ec180c03c7468877d50846f881d2017ff94"},
|
||||
{file = "langsmith-0.1.85.tar.gz", hash = "sha256:acff31f9e53efa48586cf8e32f65625a335c74d7c4fa306d1655ac18452296f6"},
|
||||
{file = "langsmith-0.1.88-py3-none-any.whl", hash = "sha256:460ebb7de440afd150fcea8f54ca8779821f2228cd59e149e5845c9dbe06db16"},
|
||||
{file = "langsmith-0.1.88.tar.gz", hash = "sha256:28a07dec19197f4808aa2628d5a3ccafcbe14cc137aef0e607bbd128e7907821"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@@ -2631,13 +2684,13 @@ testing = ["pytest", "pytest-benchmark"]
|
||||
|
||||
[[package]]
|
||||
name = "portalocker"
|
||||
version = "2.10.0"
|
||||
version = "2.10.1"
|
||||
description = "Wraps the portalocker recipe for easy usage"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
files = [
|
||||
{file = "portalocker-2.10.0-py3-none-any.whl", hash = "sha256:48944147b2cd42520549bc1bb8fe44e220296e56f7c3d551bc6ecce69d9b0de1"},
|
||||
{file = "portalocker-2.10.0.tar.gz", hash = "sha256:49de8bc0a2f68ca98bf9e219c81a3e6b27097c7bf505a87c5a112ce1aaeb9b81"},
|
||||
{file = "portalocker-2.10.1-py3-none-any.whl", hash = "sha256:53a5984ebc86a025552264b459b46a2086e269b21823cb572f8f28ee759e45bf"},
|
||||
{file = "portalocker-2.10.1.tar.gz", hash = "sha256:ef1bf844e878ab08aee7e40184156e1151f228f103aa5c6bd0724cc330960f8f"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@@ -2821,52 +2874,42 @@ files = [
|
||||
|
||||
[[package]]
|
||||
name = "pyarrow"
|
||||
version = "16.1.0"
|
||||
version = "17.0.0"
|
||||
description = "Python library for Apache Arrow"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
files = [
|
||||
{file = "pyarrow-16.1.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:17e23b9a65a70cc733d8b738baa6ad3722298fa0c81d88f63ff94bf25eaa77b9"},
|
||||
{file = "pyarrow-16.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4740cc41e2ba5d641071d0ab5e9ef9b5e6e8c7611351a5cb7c1d175eaf43674a"},
|
||||
{file = "pyarrow-16.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:98100e0268d04e0eec47b73f20b39c45b4006f3c4233719c3848aa27a03c1aef"},
|
||||
{file = "pyarrow-16.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f68f409e7b283c085f2da014f9ef81e885d90dcd733bd648cfba3ef265961848"},
|
||||
{file = "pyarrow-16.1.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:a8914cd176f448e09746037b0c6b3a9d7688cef451ec5735094055116857580c"},
|
||||
{file = "pyarrow-16.1.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:48be160782c0556156d91adbdd5a4a7e719f8d407cb46ae3bb4eaee09b3111bd"},
|
||||
{file = "pyarrow-16.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:9cf389d444b0f41d9fe1444b70650fea31e9d52cfcb5f818b7888b91b586efff"},
|
||||
{file = "pyarrow-16.1.0-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:d0ebea336b535b37eee9eee31761813086d33ed06de9ab6fc6aaa0bace7b250c"},
|
||||
{file = "pyarrow-16.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2e73cfc4a99e796727919c5541c65bb88b973377501e39b9842ea71401ca6c1c"},
|
||||
{file = "pyarrow-16.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bf9251264247ecfe93e5f5a0cd43b8ae834f1e61d1abca22da55b20c788417f6"},
|
||||
{file = "pyarrow-16.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ddf5aace92d520d3d2a20031d8b0ec27b4395cab9f74e07cc95edf42a5cc0147"},
|
||||
{file = "pyarrow-16.1.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:25233642583bf658f629eb230b9bb79d9af4d9f9229890b3c878699c82f7d11e"},
|
||||
{file = "pyarrow-16.1.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:a33a64576fddfbec0a44112eaf844c20853647ca833e9a647bfae0582b2ff94b"},
|
||||
{file = "pyarrow-16.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:185d121b50836379fe012753cf15c4ba9638bda9645183ab36246923875f8d1b"},
|
||||
{file = "pyarrow-16.1.0-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:2e51ca1d6ed7f2e9d5c3c83decf27b0d17bb207a7dea986e8dc3e24f80ff7d6f"},
|
||||
{file = "pyarrow-16.1.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:06ebccb6f8cb7357de85f60d5da50e83507954af617d7b05f48af1621d331c9a"},
|
||||
{file = "pyarrow-16.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b04707f1979815f5e49824ce52d1dceb46e2f12909a48a6a753fe7cafbc44a0c"},
|
||||
{file = "pyarrow-16.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0d32000693deff8dc5df444b032b5985a48592c0697cb6e3071a5d59888714e2"},
|
||||
{file = "pyarrow-16.1.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:8785bb10d5d6fd5e15d718ee1d1f914fe768bf8b4d1e5e9bf253de8a26cb1628"},
|
||||
{file = "pyarrow-16.1.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:e1369af39587b794873b8a307cc6623a3b1194e69399af0efd05bb202195a5a7"},
|
||||
{file = "pyarrow-16.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:febde33305f1498f6df85e8020bca496d0e9ebf2093bab9e0f65e2b4ae2b3444"},
|
||||
{file = "pyarrow-16.1.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:b5f5705ab977947a43ac83b52ade3b881eb6e95fcc02d76f501d549a210ba77f"},
|
||||
{file = "pyarrow-16.1.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:0d27bf89dfc2576f6206e9cd6cf7a107c9c06dc13d53bbc25b0bd4556f19cf5f"},
|
||||
{file = "pyarrow-16.1.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0d07de3ee730647a600037bc1d7b7994067ed64d0eba797ac74b2bc77384f4c2"},
|
||||
{file = "pyarrow-16.1.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fbef391b63f708e103df99fbaa3acf9f671d77a183a07546ba2f2c297b361e83"},
|
||||
{file = "pyarrow-16.1.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:19741c4dbbbc986d38856ee7ddfdd6a00fc3b0fc2d928795b95410d38bb97d15"},
|
||||
{file = "pyarrow-16.1.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:f2c5fb249caa17b94e2b9278b36a05ce03d3180e6da0c4c3b3ce5b2788f30eed"},
|
||||
{file = "pyarrow-16.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:e6b6d3cd35fbb93b70ade1336022cc1147b95ec6af7d36906ca7fe432eb09710"},
|
||||
{file = "pyarrow-16.1.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:18da9b76a36a954665ccca8aa6bd9f46c1145f79c0bb8f4f244f5f8e799bca55"},
|
||||
{file = "pyarrow-16.1.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:99f7549779b6e434467d2aa43ab2b7224dd9e41bdde486020bae198978c9e05e"},
|
||||
{file = "pyarrow-16.1.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f07fdffe4fd5b15f5ec15c8b64584868d063bc22b86b46c9695624ca3505b7b4"},
|
||||
{file = "pyarrow-16.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ddfe389a08ea374972bd4065d5f25d14e36b43ebc22fc75f7b951f24378bf0b5"},
|
||||
{file = "pyarrow-16.1.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:3b20bd67c94b3a2ea0a749d2a5712fc845a69cb5d52e78e6449bbd295611f3aa"},
|
||||
{file = "pyarrow-16.1.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:ba8ac20693c0bb0bf4b238751d4409e62852004a8cf031c73b0e0962b03e45e3"},
|
||||
{file = "pyarrow-16.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:31a1851751433d89a986616015841977e0a188662fcffd1a5677453f1df2de0a"},
|
||||
{file = "pyarrow-16.1.0.tar.gz", hash = "sha256:15fbb22ea96d11f0b5768504a3f961edab25eaf4197c341720c4a387f6c60315"},
|
||||
{file = "pyarrow-17.0.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:a5c8b238d47e48812ee577ee20c9a2779e6a5904f1708ae240f53ecbee7c9f07"},
|
||||
{file = "pyarrow-17.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:db023dc4c6cae1015de9e198d41250688383c3f9af8f565370ab2b4cb5f62655"},
|
||||
{file = "pyarrow-17.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:da1e060b3876faa11cee287839f9cc7cdc00649f475714b8680a05fd9071d545"},
|
||||
{file = "pyarrow-17.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75c06d4624c0ad6674364bb46ef38c3132768139ddec1c56582dbac54f2663e2"},
|
||||
{file = "pyarrow-17.0.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:fa3c246cc58cb5a4a5cb407a18f193354ea47dd0648194e6265bd24177982fe8"},
|
||||
{file = "pyarrow-17.0.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:f7ae2de664e0b158d1607699a16a488de3d008ba99b3a7aa5de1cbc13574d047"},
|
||||
{file = "pyarrow-17.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:5984f416552eea15fd9cee03da53542bf4cddaef5afecefb9aa8d1010c335087"},
|
||||
{file = "pyarrow-17.0.0-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:1c8856e2ef09eb87ecf937104aacfa0708f22dfeb039c363ec99735190ffb977"},
|
||||
{file = "pyarrow-17.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2e19f569567efcbbd42084e87f948778eb371d308e137a0f97afe19bb860ccb3"},
|
||||
{file = "pyarrow-17.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6b244dc8e08a23b3e352899a006a26ae7b4d0da7bb636872fa8f5884e70acf15"},
|
||||
{file = "pyarrow-17.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b72e87fe3e1db343995562f7fff8aee354b55ee83d13afba65400c178ab2597"},
|
||||
{file = "pyarrow-17.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:dc5c31c37409dfbc5d014047817cb4ccd8c1ea25d19576acf1a001fe07f5b420"},
|
||||
{file = "pyarrow-17.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:e3343cb1e88bc2ea605986d4b94948716edc7a8d14afd4e2c097232f729758b4"},
|
||||
{file = "pyarrow-17.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:a27532c38f3de9eb3e90ecab63dfda948a8ca859a66e3a47f5f42d1e403c4d03"},
|
||||
{file = "pyarrow-17.0.0-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:9b8a823cea605221e61f34859dcc03207e52e409ccf6354634143e23af7c8d22"},
|
||||
{file = "pyarrow-17.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:f1e70de6cb5790a50b01d2b686d54aaf73da01266850b05e3af2a1bc89e16053"},
|
||||
{file = "pyarrow-17.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0071ce35788c6f9077ff9ecba4858108eebe2ea5a3f7cf2cf55ebc1dbc6ee24a"},
|
||||
{file = "pyarrow-17.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:757074882f844411fcca735e39aae74248a1531367a7c80799b4266390ae51cc"},
|
||||
{file = "pyarrow-17.0.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:9ba11c4f16976e89146781a83833df7f82077cdab7dc6232c897789343f7891a"},
|
||||
{file = "pyarrow-17.0.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:b0c6ac301093b42d34410b187bba560b17c0330f64907bfa4f7f7f2444b0cf9b"},
|
||||
{file = "pyarrow-17.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:392bc9feabc647338e6c89267635e111d71edad5fcffba204425a7c8d13610d7"},
|
||||
{file = "pyarrow-17.0.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:af5ff82a04b2171415f1410cff7ebb79861afc5dae50be73ce06d6e870615204"},
|
||||
{file = "pyarrow-17.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:edca18eaca89cd6382dfbcff3dd2d87633433043650c07375d095cd3517561d8"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
numpy = ">=1.16.6"
|
||||
|
||||
[package.extras]
|
||||
test = ["cffi", "hypothesis", "pandas", "pytest", "pytz"]
|
||||
|
||||
[[package]]
|
||||
name = "pyarrow-hotfix"
|
||||
version = "0.6"
|
||||
@@ -2878,6 +2921,72 @@ files = [
|
||||
{file = "pyarrow_hotfix-0.6.tar.gz", hash = "sha256:79d3e030f7ff890d408a100ac16d6f00b14d44a502d7897cd9fc3e3a534e9945"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pycares"
|
||||
version = "4.4.0"
|
||||
description = "Python interface for c-ares"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
files = [
|
||||
{file = "pycares-4.4.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:24da119850841d16996713d9c3374ca28a21deee056d609fbbed29065d17e1f6"},
|
||||
{file = "pycares-4.4.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8f64cb58729689d4d0e78f0bfb4c25ce2f851d0274c0273ac751795c04b8798a"},
|
||||
{file = "pycares-4.4.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d33e2a1120887e89075f7f814ec144f66a6ce06a54f5722ccefc62fbeda83cff"},
|
||||
{file = "pycares-4.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c680fef1b502ee680f8f0b95a41af4ec2c234e50e16c0af5bbda31999d3584bd"},
|
||||
{file = "pycares-4.4.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fff16b09042ba077f7b8aa5868d1d22456f0002574d0ba43462b10a009331677"},
|
||||
{file = "pycares-4.4.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:229a1675eb33bc9afb1fc463e73ee334950ccc485bc83a43f6ae5839fb4d5fa3"},
|
||||
{file = "pycares-4.4.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:3aebc73e5ad70464f998f77f2da2063aa617cbd8d3e8174dd7c5b4518f967153"},
|
||||
{file = "pycares-4.4.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:6ef64649eba56448f65e26546d85c860709844d2fc22ef14d324fe0b27f761a9"},
|
||||
{file = "pycares-4.4.0-cp310-cp310-win32.whl", hash = "sha256:4afc2644423f4eef97857a9fd61be9758ce5e336b4b0bd3d591238bb4b8b03e0"},
|
||||
{file = "pycares-4.4.0-cp310-cp310-win_amd64.whl", hash = "sha256:5ed4e04af4012f875b78219d34434a6d08a67175150ac1b79eb70ab585d4ba8c"},
|
||||
{file = "pycares-4.4.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:bce8db2fc6f3174bd39b81405210b9b88d7b607d33e56a970c34a0c190da0490"},
|
||||
{file = "pycares-4.4.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:9a0303428d013ccf5c51de59c83f9127aba6200adb7fd4be57eddb432a1edd2a"},
|
||||
{file = "pycares-4.4.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:afb91792f1556f97be7f7acb57dc7756d89c5a87bd8b90363a77dbf9ea653817"},
|
||||
{file = "pycares-4.4.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b61579cecf1f4d616e5ea31a6e423a16680ab0d3a24a2ffe7bb1d4ee162477ff"},
|
||||
{file = "pycares-4.4.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b7af06968cbf6851566e806bf3e72825b0e6671832a2cbe840be1d2d65350710"},
|
||||
{file = "pycares-4.4.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:ceb12974367b0a68a05d52f4162b29f575d241bd53de155efe632bf2c943c7f6"},
|
||||
{file = "pycares-4.4.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:2eeec144bcf6a7b6f2d74d6e70cbba7886a84dd373c886f06cb137a07de4954c"},
|
||||
{file = "pycares-4.4.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e3a6f7cfdfd11eb5493d6d632e582408c8f3b429f295f8799c584c108b28db6f"},
|
||||
{file = "pycares-4.4.0-cp311-cp311-win32.whl", hash = "sha256:34736a2ffaa9c08ca9c707011a2d7b69074bbf82d645d8138bba771479b2362f"},
|
||||
{file = "pycares-4.4.0-cp311-cp311-win_amd64.whl", hash = "sha256:eb66c30eb11e877976b7ead13632082a8621df648c408b8e15cdb91a452dd502"},
|
||||
{file = "pycares-4.4.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:fd644505a8cfd7f6584d33a9066d4e3d47700f050ef1490230c962de5dfb28c6"},
|
||||
{file = "pycares-4.4.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:52084961262232ec04bd75f5043aed7e5d8d9695e542ff691dfef0110209f2d4"},
|
||||
{file = "pycares-4.4.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0c5368206057884cde18602580083aeaad9b860e2eac14fd253543158ce1e93"},
|
||||
{file = "pycares-4.4.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:112a4979c695b1c86f6782163d7dec58d57a3b9510536dcf4826550f9053dd9a"},
|
||||
{file = "pycares-4.4.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8d186dafccdaa3409194c0f94db93c1a5d191145a275f19da6591f9499b8e7b8"},
|
||||
{file = "pycares-4.4.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:64965dc19c578a683ea73487a215a8897276224e004d50eeb21f0bc7a0b63c88"},
|
||||
{file = "pycares-4.4.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:ed2a38e34bec6f2586435f6ff0bc5fe11d14bebd7ed492cf739a424e81681540"},
|
||||
{file = "pycares-4.4.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:94d6962db81541eb0396d2f0dfcbb18cdb8c8b251d165efc2d974ae652c547d4"},
|
||||
{file = "pycares-4.4.0-cp312-cp312-win32.whl", hash = "sha256:1168a48a834813aa80f412be2df4abaf630528a58d15c704857448b20b1675c0"},
|
||||
{file = "pycares-4.4.0-cp312-cp312-win_amd64.whl", hash = "sha256:db24c4e7fea4a052c6e869cbf387dd85d53b9736cfe1ef5d8d568d1ca925e977"},
|
||||
{file = "pycares-4.4.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:21a5a0468861ec7df7befa69050f952da13db5427ae41ffe4713bc96291d1d95"},
|
||||
{file = "pycares-4.4.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:22c00bf659a9fa44d7b405cf1cd69b68b9d37537899898d8cbe5dffa4016b273"},
|
||||
{file = "pycares-4.4.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23aa3993a352491a47fcf17867f61472f32f874df4adcbb486294bd9fbe8abee"},
|
||||
{file = "pycares-4.4.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:813d661cbe2e37d87da2d16b7110a6860e93ddb11735c6919c8a3545c7b9c8d8"},
|
||||
{file = "pycares-4.4.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:77cf5a2fd5583c670de41a7f4a7b46e5cbabe7180d8029f728571f4d2e864084"},
|
||||
{file = "pycares-4.4.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:3eaa6681c0a3e3f3868c77aca14b7760fed35fdfda2fe587e15c701950e7bc69"},
|
||||
{file = "pycares-4.4.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:ad58e284a658a8a6a84af2e0b62f2f961f303cedfe551854d7bd40c3cbb61912"},
|
||||
{file = "pycares-4.4.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:bfb89ca9e3d0a9b5332deeb666b2ede9d3469107742158f4aeda5ce032d003f4"},
|
||||
{file = "pycares-4.4.0-cp38-cp38-win32.whl", hash = "sha256:f36bdc1562142e3695555d2f4ac0cb69af165eddcefa98efc1c79495b533481f"},
|
||||
{file = "pycares-4.4.0-cp38-cp38-win_amd64.whl", hash = "sha256:902461a92b6a80fd5041a2ec5235680c7cc35e43615639ec2a40e63fca2dfb51"},
|
||||
{file = "pycares-4.4.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:7bddc6adba8f699728f7fc1c9ce8cef359817ad78e2ed52b9502cb5f8dc7f741"},
|
||||
{file = "pycares-4.4.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:cb49d5805cd347c404f928c5ae7c35e86ba0c58ffa701dbe905365e77ce7d641"},
|
||||
{file = "pycares-4.4.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:56cf3349fa3a2e67ed387a7974c11d233734636fe19facfcda261b411af14d80"},
|
||||
{file = "pycares-4.4.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8bf2eaa83a5987e48fa63302f0fe7ce3275cfda87b34d40fef9ce703fb3ac002"},
|
||||
{file = "pycares-4.4.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:82bba2ab77eb5addbf9758d514d9bdef3c1bfe7d1649a47bd9a0d55a23ef478b"},
|
||||
{file = "pycares-4.4.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:c6a8bde63106f162fca736e842a916853cad3c8d9d137e11c9ffa37efa818b02"},
|
||||
{file = "pycares-4.4.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:f5f646eec041db6ffdbcaf3e0756fb92018f7af3266138c756bb09d2b5baadec"},
|
||||
{file = "pycares-4.4.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:9dc04c54c6ea615210c1b9e803d0e2d2255f87a3d5d119b6482c8f0dfa15b26b"},
|
||||
{file = "pycares-4.4.0-cp39-cp39-win32.whl", hash = "sha256:97892cced5794d721fb4ff8765764aa4ea48fe8b2c3820677505b96b83d4ef47"},
|
||||
{file = "pycares-4.4.0-cp39-cp39-win_amd64.whl", hash = "sha256:917f08f0b5d9324e9a34211e68d27447c552b50ab967044776bbab7e42a553a2"},
|
||||
{file = "pycares-4.4.0.tar.gz", hash = "sha256:f47579d508f2f56eddd16ce72045782ad3b1b3b678098699e2b6a1b30733e1c2"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
cffi = ">=1.5.0"
|
||||
|
||||
[package.extras]
|
||||
idna = ["idna (>=2.1)"]
|
||||
|
||||
[[package]]
|
||||
name = "pycparser"
|
||||
version = "2.22"
|
||||
@@ -3513,13 +3622,13 @@ files = [
|
||||
|
||||
[[package]]
|
||||
name = "requests"
|
||||
version = "2.32.3"
|
||||
version = "2.31.0"
|
||||
description = "Python HTTP for Humans."
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
python-versions = ">=3.7"
|
||||
files = [
|
||||
{file = "requests-2.32.3-py3-none-any.whl", hash = "sha256:70761cfe03c773ceb22aa2f671b4757976145175cdfca038c02654d061d6dcc6"},
|
||||
{file = "requests-2.32.3.tar.gz", hash = "sha256:55365417734eb18255590a9ff9eb97e9e1da868d4ccd6402399eaf68af20a760"},
|
||||
{file = "requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"},
|
||||
{file = "requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@@ -3926,6 +4035,20 @@ watchdog = {version = ">=2.1.5", markers = "platform_system != \"Darwin\""}
|
||||
[package.extras]
|
||||
snowflake = ["snowflake-connector-python (>=2.8.0)", "snowflake-snowpark-python (>=0.9.0)"]
|
||||
|
||||
[[package]]
|
||||
name = "streamlit-tags"
|
||||
version = "1.2.8"
|
||||
description = "Tags custom component for Streamlit"
|
||||
optional = false
|
||||
python-versions = ">=3.6"
|
||||
files = [
|
||||
{file = "streamlit_tags-1.2.8-py3-none-any.whl", hash = "sha256:c71b10666f3fce67d8e0b3c089aa50dc48830d310223fb88005b08f157586f95"},
|
||||
{file = "streamlit_tags-1.2.8.tar.gz", hash = "sha256:9ea46b21f206dc73164e59e3c800a96c863c90af57afde20115f001a6d986583"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
streamlit = ">=0.63"
|
||||
|
||||
[[package]]
|
||||
name = "tenacity"
|
||||
version = "8.5.0"
|
||||
@@ -4004,6 +4127,17 @@ files = [
|
||||
{file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tomlkit"
|
||||
version = "0.12.5"
|
||||
description = "Style preserving TOML library"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
files = [
|
||||
{file = "tomlkit-0.12.5-py3-none-any.whl", hash = "sha256:af914f5a9c59ed9d0762c7b64d3b5d5df007448eb9cd2edc8a46b1eafead172f"},
|
||||
{file = "tomlkit-0.12.5.tar.gz", hash = "sha256:eef34fba39834d4d6b73c9ba7f3e4d1c417a4e56f89a7e96e090dd0d24b8fb3c"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "toolz"
|
||||
version = "0.12.1"
|
||||
@@ -4797,4 +4931,4 @@ testing = ["coverage (>=5.0.3)", "zope.event", "zope.testing"]
|
||||
[metadata]
|
||||
lock-version = "2.0"
|
||||
python-versions = ">=3.12.*, <4.0"
|
||||
content-hash = "4592f4cc15dcf7566fc314c127df2d649f20ecc05c2a672d2c982ad5df5174e1"
|
||||
content-hash = "7159216c0183970d94b3b819c5460bac914e8ddbbdc96bb618791c5978899b64"
|
||||
|
||||
@@ -21,7 +21,7 @@ sqlparse = "==0.5.0"
|
||||
sqlglot = "==22.5.0"
|
||||
orjson = "==3.10.3"
|
||||
sf-hamilton = {version = "==1.63.0", extras = ["visualization"]}
|
||||
aiohttp = "==3.9.5"
|
||||
aiohttp = {extras = ["speedups"], version = "==3.9.5"}
|
||||
ollama-haystack = "==0.0.6"
|
||||
langfuse = "==2.35.0"
|
||||
ollama = "==0.2.1"
|
||||
@@ -40,6 +40,13 @@ psycopg2-binary = "==2.9.9"
|
||||
setuptools = "==70.0.0"
|
||||
locust = "==2.28.0"
|
||||
|
||||
[tool.poetry.group.eval.dependencies]
|
||||
tomlkit = "==0.12.5"
|
||||
streamlit-tags = "==1.2.8"
|
||||
|
||||
[tool.poetry.group.demo.dependencies]
|
||||
requests = "==2.31.0"
|
||||
|
||||
[build-system]
|
||||
requires = ["poetry-core"]
|
||||
build-backend = "poetry.core.masonry.api"
|
||||
|
||||
@@ -15,7 +15,6 @@ class Engine(metaclass=ABCMeta):
|
||||
self,
|
||||
sql: str,
|
||||
session: aiohttp.ClientSession,
|
||||
properties: Dict[str, Any] = {},
|
||||
) -> Tuple[bool, Optional[Dict[str, Any]]]:
|
||||
...
|
||||
|
||||
|
||||
@@ -1,12 +1,13 @@
|
||||
import asyncio
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
import aiohttp
|
||||
import backoff
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from src.utils import load_env_vars
|
||||
|
||||
load_env_vars()
|
||||
if Path(".env.dev").exists():
|
||||
load_dotenv(".env.dev", override=True)
|
||||
|
||||
|
||||
@backoff.on_exception(backoff.expo, aiohttp.ClientError, max_time=60, max_tries=3)
|
||||
|
||||
@@ -17,7 +17,7 @@ from src.pipelines.ask.components.prompts import (
|
||||
TEXT_TO_SQL_RULES,
|
||||
text_to_sql_system_prompt,
|
||||
)
|
||||
from src.utils import async_timer, init_providers, timer
|
||||
from src.utils import async_timer, timer
|
||||
from src.web.v1.services.ask import AskRequest
|
||||
|
||||
logger = logging.getLogger("wren-ai-service")
|
||||
@@ -234,7 +234,7 @@ class FollowUpGeneration(BasicPipeline):
|
||||
if __name__ == "__main__":
|
||||
from langfuse.decorators import langfuse_context
|
||||
|
||||
from src.utils import init_langfuse, load_env_vars
|
||||
from src.utils import init_langfuse, init_providers, load_env_vars
|
||||
|
||||
load_env_vars()
|
||||
init_langfuse()
|
||||
|
||||
@@ -19,7 +19,7 @@ from src.pipelines.ask.components.prompts import (
|
||||
TEXT_TO_SQL_RULES,
|
||||
text_to_sql_system_prompt,
|
||||
)
|
||||
from src.utils import async_timer, init_providers, timer
|
||||
from src.utils import async_timer, timer
|
||||
|
||||
logger = logging.getLogger("wren-ai-service")
|
||||
|
||||
@@ -192,7 +192,7 @@ class Generation(BasicPipeline):
|
||||
if __name__ == "__main__":
|
||||
from langfuse.decorators import langfuse_context
|
||||
|
||||
from src.utils import init_langfuse, load_env_vars
|
||||
from src.utils import init_langfuse, init_providers, load_env_vars
|
||||
|
||||
load_env_vars()
|
||||
init_langfuse()
|
||||
|
||||
@@ -13,7 +13,6 @@ from src.core.pipeline import BasicPipeline, async_validate
|
||||
from src.core.provider import DocumentStoreProvider, EmbedderProvider
|
||||
from src.utils import (
|
||||
async_timer,
|
||||
init_providers,
|
||||
timer,
|
||||
)
|
||||
|
||||
@@ -149,7 +148,7 @@ class HistoricalQuestion(BasicPipeline):
|
||||
if __name__ == "__main__":
|
||||
from langfuse.decorators import langfuse_context
|
||||
|
||||
from src.utils import init_langfuse, load_env_vars
|
||||
from src.utils import init_langfuse, init_providers, load_env_vars
|
||||
|
||||
load_env_vars()
|
||||
init_langfuse()
|
||||
|
||||
@@ -9,7 +9,7 @@ from langfuse.decorators import observe
|
||||
|
||||
from src.core.pipeline import BasicPipeline, async_validate
|
||||
from src.core.provider import DocumentStoreProvider, EmbedderProvider
|
||||
from src.utils import async_timer, init_providers
|
||||
from src.utils import async_timer
|
||||
|
||||
logger = logging.getLogger("wren-ai-service")
|
||||
|
||||
@@ -83,7 +83,7 @@ class Retrieval(BasicPipeline):
|
||||
if __name__ == "__main__":
|
||||
from langfuse.decorators import langfuse_context
|
||||
|
||||
from src.utils import init_langfuse, load_env_vars
|
||||
from src.utils import init_langfuse, init_providers, load_env_vars
|
||||
|
||||
load_env_vars()
|
||||
init_langfuse()
|
||||
|
||||
@@ -17,7 +17,7 @@ from src.pipelines.ask.components.prompts import (
|
||||
TEXT_TO_SQL_RULES,
|
||||
text_to_sql_system_prompt,
|
||||
)
|
||||
from src.utils import async_timer, init_providers, timer
|
||||
from src.utils import async_timer, timer
|
||||
|
||||
logger = logging.getLogger("wren-ai-service")
|
||||
|
||||
@@ -158,7 +158,7 @@ class SQLCorrection(BasicPipeline):
|
||||
if __name__ == "__main__":
|
||||
from langfuse.decorators import langfuse_context
|
||||
|
||||
from src.utils import init_langfuse, load_env_vars
|
||||
from src.utils import init_langfuse, init_providers, load_env_vars
|
||||
|
||||
load_env_vars()
|
||||
init_langfuse()
|
||||
|
||||
@@ -24,7 +24,6 @@ from src.pipelines.ask_details.components.prompts import (
|
||||
)
|
||||
from src.utils import (
|
||||
async_timer,
|
||||
init_providers,
|
||||
timer,
|
||||
)
|
||||
|
||||
@@ -197,7 +196,7 @@ class Generation(BasicPipeline):
|
||||
if __name__ == "__main__":
|
||||
from langfuse.decorators import langfuse_context, observe
|
||||
|
||||
from src.utils import init_langfuse, load_env_vars
|
||||
from src.utils import init_langfuse, init_providers, load_env_vars
|
||||
|
||||
load_env_vars()
|
||||
init_langfuse()
|
||||
|
||||
@@ -17,7 +17,7 @@ from tqdm import tqdm
|
||||
|
||||
from src.core.pipeline import BasicPipeline, async_validate
|
||||
from src.core.provider import DocumentStoreProvider, EmbedderProvider
|
||||
from src.utils import async_timer, init_providers, timer
|
||||
from src.utils import async_timer, timer
|
||||
|
||||
logger = logging.getLogger("wren-ai-service")
|
||||
|
||||
@@ -124,6 +124,25 @@ class DDLConverter:
|
||||
|
||||
logger.debug(f"original mdl_json: {mdl}")
|
||||
|
||||
ddl_commands = self.get_ddl_commands(mdl)
|
||||
|
||||
return {
|
||||
"documents": [
|
||||
Document(
|
||||
id=str(i),
|
||||
meta={"id": str(i)},
|
||||
content=ddl_command,
|
||||
)
|
||||
for i, ddl_command in enumerate(
|
||||
tqdm(
|
||||
ddl_commands,
|
||||
desc="indexing ddl commands into the ddl store",
|
||||
)
|
||||
)
|
||||
]
|
||||
}
|
||||
|
||||
def get_ddl_commands(self, mdl: Dict[str, Any]) -> List[str]:
|
||||
semantics = {
|
||||
"models": [],
|
||||
"relationships": mdl["relationships"],
|
||||
@@ -159,7 +178,7 @@ class DDLConverter:
|
||||
}
|
||||
)
|
||||
|
||||
ddl_commands = (
|
||||
return (
|
||||
self._convert_models_and_relationships(
|
||||
semantics["models"], semantics["relationships"]
|
||||
)
|
||||
@@ -167,22 +186,6 @@ class DDLConverter:
|
||||
+ self._convert_views(semantics["views"])
|
||||
)
|
||||
|
||||
return {
|
||||
"documents": [
|
||||
Document(
|
||||
id=str(i),
|
||||
meta={"id": str(i)},
|
||||
content=ddl_command,
|
||||
)
|
||||
for i, ddl_command in enumerate(
|
||||
tqdm(
|
||||
ddl_commands,
|
||||
desc="indexing ddl commands into the ddl store",
|
||||
)
|
||||
)
|
||||
]
|
||||
}
|
||||
|
||||
# TODO: refactor this method
|
||||
def _convert_models_and_relationships(
|
||||
self, models: List[Dict[str, Any]], relationships: List[Dict[str, Any]]
|
||||
@@ -458,7 +461,7 @@ class Indexing(BasicPipeline):
|
||||
if __name__ == "__main__":
|
||||
from langfuse.decorators import langfuse_context
|
||||
|
||||
from src.utils import init_langfuse, load_env_vars
|
||||
from src.utils import init_langfuse, init_providers, load_env_vars
|
||||
|
||||
load_env_vars()
|
||||
init_langfuse()
|
||||
|
||||
@@ -1,37 +0,0 @@
|
||||
import argparse
|
||||
import os
|
||||
import shutil
|
||||
from pathlib import Path
|
||||
|
||||
from .utils import load_env_vars
|
||||
|
||||
load_env_vars()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Prepare the MDL JSON file for the Wren engine using the Spider dataset"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--dataset_name",
|
||||
type=str,
|
||||
default=os.getenv("DATASET_NAME"),
|
||||
help="Database name of the Spider dataset",
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
dataset_name = args.dataset_name
|
||||
|
||||
assert Path(
|
||||
f"src/eval/data/{dataset_name}_mdl.json"
|
||||
).exists(), f"File not found in src/eval/data: {dataset_name}_mdl.json"
|
||||
|
||||
# remove all files in src/eval/wren-engine/etc/mdl
|
||||
os.system("rm -rf tools/dev/etc/mdl/*")
|
||||
os.makedirs("tools/dev/etc/mdl", exist_ok=True)
|
||||
|
||||
# move the file to src/eval/wren-engine/etc/mdl
|
||||
shutil.copyfile(
|
||||
f"src/eval/data/{dataset_name}_mdl.json",
|
||||
f"tools/dev/etc/mdl/{dataset_name}_mdl.json",
|
||||
)
|
||||
@@ -21,7 +21,6 @@ class WrenUI(Engine):
|
||||
self,
|
||||
sql: str,
|
||||
session: aiohttp.ClientSession,
|
||||
properties: Dict[str, Any] = {},
|
||||
) -> Tuple[bool, Optional[Dict[str, Any]]]:
|
||||
async with session.post(
|
||||
f"{self._endpoint}/api/graphql",
|
||||
@@ -46,27 +45,25 @@ class WrenUI(Engine):
|
||||
class WrenIbis(Engine):
|
||||
def __init__(self, endpoint: str = os.getenv("WREN_IBIS_ENDPOINT")):
|
||||
self._endpoint = endpoint
|
||||
self._source = os.getenv("WREN_IBIS_SOURCE")
|
||||
self._manifest = os.getenv("WREN_IBIS_MANIFEST")
|
||||
self._connection_info = (
|
||||
orjson.loads(base64.b64decode(os.getenv("WREN_IBIS_CONNECTION_INFO")))
|
||||
if os.getenv("WREN_IBIS_CONNECTION_INFO")
|
||||
else {}
|
||||
)
|
||||
|
||||
async def dry_run_sql(
|
||||
self,
|
||||
sql: str,
|
||||
session: aiohttp.ClientSession,
|
||||
properties: Dict[str, Any] = {
|
||||
"source": os.getenv("WREN_IBIS_SOURCE"),
|
||||
"manifest": os.getenv("WREN_IBIS_MANIFEST"),
|
||||
"connection_info": orjson.loads(
|
||||
base64.b64decode(os.getenv("WREN_IBIS_CONNECTION_INFO"))
|
||||
)
|
||||
if os.getenv("WREN_IBIS_CONNECTION_INFO")
|
||||
else {},
|
||||
},
|
||||
) -> Tuple[bool, Optional[Dict[str, Any]]]:
|
||||
async with session.post(
|
||||
f"{self._endpoint}/v2/connector/{properties.get('source', '')}/query?dryRun=true",
|
||||
f"{self._endpoint}/v2/connector/{self._source}/query?dryRun=true",
|
||||
json={
|
||||
"sql": remove_limit_statement(add_quotes(sql)),
|
||||
"manifestStr": properties.get("manifest", ""),
|
||||
"connectionInfo": properties.get("connection_info", {}),
|
||||
"manifestStr": self._manifest,
|
||||
"connectionInfo": self._connection_info,
|
||||
},
|
||||
) as response:
|
||||
if response.status == 204:
|
||||
@@ -74,3 +71,23 @@ class WrenIbis(Engine):
|
||||
res = await response.text()
|
||||
|
||||
return False, res
|
||||
|
||||
|
||||
@provider("wren_engine")
|
||||
class WrenEngine(Engine):
|
||||
def __init__(self, endpoint: str = os.getenv("WREN_ENGINE_ENDPOINT")):
|
||||
self._endpoint = endpoint
|
||||
|
||||
async def dry_run_sql(
|
||||
self,
|
||||
sql: str,
|
||||
session: aiohttp.ClientSession,
|
||||
) -> Tuple[bool, Optional[Dict[str, Any]]]:
|
||||
async with session.get(
|
||||
f"{self._endpoint}/v1/mdl/dry-run",
|
||||
json={"sql": remove_limit_statement(add_quotes(sql)), "limit": 1},
|
||||
) as response:
|
||||
if response.status == 200:
|
||||
return True, None
|
||||
res = await response.text()
|
||||
return False, res
|
||||
|
||||
@@ -3,7 +3,7 @@ from src.providers import loader
|
||||
|
||||
def test_import_mods():
|
||||
loader.import_mods("src.providers")
|
||||
assert len(loader.PROVIDERS) == 9
|
||||
assert len(loader.PROVIDERS) == 10
|
||||
|
||||
|
||||
def test_get_provider():
|
||||
@@ -39,3 +39,6 @@ def test_get_provider():
|
||||
|
||||
provider = loader.get_provider("wren_ibis")
|
||||
assert provider.__name__ == "WrenIbis"
|
||||
|
||||
provider = loader.get_provider("wren_engine")
|
||||
assert provider.__name__ == "WrenEngine"
|
||||
|
||||
@@ -28,6 +28,7 @@ services:
|
||||
- ${IBIS_SERVER_PORT}:${IBIS_SERVER_PORT}
|
||||
environment:
|
||||
WREN_ENGINE_ENDPOINT: http://engine:${WREN_ENGINE_PORT}
|
||||
LOG_LEVEL: DEBUG
|
||||
networks:
|
||||
- wren
|
||||
|
||||
|
||||
Reference in New Issue
Block a user