symbolicai 0.17.5__py3-none-any.whl → 0.17.6__py3-none-any.whl

symai/__init__.py

@@ -33,7 +33,7 @@ os.environ['TOKENIZERS_PARALLELISM'] = "false"
 # Create singleton instance
 config_manager = settings.SymAIConfig()
 
-SYMAI_VERSION = "0.17.5"
+SYMAI_VERSION = "0.17.6"
 __version__   = SYMAI_VERSION
 __root_dir__  = config_manager.config_dir
 

symai/backend/engines/search/engine_openai.py

@@ -1,14 +1,18 @@
+import hashlib
 import json
 import logging
-import requests
+import re
 from copy import deepcopy
 from dataclasses import dataclass
+from urllib.parse import parse_qsl, urlencode, urlsplit, urlunsplit
+
+from openai import OpenAI
 
 from ....symbol import Result
 from ....utils import CustomUserWarning
 from ...base import Engine
-from ...settings import SYMAI_CONFIG
 from ...mixin import OPENAI_CHAT_MODELS, OPENAI_REASONING_MODELS
+from ...settings import SYMAI_CONFIG
 
 logging.getLogger("requests").setLevel(logging.ERROR)
 logging.getLogger("urllib3").setLevel(logging.ERROR)
@@ -16,6 +20,10 @@ logging.getLogger("httpx").setLevel(logging.ERROR)
 logging.getLogger("httpcore").setLevel(logging.ERROR)
 
 
+TRACKING_KEYS = {
+    "utm_source" # so far I've only seen this one
+}
+
 @dataclass
 class Citation:
     id: str
@@ -34,32 +42,111 @@ class SearchResult(Result):
         if value.get('error'):
             CustomUserWarning(value['error'], raise_with=ValueError)
         try:
-            for output in value.get('output', []):
-                if output.get('type') == 'message' and output.get('content'):
-                    annotations = output['content'][0].get('annotations', [])
-                    citations = []
-                    for n, annotation in enumerate(annotations):
-                        if annotation.get('type') == 'url_citation':
-                            citation = Citation(
-                                id=f'[{n + 1}]',
-                                start=annotation.get('start_index'),
-                                end=annotation.get('end_index'),
-                                title=annotation.get('title', ''),
-                                url=annotation.get('url', ''),
-                            )
-                            if citation not in citations:
-                                citations.append(citation)
-            self._value = output['content'][0]['text']
-            delta = 0
-            for citation in citations:
-                self._value = self._value[:citation.start - delta] + citation.id + self._value[citation.end - delta:]
-                delta += (citation.end - citation.start) - len(citation.id)
-            self._citations = citations
+            text, annotations = self._extract_text_and_annotations(value)
+            if text is None:
+                self._value = None
+                self._citations = []
+                return
+            replaced_text, ordered = self._replace_links_with_citations(text, annotations, id_mode="sequential")
+            self._value = replaced_text
+            self._citations = [
+                Citation(id=cid, title=title, url=url, start=0, end=0)
+                for cid, title, url in ordered
+            ]
 
         except Exception as e:
             self._value = None
             CustomUserWarning(f"Failed to parse response: {e}", raise_with=ValueError)
 
+    def _extract_text(self, value) -> str | None:
+        text = None
+        for output in value.get('output', []):
+            if output.get('type') == 'message' and output.get('content'):
+                content0 = output['content'][0]
+                if 'text' in content0 and content0['text']:
+                    text = content0['text']
+        return text
+
+    def _extract_text_and_annotations(self, value):
+        text = None
+        annotations = []
+        for output in value.get('output', []):
+            if output.get('type') != 'message' or not output.get('content'):
+                continue
+            for content in output.get('content', []) or []:
+                if 'text' in content and content['text']:
+                    text = content['text']
+                anns = content.get('annotations', []) or []
+                for ann in anns:
+                    if ann.get('type') == 'url_citation':
+                        annotations.append(ann)
+        return text, annotations
+
+    def _normalize_url(self, u: str) -> str:
+        parts = urlsplit(u)
+        scheme = parts.scheme.lower()
+        netloc = parts.netloc.lower()
+        path = parts.path.rstrip('/') or '/'
+        q = []
+        for k, v in parse_qsl(parts.query, keep_blank_values=True):
+            kl = k.lower()
+            if kl in TRACKING_KEYS or kl.startswith('utm_'):
+                continue
+            q.append((k, v))
+        query = urlencode(q, doseq=True)
+        fragment = ''
+        return urlunsplit((scheme, netloc, path, query, fragment))
+
+    def _make_title_map(self, annotations):
+        m = {}
+        for a in annotations or []:
+            url = a.get('url')
+            if not url:
+                continue
+            nu = self._normalize_url(url)
+            title = (a.get('title') or '').strip()
+            if nu not in m and title:
+                m[nu] = title
+        return m
+
+    def _hostname(self, u: str) -> str:
+        return urlsplit(u).netloc
+
+    def _short_hash_id(self, nu: str, length=6) -> str:
+        return hashlib.sha1(nu.encode('utf-8')).hexdigest()[:length]
+
+    def _replace_links_with_citations(self, text: str, annotations, id_mode: str = 'sequential'):
+        title_map = self._make_title_map(annotations)
+        id_map = {}
+        ordered = []  # list of ("[n]", title, normalized_url)
+        next_id = 1
+
+        pattern = re.compile(r"\[([^\]]*?)\]\((https?://[^\s)]+)\)")
+
+        def _get_id(nu: str) -> str:
+            nonlocal next_id
+            if id_mode == 'hash':
+                return self._short_hash_id(nu)
+            if nu not in id_map:
+                id_map[nu] = str(next_id)
+                t = title_map.get(nu) or self._hostname(nu)
+                ordered.append((f"[{id_map[nu]}]", t, nu))
+                next_id += 1
+            return id_map[nu]
+
+        def _repl(m):
+            link_text, url = m.group(1), m.group(2)
+            nu = self._normalize_url(url)
+            cid = _get_id(nu)
+            title = title_map.get(nu)
+            if not title:
+                lt = (link_text or '').strip()
+                title = lt if (' ' in lt) else self._hostname(nu)
+            return f"[{cid}] ({title})"
+
+        replaced = pattern.sub(_repl, text)
+        return replaced, ordered
+
     def __str__(self) -> str:
         try:
             return json.dumps(self.raw, indent=2)
@@ -86,6 +173,10 @@ class GPTXSearchEngine(Engine):
         self.api_key = self.config.get('SEARCH_ENGINE_API_KEY')
         self.model = self.config.get('SEARCH_ENGINE_MODEL', 'gpt-4.1') # Default to gpt-4.1 as per docs
         self.name = self.__class__.__name__
+        try:
+            self.client = OpenAI(api_key=self.api_key)
+        except Exception as e:
+            CustomUserWarning(f"Failed to initialize OpenAI client: {e}", raise_with=ValueError)
 
     def id(self) -> str:
         if self.config.get('SEARCH_ENGINE_API_KEY') and \
@@ -117,19 +208,12 @@ class GPTXSearchEngine(Engine):
             "model": self.model,
             "input": messages,
             "tools": [tool_definition],
-            "tool_choice": {"type": "web_search_preview"} # force the use of web search tool
-        }
-
-        headers = {
-            "Authorization": f"Bearer {self.api_key}",
-            "Content-Type": "application/json",
-            "OpenAI-Beta": "assistants=v1" # Required for some beta features, might be useful
+            "tool_choice": {"type": "web_search_preview"} if self.model not in OPENAI_REASONING_MODELS else "auto" # force the use of web search tool for non-reasoning models
         }
-        api_url = "https://api.openai.com/v1/responses"
 
         try:
-            res = requests.post(api_url, json=payload, headers=headers)
-            res = SearchResult(res.json())
+            res = self.client.responses.create(**payload)
+            res = SearchResult(res.dict())
         except Exception as e:
             CustomUserWarning(f"Failed to make request: {e}", raise_with=ValueError)
 

{symbolicai-0.17.5.dist-info → symbolicai-0.17.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: symbolicai
-Version: 0.17.5
+Version: 0.17.6
 Summary: A Neurosymbolic Perspective on Large Language Models
 Author-email: Marius-Constantin Dinu <marius@extensity.ai>, Leoveanu-Condrei Claudiu <leo@extensity.ai>
 Project-URL: Homepage, https://extensity.ai

{symbolicai-0.17.5.dist-info → symbolicai-0.17.6.dist-info}/RECORD

@@ -1,5 +1,5 @@
 symai/TERMS_OF_SERVICE.md,sha256=HN42UXVI_wAVDHjMShzy_k7xAsbjXaATNeMKcIte_eg,91409
-symai/__init__.py,sha256=q4Lept252Iy6bETSCL9-LMHKU9NrPT8qJMSbsWwdwVQ,16464
+symai/__init__.py,sha256=bL2mJzfktI9IqkdePuW2tDxOFfDNn22bdqM01brcGus,16464
 symai/chat.py,sha256=vqEe7NqSWdzr9ixkko_094SR1LIbgPLcZxQ8W7782N4,12775
 symai/components.py,sha256=L_Kbuyc0JW6c8zkVRd406HzPifLM3ZytRVas6EHE7Ls,50617
 symai/constraints.py,sha256=S1ywLB8nFQy4-beDoJz6IvLTiZHGR8Fu5RNTY4v5zG0,1641
@@ -55,7 +55,7 @@ symai/backend/engines/neurosymbolic/engine_openai_gptX_completion.py,sha256=YgxR
 symai/backend/engines/neurosymbolic/engine_openai_gptX_reasoning.py,sha256=QVbyZybUPSAQHiA66V6we2W2dAsk52g1kJ7kMdGqb9I,22951
 symai/backend/engines/ocr/engine_apilayer.py,sha256=hZo4lk0ECRIzaGEpmCSNjR5Xrh8mwkKMD2ddpdgioVU,2399
 symai/backend/engines/output/engine_stdout.py,sha256=2hhyhMHFJTfjVRaODYd_5XPnV9pT03URcpYbeMY_USU,951
-symai/backend/engines/search/engine_openai.py,sha256=4q71QMsYUOw--2dz5gE-uu6TewO6fDd-KF5tz9PZnaQ,5779
+symai/backend/engines/search/engine_openai.py,sha256=zARzTr0qO7p8o1TCS441KNIgtZR9-mjdjyICO2ajtVw,8492
 symai/backend/engines/search/engine_perplexity.py,sha256=yxuhGaA38d1FRbLv6piLll0QDxCCyBVK6eeomjYNryM,4157
 symai/backend/engines/search/engine_serpapi.py,sha256=UqvGHs1J9BOv05C0FJUQjbz29_VuWncIkeDwlRPUilU,3698
 symai/backend/engines/speech_to_text/engine_local_whisper.py,sha256=LRsXliCpHDFPFaE-vPky3-DLkmYwmwe2mxfF0Brz4Wg,8220
@@ -152,8 +152,8 @@ symai/ops/primitives.py,sha256=EaB2Ekx9yGNDaQa3aKS5KpuEr5awAUbO3OcBbufI-l4,11072
 symai/server/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 symai/server/huggingface_server.py,sha256=UpSBflnQaenDjY1AAn5LUYeg5J4gJLWiMuC5DcoIV3E,8743
 symai/server/llama_cpp_server.py,sha256=qVCldTdcQhK2YCu7sDNSYziu1p2AQieqMFfY028-yOc,2049
-symbolicai-0.17.5.dist-info/METADATA,sha256=GcuEpuspOaef3uCFQ6ZQ63fyOwP9V0-he1v1AYYEV08,21327
-symbolicai-0.17.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-symbolicai-0.17.5.dist-info/entry_points.txt,sha256=JV5sdydIfUZdDF6QBEQHiZHod6XNPjCjpWQrXh7gTAw,261
-symbolicai-0.17.5.dist-info/top_level.txt,sha256=bOoIDfpDIvCQtQgXcwVKJvxAKwsxpxo2IL4z92rNJjw,6
-symbolicai-0.17.5.dist-info/RECORD,,
+symbolicai-0.17.6.dist-info/METADATA,sha256=UQTu70XQcvbzRzoeq8TBdbxbiUnRpG41JzVaR4XJ1j8,21327
+symbolicai-0.17.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+symbolicai-0.17.6.dist-info/entry_points.txt,sha256=JV5sdydIfUZdDF6QBEQHiZHod6XNPjCjpWQrXh7gTAw,261
+symbolicai-0.17.6.dist-info/top_level.txt,sha256=bOoIDfpDIvCQtQgXcwVKJvxAKwsxpxo2IL4z92rNJjw,6
+symbolicai-0.17.6.dist-info/RECORD,,