File size: 2,795 Bytes
0861ec7 fad1ac4 0861ec7 6153fbc 0861ec7 820aa6d 0861ec7 820aa6d 0861ec7 820aa6d 0861ec7 820aa6d 0861ec7 820aa6d 0861ec7 820aa6d 2f9d235 820aa6d 0861ec7 820aa6d 6153fbc 820aa6d 4121aea 820aa6d fad1ac4 820aa6d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 |
import faiss
import numpy as np
from fastapi import FastAPI, Query
from fastapi.responses import JSONResponse
from datasets import load_dataset
from sentence_transformers import SentenceTransformer
from typing import List, Dict
app = FastAPI()
FIELDS = (
"full_name",
"description",
"default_branch",
"open_issues",
"stargazers_count",
"forks_count",
"watchers_count",
"license",
"size",
"fork",
"updated_at",
"has_build_zig",
"has_build_zig_zon",
"created_at",
)
model = SentenceTransformer("all-MiniLM-L6-v2")
def load_dataset_with_fields(name, include_readme=False):
dataset = load_dataset(name)["train"]
repo_texts = [
" ".join(str(x.get(field, "")) for field in FIELDS) +
(" " + x.get("readme_content", "") if include_readme else "") +
" " + " ".join(x.get("topics", []))
for x in dataset
]
if not include_readme:
dataset = [{k: v for k, v in item.items() if k != "readme_content"} for item in dataset]
return dataset, repo_texts
datasets = {
"packages": load_dataset_with_fields("zigistry/packages", include_readme=True),
"programs": load_dataset_with_fields("zigistry/programs", include_readme=True),
}
indices = {}
for key, (dataset, repo_texts) in datasets.items():
repo_embeddings = model.encode(repo_texts)
index = faiss.IndexFlatL2(repo_embeddings.shape[1])
index.add(np.array(repo_embeddings))
indices[key] = (index, dataset)
def filter_results_by_distance(distances, idxs, dataset, threshold_ratio=0.3):
if len(distances) == 0:
return []
min_distance = np.min(distances)
max_distance = np.max(distances)
threshold = min_distance + ((max_distance - min_distance) * threshold_ratio)
results = [
dataset[int(i)]
for d, i in zip(distances, idxs)
if d <= threshold
]
return results
@app.get("/searchPackages/")
def search_packages(q: str):
key = "packages"
index, dataset = indices[key]
query_embedding = model.encode([q])
distances, idxs = index.search(np.array(query_embedding), len(dataset))
results = filter_results_by_distance(distances[0], idxs[0], dataset)
headers = {"Access-Control-Allow-Origin": "*", "Content-Type": "application/json"}
return JSONResponse(content=results, headers=headers)
@app.get("/searchPrograms/")
def search_programs(q: str):
key = "programs"
index, dataset = indices[key]
query_embedding = model.encode([q])
distances, idxs = index.search(np.array(query_embedding), len(dataset))
results = filter_results_by_distance(distances[0], idxs[0], dataset)
headers = {"Access-Control-Allow-Origin": "*", "Content-Type": "application/json"}
return JSONResponse(content=results, headers=headers)
|