This commit is contained in:
Alex
2023-09-29 17:17:48 +01:00
parent 783e7f6939
commit 347cfe253f
9 changed files with 216 additions and 133 deletions

View File

@@ -14,7 +14,7 @@ from transformers import GPT2TokenizerFast
from application.core.settings import settings
from application.llm.openai import OpenAILLM, AzureOpenAILLM
from application.vectorstore.faiss import FaissStore
from application.vectorstore.vector_creator import VectorCreator
from application.error import bad_request
@@ -234,7 +234,7 @@ def stream():
vectorstore = get_vectorstore({"active_docs": data["active_docs"]})
else:
vectorstore = ""
docsearch = FaissStore(vectorstore, embeddings_key)
docsearch = VectorCreator.create_vectorstore(settings.VECTOR_STORE, vectorstore, embeddings_key)
return Response(
complete_stream(question, docsearch,
@@ -268,7 +268,7 @@ def api_answer():
vectorstore = get_vectorstore(data)
# loading the index and the store and the prompt template
# Note if you have used other embeddings than OpenAI, you need to change the embeddings
docsearch = FaissStore(vectorstore, embeddings_key)
docsearch = VectorCreator.create_vectorstore(settings.VECTOR_STORE, vectorstore, embeddings_key)
if is_azure_configured():
llm = AzureOpenAILLM(

View File

@@ -34,25 +34,26 @@ def upload_index_files():
if "name" not in request.form:
return {"status": "no name"}
job_name = secure_filename(request.form["name"])
if "file_faiss" not in request.files:
print("No file part")
return {"status": "no file"}
file_faiss = request.files["file_faiss"]
if file_faiss.filename == "":
return {"status": "no file name"}
if "file_pkl" not in request.files:
print("No file part")
return {"status": "no file"}
file_pkl = request.files["file_pkl"]
if file_pkl.filename == "":
return {"status": "no file name"}
# saves index files
save_dir = os.path.join(current_dir, "indexes", user, job_name)
if not os.path.exists(save_dir):
os.makedirs(save_dir)
file_faiss.save(os.path.join(save_dir, "index.faiss"))
file_pkl.save(os.path.join(save_dir, "index.pkl"))
if settings.VECTOR_STORE == "faiss":
if "file_faiss" not in request.files:
print("No file part")
return {"status": "no file"}
file_faiss = request.files["file_faiss"]
if file_faiss.filename == "":
return {"status": "no file name"}
if "file_pkl" not in request.files:
print("No file part")
return {"status": "no file"}
file_pkl = request.files["file_pkl"]
if file_pkl.filename == "":
return {"status": "no file name"}
# saves index files
if not os.path.exists(save_dir):
os.makedirs(save_dir)
file_faiss.save(os.path.join(save_dir, "index.faiss"))
file_pkl.save(os.path.join(save_dir, "index.pkl"))
# create entry in vectors_collection
vectors_collection.insert_one(
{

View File

@@ -11,6 +11,8 @@ from celery.result import AsyncResult
from application.api.user.tasks import ingest
from application.core.settings import settings
from application.vectorstore.vector_creator import VectorCreator
mongo = MongoClient(settings.MONGO_URI)
db = mongo["docsgpt"]
conversations_collection = db["conversations"]
@@ -90,10 +92,17 @@ def delete_old():
return {"status": "error"}
path_clean = "/".join(dirs)
vectors_collection.delete_one({"location": path})
try:
shutil.rmtree(path_clean)
except FileNotFoundError:
pass
if settings.VECTOR_STORE == "faiss":
try:
shutil.rmtree(os.path.join(current_dir, path_clean))
except FileNotFoundError:
pass
else:
vetorstore = VectorCreator.create_vectorstore(
settings.VECTOR_STORE, path=os.path.join(current_dir, path_clean)
)
vetorstore.delete_index()
return {"status": "ok"}
@user.route("/api/upload", methods=["POST"])
@@ -173,11 +182,11 @@ def combined_json():
"location": "local",
}
)
data_remote = requests.get("https://d3dg1063dc54p9.cloudfront.net/combined.json").json()
for index in data_remote:
index["location"] = "remote"
data.append(index)
if settings.VECTOR_STORE == "faiss":
data_remote = requests.get("https://d3dg1063dc54p9.cloudfront.net/combined.json").json()
for index in data_remote:
index["location"] = "remote"
data.append(index)
return jsonify(data)