55and searchable alongside structured graph data.
66"""
77
8- from dataclasses import dataclass , field
8+ from http import HTTPStatus
99from pathlib import Path
1010from typing import Any , Dict , List , Optional
1111
12- import httpx
13- import logging
14-
15- logger = logging .getLogger (__name__ )
16-
17-
18- @dataclass
19- class DocumentUploadResult :
20- """Result from document upload."""
21-
22- document_id : str
23- sections_indexed : int
24- total_content_length : int
25- section_ids : List [str ]
26- success : bool = True
27- error : Optional [str ] = None
28-
29-
30- @dataclass
31- class DocumentSearchHit :
32- """A single search result."""
33-
34- document_id : str
35- score : float
36- source_type : str
37- snippet : str
38- section_label : Optional [str ] = None
39- document_title : Optional [str ] = None
40- entity_ticker : Optional [str ] = None
41- form_type : Optional [str ] = None
42- filing_date : Optional [str ] = None
43- tags : Optional [List [str ]] = None
44- folder : Optional [str ] = None
45-
46-
47- @dataclass
48- class DocumentSearchResult :
49- """Result from document search."""
50-
51- total : int
52- hits : List [DocumentSearchHit ]
53- query : str
54- graph_id : str
55-
56-
57- @dataclass
58- class DocumentInfo :
59- """Information about an indexed document."""
60-
61- document_title : str
62- section_count : int
63- source_type : str
64- folder : Optional [str ] = None
65- tags : Optional [List [str ]] = None
66- last_indexed : Optional [str ] = None
67-
68-
69- @dataclass
70- class DocumentListResult :
71- """Result from listing documents."""
72-
73- total : int
74- documents : List [DocumentInfo ]
75- graph_id : str
12+ from ..api .documents .delete_document import sync_detailed as delete_document
13+ from ..api .documents .list_documents import sync_detailed as list_documents
14+ from ..api .documents .upload_document import sync_detailed as upload_document
15+ from ..api .search .get_document_section import sync_detailed as get_document_section
16+ from ..api .search .search_documents import sync_detailed as search_documents
17+ from ..client import AuthenticatedClient
18+ from ..models .document_list_response import DocumentListResponse
19+ from ..models .document_section import DocumentSection
20+ from ..models .document_upload_request import DocumentUploadRequest
21+ from ..models .document_upload_response import DocumentUploadResponse
22+ from ..models .search_request import SearchRequest
23+ from ..models .search_response import SearchResponse
24+ from ..types import UNSET
7625
7726
7827class DocumentClient :
@@ -82,18 +31,20 @@ def __init__(self, config: Dict[str, Any]):
8231 self .config = config
8332 self .base_url = config ["base_url" ]
8433 self .headers = config .get ("headers" , {})
34+ self .token = config .get ("token" )
8535 self .timeout = config .get ("timeout" , 60 )
86- self ._http_client = httpx .Client (
87- timeout = self .timeout ,
36+
37+ def _get_client (self ) -> AuthenticatedClient :
38+ if not self .token :
39+ raise Exception ("No API key provided. Set X-API-Key in headers." )
40+ return AuthenticatedClient (
41+ base_url = self .base_url ,
42+ token = self .token ,
43+ prefix = "" ,
44+ auth_header_name = "X-API-Key" ,
8845 headers = self .headers ,
8946 )
9047
91- def _url (self , graph_id : str , path : str = "" ) -> str :
92- return f"{ self .base_url } /v1/graphs/{ graph_id } /documents{ path } "
93-
94- def _search_url (self , graph_id : str , path : str = "" ) -> str :
95- return f"{ self .base_url } /v1/graphs/{ graph_id } /search{ path } "
96-
9748 def upload (
9849 self ,
9950 graph_id : str ,
@@ -102,7 +53,7 @@ def upload(
10253 tags : Optional [List [str ]] = None ,
10354 folder : Optional [str ] = None ,
10455 external_id : Optional [str ] = None ,
105- ) -> DocumentUploadResult :
56+ ) -> DocumentUploadResponse :
10657 """Upload a markdown document for text indexing.
10758
10859 The document is sectioned on headings, embedded, and indexed
@@ -117,40 +68,23 @@ def upload(
11768 external_id: Optional external ID for upsert behavior.
11869
11970 Returns:
120- DocumentUploadResult with section IDs and counts.
71+ DocumentUploadResponse with section IDs and counts.
12172 """
122- payload : Dict [str , Any ] = {"title" : title , "content" : content }
123- if tags is not None :
124- payload ["tags" ] = tags
125- if folder is not None :
126- payload ["folder" ] = folder
127- if external_id is not None :
128- payload ["external_id" ] = external_id
129-
130- response = self ._http_client .post (self ._url (graph_id ), json = payload )
131-
132- if response .status_code == 200 :
133- data = response .json ()
134- return DocumentUploadResult (
135- document_id = data ["document_id" ],
136- sections_indexed = data ["sections_indexed" ],
137- total_content_length = data ["total_content_length" ],
138- section_ids = data ["section_ids" ],
139- )
140- else :
141- error_detail = response .text
142- try :
143- error_detail = response .json ().get ("detail" , response .text )
144- except Exception :
145- pass
146- return DocumentUploadResult (
147- document_id = "" ,
148- sections_indexed = 0 ,
149- total_content_length = 0 ,
150- section_ids = [],
151- success = False ,
152- error = f"{ response .status_code } : { error_detail } " ,
73+ body = DocumentUploadRequest (
74+ title = title ,
75+ content = content ,
76+ tags = tags if tags is not None else UNSET ,
77+ folder = folder if folder is not None else UNSET ,
78+ external_id = external_id if external_id is not None else UNSET ,
79+ )
80+
81+ client = self ._get_client ()
82+ response = upload_document (graph_id = graph_id , client = client , body = body )
83+ if response .status_code != HTTPStatus .OK :
84+ raise Exception (
85+ f"Document upload failed ({ response .status_code } ): { response .content .decode ()} "
15386 )
87+ return response .parsed
15488
15589 def upload_file (
15690 self ,
@@ -160,7 +94,7 @@ def upload_file(
16094 tags : Optional [List [str ]] = None ,
16195 folder : Optional [str ] = None ,
16296 external_id : Optional [str ] = None ,
163- ) -> DocumentUploadResult :
97+ ) -> DocumentUploadResponse :
16498 """Upload a markdown file by path.
16599
166100 Reads the file, optionally extracts title from filename,
@@ -178,7 +112,6 @@ def upload_file(
178112 content = path .read_text ()
179113
180114 if title is None :
181- # Try frontmatter title, fall back to filename
182115 title = path .stem .replace ("-" , " " ).replace ("_" , " " ).title ()
183116
184117 return self .upload (
@@ -196,7 +129,7 @@ def upload_directory(
196129 directory : str | Path ,
197130 pattern : str = "*.md" ,
198131 folder : Optional [str ] = None ,
199- ) -> List [DocumentUploadResult ]:
132+ ) -> List [DocumentUploadResponse ]:
200133 """Upload all markdown files from a directory.
201134
202135 Args:
@@ -231,7 +164,7 @@ def search(
231164 section : Optional [str ] = None ,
232165 semantic : bool = False ,
233166 size : int = 10 ,
234- ) -> DocumentSearchResult :
167+ ) -> SearchResponse :
235168 """Search documents with full-text or semantic search.
236169
237170 Args:
@@ -245,101 +178,71 @@ def search(
245178 size: Max results to return.
246179
247180 Returns:
248- DocumentSearchResult with ranked hits.
181+ SearchResponse with ranked hits.
249182 """
250- payload : Dict [str , Any ] = {"query" : query , "size" : size }
251- if source_type is not None :
252- payload ["source_type" ] = source_type
253- if entity is not None :
254- payload ["entity" ] = entity
255- if form_type is not None :
256- payload ["form_type" ] = form_type
257- if section is not None :
258- payload ["section" ] = section
259- if semantic :
260- payload ["semantic" ] = True
261-
262- response = self ._http_client .post (self ._search_url (graph_id ), json = payload )
263- response .raise_for_status ()
264- data = response .json ()
265-
266- hits = [
267- DocumentSearchHit (
268- document_id = h ["document_id" ],
269- score = h ["score" ],
270- source_type = h ["source_type" ],
271- snippet = h ["snippet" ],
272- section_label = h .get ("section_label" ),
273- document_title = h .get ("document_title" ),
274- entity_ticker = h .get ("entity_ticker" ),
275- form_type = h .get ("form_type" ),
276- filing_date = h .get ("filing_date" ),
277- tags = h .get ("tags" ),
278- folder = h .get ("folder" ),
279- )
280- for h in data .get ("hits" , [])
281- ]
282-
283- return DocumentSearchResult (
284- total = data ["total" ],
285- hits = hits ,
286- query = data ["query" ],
287- graph_id = data ["graph_id" ],
183+ body = SearchRequest (
184+ query = query ,
185+ source_type = source_type if source_type is not None else UNSET ,
186+ entity = entity if entity is not None else UNSET ,
187+ form_type = form_type if form_type is not None else UNSET ,
188+ section = section if section is not None else UNSET ,
189+ semantic = semantic ,
190+ size = size ,
288191 )
289192
290- def get_section (self , graph_id : str , document_id : str ) -> Optional [Dict [str , Any ]]:
193+ client = self ._get_client ()
194+ response = search_documents (graph_id = graph_id , client = client , body = body )
195+ if response .status_code != HTTPStatus .OK :
196+ raise Exception (
197+ f"Document search failed ({ response .status_code } ): { response .content .decode ()} "
198+ )
199+ return response .parsed
200+
201+ def get_section (self , graph_id : str , document_id : str ) -> Optional [DocumentSection ]:
291202 """Retrieve the full text of a document section by ID.
292203
293204 Args:
294205 graph_id: Target graph ID.
295206 document_id: Document section ID.
296207
297208 Returns:
298- Dict with full section content and metadata, or None if not found.
209+ DocumentSection with full content and metadata, or None if not found.
299210 """
300- response = self ._http_client .get (self ._search_url (graph_id , f"/{ document_id } " ))
301- if response .status_code == 404 :
211+ client = self ._get_client ()
212+ response = get_document_section (
213+ graph_id = graph_id , document_id = document_id , client = client
214+ )
215+ if response .status_code == HTTPStatus .NOT_FOUND :
302216 return None
303- response .raise_for_status ()
304- return response .json ()
217+ if response .status_code != HTTPStatus .OK :
218+ raise Exception (
219+ f"Get section failed ({ response .status_code } ): { response .content .decode ()} "
220+ )
221+ return response .parsed
305222
306223 def list (
307224 self , graph_id : str , source_type : Optional [str ] = None
308- ) -> DocumentListResult :
225+ ) -> DocumentListResponse :
309226 """List indexed documents for a graph.
310227
311228 Args:
312229 graph_id: Target graph ID.
313230 source_type: Optional filter by source type.
314231
315232 Returns:
316- DocumentListResult with document inventory.
233+ DocumentListResponse with document inventory.
317234 """
318- params = {}
319- if source_type is not None :
320- params ["source_type" ] = source_type
321-
322- response = self ._http_client .get (self ._url (graph_id ), params = params )
323- response .raise_for_status ()
324- data = response .json ()
325-
326- documents = [
327- DocumentInfo (
328- document_title = d ["document_title" ],
329- section_count = d ["section_count" ],
330- source_type = d ["source_type" ],
331- folder = d .get ("folder" ),
332- tags = d .get ("tags" ),
333- last_indexed = d .get ("last_indexed" ),
334- )
335- for d in data .get ("documents" , [])
336- ]
337-
338- return DocumentListResult (
339- total = data ["total" ],
340- documents = documents ,
341- graph_id = data ["graph_id" ],
235+ client = self ._get_client ()
236+ response = list_documents (
237+ graph_id = graph_id ,
238+ client = client ,
239+ source_type = source_type if source_type is not None else UNSET ,
342240 )
241+ if response .status_code != HTTPStatus .OK :
242+ raise Exception (
243+ f"List documents failed ({ response .status_code } ): { response .content .decode ()} "
244+ )
245+ return response .parsed
343246
344247 def delete (self , graph_id : str , document_id : str ) -> bool :
345248 """Delete a document and all its sections.
@@ -351,14 +254,18 @@ def delete(self, graph_id: str, document_id: str) -> bool:
351254 Returns:
352255 True if deleted, False if not found.
353256 """
354- response = self ._http_client .delete (self ._url (graph_id , f"/{ document_id } " ))
355- if response .status_code == 204 :
257+ client = self ._get_client ()
258+ response = delete_document (
259+ graph_id = graph_id , document_id = document_id , client = client
260+ )
261+ if response .status_code == HTTPStatus .NO_CONTENT :
356262 return True
357- if response .status_code == 404 :
263+ if response .status_code == HTTPStatus . NOT_FOUND :
358264 return False
359- response .raise_for_status ()
360- return False
265+ raise Exception (
266+ f"Delete document failed ({ response .status_code } ): { response .content .decode ()} "
267+ )
361268
362269 def close (self ):
363- """Close the HTTP client."""
364- self . _http_client . close ()
270+ """Close the client (no-op, AuthenticatedClient is created per-call) ."""
271+ pass
0 commit comments