ivanwu/jarvis-models
1
0
Fork 0
mirror of https://github.com/BoardWare-Genius/jarvis-models.git synced 2025-12-13 16:53:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: update the parameter name

Browse Source
This commit is contained in:
tom
2025-08-18 17:21:55 +08:00
parent af62ccc2ea
commit 8358a265c8
1 changed files with 21 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
src/blackbox/chroma_upsert.py
View File

@ -43,25 +43,7 @@ class ChromaUpsert(Blackbox):
return isinstance(data, list) return isinstance(data, list)
# @logging_time(logger=logger) # @logging_time(logger=logger)
def processing(self, file, string, context: list, settings: dict) -> str: def processing(self, file, text, text_ids, settings: dict) -> str:
# 用户的操作历史
if context is None:
context = []
# context = [
# {
# "collection_id": "123",
# "action": "query",
# "content": "你吃饭了吗",
# "answer": "吃了",
# },
# {
# "collection_id": "123",
# "action": "upsert",
# "content": "file_name or string",
# "answer": "collection 123 has 12472 documents. /tmp/Cheap and Quick：Efficient Vision-Language Instruction Tuning for Large Language Models.pdf ids is 0~111",
# },
# ]
if settings is None: if settings is None:
settings = {} settings = {}
@ -101,7 +83,8 @@ class ChromaUpsert(Blackbox):
else: else:
embedding_model = SentenceTransformerEmbeddings(model_name=chroma_embedding_model, device = "cuda:0") embedding_model = SentenceTransformerEmbeddings(model_name=chroma_embedding_model, device = "cuda:0")
response_file =''
response_string = ''
if file is not None: if file is not None:
file_type = file.split(".")[-1] file_type = file.split(".")[-1]
print("file_type: ",file_type) print("file_type: ",file_type)
@ -129,35 +112,28 @@ class ChromaUpsert(Blackbox):
Chroma.from_documents(documents=docs, embedding=embedding_model, ids=ids, collection_name=chroma_collection_id, client=client) Chroma.from_documents(documents=docs, embedding=embedding_model, ids=ids, collection_name=chroma_collection_id, client=client)
collection_number = client.get_collection(chroma_collection_id).count() response_file = f"\n{file} ids is 0~{len(docs)-1}"
response_file = f"collection {chroma_collection_id} has {collection_number} documents. {file} ids is 0~{len(docs)-1}"
if string is not None: if text is not None and text_ids is not None:
# 生成一个新的id ids_string: 1 Chroma.from_texts(texts=[text], embedding=embedding_model, ids=[text_ids], collection_name=chroma_collection_id, client=client)
# ids = setting.ChromaSetting.string_ids[0] + 1
ids = "1"
Chroma.from_texts(texts=[string], embedding=embedding_model, ids=[ids], collection_name=chroma_collection_id, client=client) response_string = f"\n{text} ids is {ids}"
collection_number = client.get_collection(chroma_collection_id).count() vector_count = client.get_collection(chroma_collection_id).count()
response_string = f"collection {chroma_collection_id} has {collection_number} documents. {string} ids is {ids}" response_documents_num = f"collection {chroma_collection_id} has {vector_count} vectors."
print(client.get_collection(chroma_collection_id).get())
if file is not None and string is not None:
return response_file + " \n and " + response_string return response_documents_num + response_file + response_string
elif file is not None and string is None:
return response_file
elif file is None and string is not None:
return response_string
async def fast_api_handler(self, request: Request) -> Response: async def fast_api_handler(self, request: Request) -> Response:
user_file = (await request.form()).get("file") user_file = (await request.form()).get("file")
user_string = (await request.form()).get("string") user_text = (await request.form()).get("text")
context = (await request.form()).get("context") user_text_ids = (await request.form()).get("text_ids")
setting: dict = (await request.form()).get("settings") setting: dict = (await request.form()).get("settings")
if isinstance(setting, str): if isinstance(setting, str):
@ -166,8 +142,11 @@ class ChromaUpsert(Blackbox):
except json.JSONDecodeError: except json.JSONDecodeError:
return JSONResponse(content={"error": "Invalid settings format"}, status_code=status.HTTP_400_BAD_REQUEST) return JSONResponse(content={"error": "Invalid settings format"}, status_code=status.HTTP_400_BAD_REQUEST)
if user_file is None and user_string is None: if user_file is None and user_text is None:
return JSONResponse(content={"error": "file or string is required"}, status_code=status.HTTP_400_BAD_REQUEST) return JSONResponse(content={"error": "file or text is required"}, status_code=status.HTTP_400_BAD_REQUEST)
if user_text is not None and user_text_ids is None:
return JSONResponse(content={"error": "text_ids is required when text is provided"}, status_code=status.HTTP_400_BAD_REQUEST)
if user_file is not None: if user_file is not None:
pdf_bytes = await user_file.read() pdf_bytes = await user_file.read()
@ -182,7 +161,7 @@ class ChromaUpsert(Blackbox):
safe_filename = None safe_filename = None
try: try:
txt = self.processing(safe_filename, user_string, context, setting) txt = self.processing(safe_filename, user_text, user_text_ids, setting)
print(txt) print(txt)
except ValueError as e: except ValueError as e:
return JSONResponse(content={"error": str(e)}, status_code=status.HTTP_400_BAD_REQUEST) return JSONResponse(content={"error": str(e)}, status_code=status.HTTP_400_BAD_REQUEST)