Spaces:
Running
Running
File size: 6,612 Bytes
81e42f7 |
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 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 |
import requests
import logging
import ftfy
import sys
from langchain_community.document_loaders import (
AzureAIDocumentIntelligenceLoader,
BSHTMLLoader,
CSVLoader,
Docx2txtLoader,
OutlookMessageLoader,
PyPDFLoader,
TextLoader,
UnstructuredEPubLoader,
UnstructuredExcelLoader,
UnstructuredMarkdownLoader,
UnstructuredPowerPointLoader,
UnstructuredRSTLoader,
UnstructuredXMLLoader,
YoutubeLoader,
)
from langchain_core.documents import Document
from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
log = logging.getLogger(__name__)
log.setLevel(SRC_LOG_LEVELS["RAG"])
known_source_ext = [
"go",
"py",
"java",
"sh",
"bat",
"ps1",
"cmd",
"js",
"ts",
"css",
"cpp",
"hpp",
"h",
"c",
"cs",
"sql",
"log",
"ini",
"pl",
"pm",
"r",
"dart",
"dockerfile",
"env",
"php",
"hs",
"hsc",
"lua",
"nginxconf",
"conf",
"m",
"mm",
"plsql",
"perl",
"rb",
"rs",
"db2",
"scala",
"bash",
"swift",
"vue",
"svelte",
"msg",
"ex",
"exs",
"erl",
"tsx",
"jsx",
"hs",
"lhs",
"json",
]
class TikaLoader:
def __init__(self, url, file_path, mime_type=None):
self.url = url
self.file_path = file_path
self.mime_type = mime_type
def load(self) -> list[Document]:
with open(self.file_path, "rb") as f:
data = f.read()
if self.mime_type is not None:
headers = {"Content-Type": self.mime_type}
else:
headers = {}
endpoint = self.url
if not endpoint.endswith("/"):
endpoint += "/"
endpoint += "tika/text"
r = requests.put(endpoint, data=data, headers=headers)
if r.ok:
raw_metadata = r.json()
text = raw_metadata.get("X-TIKA:content", "<No text content found>")
if "Content-Type" in raw_metadata:
headers["Content-Type"] = raw_metadata["Content-Type"]
log.debug("Tika extracted text: %s", text)
return [Document(page_content=text, metadata=headers)]
else:
raise Exception(f"Error calling Tika: {r.reason}")
class Loader:
def __init__(self, engine: str = "", **kwargs):
self.engine = engine
self.kwargs = kwargs
def load(
self, filename: str, file_content_type: str, file_path: str
) -> list[Document]:
loader = self._get_loader(filename, file_content_type, file_path)
docs = loader.load()
return [
Document(
page_content=ftfy.fix_text(doc.page_content), metadata=doc.metadata
)
for doc in docs
]
def _get_loader(self, filename: str, file_content_type: str, file_path: str):
file_ext = filename.split(".")[-1].lower()
if self.engine == "tika" and self.kwargs.get("TIKA_SERVER_URL"):
if file_ext in known_source_ext or (
file_content_type and file_content_type.find("text/") >= 0
):
loader = TextLoader(file_path, autodetect_encoding=True)
else:
loader = TikaLoader(
url=self.kwargs.get("TIKA_SERVER_URL"),
file_path=file_path,
mime_type=file_content_type,
)
elif (
self.engine == "document_intelligence"
and self.kwargs.get("DOCUMENT_INTELLIGENCE_ENDPOINT") != ""
and self.kwargs.get("DOCUMENT_INTELLIGENCE_KEY") != ""
and (
file_ext in ["pdf", "xls", "xlsx", "docx", "ppt", "pptx"]
or file_content_type
in [
"application/vnd.ms-excel",
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
"application/vnd.openxmlformats-officedocument.wordprocessingml.document",
"application/vnd.ms-powerpoint",
"application/vnd.openxmlformats-officedocument.presentationml.presentation",
]
)
):
loader = AzureAIDocumentIntelligenceLoader(
file_path=file_path,
api_endpoint=self.kwargs.get("DOCUMENT_INTELLIGENCE_ENDPOINT"),
api_key=self.kwargs.get("DOCUMENT_INTELLIGENCE_KEY"),
)
else:
if file_ext == "pdf":
loader = PyPDFLoader(
file_path, extract_images=self.kwargs.get("PDF_EXTRACT_IMAGES")
)
elif file_ext == "csv":
loader = CSVLoader(file_path)
elif file_ext == "rst":
loader = UnstructuredRSTLoader(file_path, mode="elements")
elif file_ext == "xml":
loader = UnstructuredXMLLoader(file_path)
elif file_ext in ["htm", "html"]:
loader = BSHTMLLoader(file_path, open_encoding="unicode_escape")
elif file_ext == "md":
loader = TextLoader(file_path, autodetect_encoding=True)
elif file_content_type == "application/epub+zip":
loader = UnstructuredEPubLoader(file_path)
elif (
file_content_type
== "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
or file_ext == "docx"
):
loader = Docx2txtLoader(file_path)
elif file_content_type in [
"application/vnd.ms-excel",
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
] or file_ext in ["xls", "xlsx"]:
loader = UnstructuredExcelLoader(file_path)
elif file_content_type in [
"application/vnd.ms-powerpoint",
"application/vnd.openxmlformats-officedocument.presentationml.presentation",
] or file_ext in ["ppt", "pptx"]:
loader = UnstructuredPowerPointLoader(file_path)
elif file_ext == "msg":
loader = OutlookMessageLoader(file_path)
elif file_ext in known_source_ext or (
file_content_type and file_content_type.find("text/") >= 0
):
loader = TextLoader(file_path, autodetect_encoding=True)
else:
loader = TextLoader(file_path, autodetect_encoding=True)
return loader
|