compair-core 0.3.15__py3-none-any.whl → 0.4.1__py3-none-any.whl

compair_core/api.py

@@ -2370,6 +2370,8 @@ def get_activity_feed(
 ):
     """Retrieve recent activities for a user's groups."""
     require_feature(HAS_ACTIVITY, "Activity feed")
+    if not IS_CLOUD:
+        raise HTTPException(status_code=501, detail="Activity feed is only available in the Compair Cloud edition.")
     with compair.Session() as session:
         # Get user's groups
         
@@ -3514,7 +3516,11 @@ CORE_PATHS: set[str] = {
     "/load_documents",
     "/load_document",
     "/load_document_by_id",
+    "/load_user_files",
     "/create_doc",
+    "/update_doc",
+    "/delete_doc",
+    "/delete_docs",
     "/process_doc",
     "/status/{task_id}",
     "/upload/ocr-file",
@@ -3523,6 +3529,7 @@ CORE_PATHS: set[str] = {
     "/load_references",
     "/load_feedback",
     "/documents/{document_id}/feedback",
+    "/get_activity_feed",
 }
 
 for route in router.routes:

compair_core/compair/__init__.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import os
+from pathlib import Path
 from sqlalchemy import Engine, create_engine
 from sqlalchemy.orm import sessionmaker
 
@@ -37,27 +38,51 @@ if edition == "cloud":
 
 
 def _handle_engine() -> Engine:
+    # Preferred configuration: explicit database URL
+    explicit_url = (
+        os.getenv("COMPAIR_DATABASE_URL")
+        or os.getenv("COMPAIR_DB_URL")
+        or os.getenv("DATABASE_URL")
+    )
+    if explicit_url:
+        if explicit_url.startswith("sqlite:"):
+            return create_engine(explicit_url, connect_args={"check_same_thread": False})
+        return create_engine(explicit_url)
+
+    # Backwards compatibility with legacy Postgres env variables
     db = os.getenv("DB")
     db_user = os.getenv("DB_USER")
     db_passw = os.getenv("DB_PASSW")
-    db_url = os.getenv("DB_URL")
+    db_host = os.getenv("DB_URL")
 
-    if all([db, db_user, db_passw, db_url]):
+    if all([db, db_user, db_passw, db_host]):
         return create_engine(
-            f"postgresql+psycopg2://{db_user}:{db_passw}@{db_url}/{db}",
+            f"postgresql+psycopg2://{db_user}:{db_passw}@{db_host}/{db}",
             pool_size=10,
             max_overflow=0,
         )
 
-    sqlite_dir = os.getenv("COMPAIR_SQLITE_DIR", "/data")
+    # Local default: place an SQLite database inside COMPAIR_DB_DIR
+    db_dir = (
+        os.getenv("COMPAIR_DB_DIR")
+        or os.getenv("COMPAIR_SQLITE_DIR")
+        or os.path.join(Path.home(), ".compair-core", "data")
+    )
+    db_name = os.getenv("COMPAIR_DB_NAME") or os.getenv("COMPAIR_SQLITE_NAME") or "compair.db"
+
+    db_path = Path(db_dir).expanduser()
     try:
-        os.makedirs(sqlite_dir, exist_ok=True)
+        db_path.mkdir(parents=True, exist_ok=True)
     except OSError:
-        fallback_dir = os.path.join(os.getcwd(), "compair_data")
-        os.makedirs(fallback_dir, exist_ok=True)
-        sqlite_dir = fallback_dir
-    sqlite_path = os.path.join(sqlite_dir, os.getenv("COMPAIR_SQLITE_NAME", "compair.db"))
-    return create_engine(f"sqlite:///{sqlite_path}", connect_args={"check_same_thread": False})
+        fallback_dir = Path(os.getcwd()) / "compair_data"
+        fallback_dir.mkdir(parents=True, exist_ok=True)
+        db_path = fallback_dir
+
+    sqlite_path = db_path / db_name
+    return create_engine(
+        f"sqlite:///{sqlite_path}",
+        connect_args={"check_same_thread": False},
+    )
 
 
 def initialize_database() -> None:

compair_core/compair/feedback.py

@@ -35,7 +35,8 @@ class Reviewer:
 
         self._cloud_impl = None
         self._openai_client = None
-        self.openai_model = os.getenv("COMPAIR_OPENAI_MODEL", "gpt-4o-mini")
+        self.openai_model = os.getenv("COMPAIR_OPENAI_MODEL", "gpt-5-nano")
+        self.custom_endpoint = os.getenv("COMPAIR_GENERATION_ENDPOINT")
 
         if self.edition == "cloud" and CloudReviewer is not None:
             self._cloud_impl = CloudReviewer()
@@ -55,6 +56,9 @@ class Reviewer:
                 if self._openai_client is None and not hasattr(openai, "ChatCompletion"):
                     log_event("openai_feedback_unavailable", reason="openai_library_missing")
                     self.provider = "fallback"
+            if self.provider == "http" and not self.custom_endpoint:
+                log_event("custom_feedback_unavailable", reason="missing_endpoint")
+                self.provider = "fallback"
             if self.provider == "local":
                 self.model = os.getenv("COMPAIR_LOCAL_GENERATION_MODEL", "local-feedback")
                 base_url = os.getenv("COMPAIR_LOCAL_MODEL_URL", "http://local-model:9000")
@@ -63,6 +67,9 @@ class Reviewer:
             else:
                 self.model = "external"
                 self.endpoint = None
+            if self.provider not in {"local", "openai", "http", "fallback"}:
+                log_event("feedback_provider_unknown", provider=self.provider)
+                self.provider = "fallback"
 
     @property
     def is_cloud(self) -> bool:
@@ -89,6 +96,33 @@ def _fallback_feedback(text: str, references: list[Any]) -> str:
     return f"Consider aligning with these reference passages: {joined}"
 
 
+
+def _local_reference_feedback(
+    reviewer: Reviewer,
+    references: list[Any],
+    user: User,
+) -> str | None:
+    if not references:
+        return None
+    summaries: list[str] = []
+    for ref in references[:3]:
+        doc = getattr(ref, "document", None)
+        title = getattr(doc, "title", None) or "a related document"
+        snippet = getattr(ref, "content", "") or getattr(ref, "text", "")
+        snippet = snippet.replace("\n", " ").strip()
+        if not snippet:
+            continue
+        summaries.append(f'"{title}" — {snippet[:200]}')
+    if not summaries:
+        return None
+    instruction = reviewer.length_map.get(user.preferred_feedback_length, "1–2 short sentences")
+    if len(summaries) == 1:
+        body = summaries[0]
+    else:
+        body = "; ".join(summaries)
+    return f"[local-feedback] {instruction}: Consider the guidance from {body}"
+
+
 def _openai_feedback(
     reviewer: Reviewer,
     doc: Document,
@@ -100,56 +134,92 @@ def _openai_feedback(
         return None
     instruction = reviewer.length_map.get(user.preferred_feedback_length, "1–2 short sentences")
     ref_text = "\n\n".join(_reference_snippets(references, limit=3))
-    messages = [
-        {
-            "role": "system",
-            "content": (
-                "You are Compair, an assistant that delivers concise, actionable feedback on a user's document. "
-                "Focus on clarity, cohesion, and usefulness."
-            ),
-        },
-        {
-            "role": "user",
-            "content": (
-                f"Document:\n{text}\n\nHelpful reference excerpts:\n{ref_text or 'None provided'}\n\n"
-                f"Respond with {instruction} that highlights the most valuable revision to make next."
-            ),
-        },
-    ]
+    system_prompt = (
+        "You are Compair, an assistant that delivers concise, actionable feedback on a user's document. "
+        "Focus on clarity, cohesion, and usefulness."
+    )
+    user_prompt = (
+        f"Document:\n{text}\n\nHelpful reference excerpts:\n{ref_text or 'None provided'}\n\n"
+        f"Respond with {instruction} that highlights the most valuable revision to make next."
+    )
+
+    def _extract_response_text(response: Any) -> str | None:
+        if response is None:
+            return None
+        text_out = getattr(response, "output_text", None)
+        if isinstance(text_out, str) and text_out.strip():
+            return text_out.strip()
+        outputs = getattr(response, "output", None) or getattr(response, "outputs", None)
+        pieces: list[str] = []
+        if outputs:
+            for item in outputs:
+                content_field = None
+                if isinstance(item, dict):
+                    content_field = item.get("content")
+                else:
+                    content_field = getattr(item, "content", None)
+                if not content_field:
+                    continue
+                for part in content_field:
+                    if isinstance(part, dict):
+                        val = part.get("text") or part.get("output_text")
+                        if val:
+                            pieces.append(str(val))
+                    elif part:
+                        pieces.append(str(part))
+        if pieces:
+            merged = "\n".join(pieces).strip()
+            return merged or None
+        return None
 
     try:
-        if reviewer._openai_client is not None and hasattr(reviewer._openai_client, "responses"):
-            response = reviewer._openai_client.responses.create(  # type: ignore[union-attr]
+        client = reviewer._openai_client
+        if client is None and hasattr(openai, "OpenAI"):
+            api_key = os.getenv("COMPAIR_OPENAI_API_KEY") or None
+            try:  # pragma: no cover - optional dependency differences
+                client = openai.OpenAI(api_key=api_key) if api_key else openai.OpenAI()
+            except TypeError:
+                client = openai.OpenAI()
+            reviewer._openai_client = client
+
+        content: str | None = None
+        if client is not None and hasattr(client, "responses"):
+            response = client.responses.create(
                 model=reviewer.openai_model,
-                input=messages,
+                instructions=system_prompt,
+                input=user_prompt,
                 max_output_tokens=256,
+                store=False,
+            )
+            content = _extract_response_text(response)
+        elif client is not None and hasattr(client, "chat") and hasattr(client.chat, "completions"):
+            response = client.chat.completions.create(
+                model=reviewer.openai_model,
+                messages=[{"role": "system", "content": system_prompt}, {"role": "user", "content": user_prompt}],
+                temperature=0.3,
+                max_tokens=256,
             )
-            content = getattr(response, "output_text", None)
-            if not content and hasattr(response, "outputs"):
-                # Legacy compatibility: join content parts
-                parts = []
-                for item in getattr(response, "outputs", []):
-                    parts.extend(getattr(item, "content", []))
-                content = " ".join(getattr(part, "text", "") for part in parts)
+            choices = getattr(response, "choices", None) or []
+            if choices:
+                message = getattr(choices[0], "message", None)
+                if message is not None:
+                    content = getattr(message, "content", None)
+                if not content:
+                    content = getattr(choices[0], "text", None)
+                if isinstance(content, str):
+                    content = content.strip()
         elif hasattr(openai, "ChatCompletion"):
             chat_response = openai.ChatCompletion.create(  # type: ignore[attr-defined]
                 model=reviewer.openai_model,
-                messages=messages,
+                messages=[{"role": "system", "content": system_prompt}, {"role": "user", "content": user_prompt}],
                 temperature=0.3,
                 max_tokens=256,
             )
-            content = (
-                chat_response["choices"][0]["message"]["content"].strip()  # type: ignore[index, assignment]
-            )
-        else:
-            content = None
+            content = chat_response["choices"][0]["message"]["content"].strip()  # type: ignore[index, assignment]
+        if content:
+            return content.strip()
     except Exception as exc:  # pragma: no cover - network/API failure
         log_event("openai_feedback_failed", error=str(exc))
-        content = None
-    if content:
-        content = content.strip()
-        if content:
-            return content
     return None
 
 
@@ -181,6 +251,36 @@ def _local_feedback(
     return None
 
 
+def _http_feedback(
+    reviewer: Reviewer,
+    text: str,
+    references: list[Any],
+    user: User,
+) -> str | None:
+    if not reviewer.custom_endpoint:
+        return None
+    payload = {
+        "document": text,
+        "references": [getattr(ref, "content", "") for ref in references],
+        "length_instruction": reviewer.length_map.get(
+            user.preferred_feedback_length,
+            "1–2 short sentences",
+        ),
+    }
+    try:
+        response = requests.post(reviewer.custom_endpoint, json=payload, timeout=30)
+        response.raise_for_status()
+        data = response.json()
+        feedback = data.get("feedback") or data.get("text")
+        if isinstance(feedback, str):
+            feedback = feedback.strip()
+        if feedback:
+            return feedback
+    except Exception as exc:  # pragma: no cover - network failures stay graceful
+        log_event("custom_feedback_failed", error=str(exc))
+    return None
+
+
 def get_feedback(
     reviewer: Reviewer,
     doc: Document,
@@ -196,9 +296,18 @@ def get_feedback(
         if feedback:
             return feedback
 
-    if reviewer.provider == "local" and getattr(reviewer, "endpoint", None):
-        feedback = _local_feedback(reviewer, text, references, user)
+    if reviewer.provider == "http":
+        feedback = _http_feedback(reviewer, text, references, user)
+        if feedback:
+            return feedback
+
+    if reviewer.provider == "local":
+        feedback = _local_reference_feedback(reviewer, references, user)
         if feedback:
             return feedback
+        if getattr(reviewer, "endpoint", None):
+            feedback = _local_feedback(reviewer, text, references, user)
+            if feedback:
+                return feedback
 
     return _fallback_feedback(text, references)

compair_core/server/local_model/ocr.py

@@ -0,0 +1,44 @@
+"""Minimal OCR endpoint leveraging pytesseract when available."""
+from __future__ import annotations
+
+import io
+import os
+from typing import Any, Dict
+
+from fastapi import FastAPI, File, HTTPException, UploadFile
+
+app = FastAPI(title="Compair Local OCR", version="0.1.0")
+
+try:  # Optional dependency
+    import pytesseract  # type: ignore
+    from PIL import Image  # type: ignore
+except ImportError:  # pragma: no cover - optional
+    pytesseract = None  # type: ignore
+    Image = None  # type: ignore
+
+_OCR_FALLBACK = os.getenv("COMPAIR_LOCAL_OCR_FALLBACK", "text")  # text | none
+
+
+def _extract_text(data: bytes) -> str:
+    if pytesseract is None or Image is None:
+        if _OCR_FALLBACK == "text":
+            try:
+                return data.decode("utf-8")
+            except UnicodeDecodeError:
+                return data.decode("latin-1", errors="ignore")
+        return ""
+    try:
+        image = Image.open(io.BytesIO(data))
+        return pytesseract.image_to_string(image)
+    except Exception:
+        return ""
+
+
+@app.post("/ocr-file")
+async def ocr_file(file: UploadFile = File(...)) -> Dict[str, Any]:
+    payload = await file.read()
+    text = _extract_text(payload)
+    if not text:
+        raise HTTPException(status_code=501, detail="OCR not available or failed to extract text.")
+    return {"extracted_text": text}
+

compair_core/server/routers/capabilities.py

@@ -36,6 +36,10 @@ def capabilities(settings: Settings = Depends(get_settings)) -> dict[str, object
             "docs": None if edition == "core" else 100,
             "feedback_per_day": None if edition == "core" else 50,
         },
+        "features": {
+            "ocr_upload": settings.ocr_enabled,
+            "activity_feed": edition == "cloud",
+        },
         "server": "Compair Cloud" if edition == "cloud" else "Compair Core",
         "version": settings.version,
         "legacy_routes": settings.include_legacy_routes,

{compair_core-0.3.15.dist-info → compair_core-0.4.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: compair-core
-Version: 0.3.15
+Version: 0.4.1
 Summary: Open-source foundation of the Compair collaboration platform.
 Author: RocketResearch, Inc.
 License: MIT
@@ -86,7 +86,8 @@ Container definitions and build pipelines live outside this public package:
 Key environment variables for the core edition:
 
 - `COMPAIR_EDITION` (`core`) – corresponds to this core local implementation.
-- `COMPAIR_SQLITE_DIR` / `COMPAIR_SQLITE_NAME` – override the default local SQLite path (falls back to `./compair_data` if `/data` is not writable).
+- `COMPAIR_DATABASE_URL` – optional explicit SQLAlchemy URL (e.g. `postgresql+psycopg2://user:pass@host/db`). When omitted, Compair falls back to a local SQLite file.
+- `COMPAIR_DB_DIR` / `COMPAIR_DB_NAME` – directory and filename for the bundled SQLite database (default: `~/.compair-core/data/compair.db`). Legacy `COMPAIR_SQLITE_*` variables remain supported.
 - `COMPAIR_LOCAL_MODEL_URL` – endpoint for your local embeddings/feedback service (defaults to `http://local-model:9000`).
 - `COMPAIR_EMAIL_BACKEND` – the core mailer logs emails to stdout; cloud overrides this with transactional delivery.
 - `COMPAIR_REQUIRE_AUTHENTICATION` (`true`) – set to `false` to run the API in single-user mode without login or account management. When disabled, Compair auto-provisions a local user, group, and long-lived session token so you can upload documents immediately.
@@ -94,8 +95,10 @@ Key environment variables for the core edition:
 - `COMPAIR_INCLUDE_LEGACY_ROUTES` (`false`) – opt-in to the full legacy API surface (used by the hosted product) when running the core edition. Leave unset to expose only the streamlined single-user endpoints in Swagger.
 - `COMPAIR_EMBEDDING_DIM` – force the embedding vector size stored in the database (defaults to 384 for core, 1536 for cloud). Keep this in sync with whichever embedding model you configure.
 - `COMPAIR_VECTOR_BACKEND` (`auto`) – set to `pgvector` when running against PostgreSQL with the pgvector extension, or `json` to store embeddings as JSON (the default for SQLite deployments).
-- `COMPAIR_GENERATION_PROVIDER` (`local`) – choose how feedback is produced. Options: `local` (call the bundled FastAPI service), `openai` (use ChatGPT-compatible APIs with an API key), or `fallback` (skip generation and surface similar references only).
+- `COMPAIR_GENERATION_PROVIDER` (`local`) – choose how feedback is produced. Options: `local` (call the bundled FastAPI service), `openai` (use ChatGPT-compatible APIs with an API key), `http` (POST the request to a custom endpoint), or `fallback` (skip generation and surface similar references only).
 - `COMPAIR_OPENAI_API_KEY` / `COMPAIR_OPENAI_MODEL` – when using the OpenAI provider, supply your API key and optional model name (defaults to `gpt-4o-mini`). The fallback kicks in automatically if the key or SDK is unavailable.
+- `COMPAIR_GENERATION_ENDPOINT` – HTTP endpoint invoked when `COMPAIR_GENERATION_PROVIDER=http`; the service receives a JSON payload (`document`, `references`, `length_instruction`) and should return `{"feedback": ...}`.
+- `COMPAIR_OCR_ENDPOINT` – endpoint the backend calls for OCR uploads (defaults to the bundled Tesseract wrapper at `http://local-ocr:9001/ocr-file`). Provide your own service by overriding this URL.
 
 See `compair_core/server/settings.py` for the full settings surface.
 

{compair_core-0.3.15.dist-info → compair_core-0.4.1.dist-info}/RECORD

@@ -1,10 +1,10 @@
 compair_core/__init__.py,sha256=ktPgTk1QCd7PF-CUzfcd49JvkEut68SEefx2qcL5M5s,122
-compair_core/api.py,sha256=4djXWddiUQLvXWCgebuuS2NYo3WwDMO3TS5UFM29gB4,136290
-compair_core/compair/__init__.py,sha256=V2mqe6UQEvY4U8XL8T-TtCRNDWVUMNeCLZ8nsYQLvr4,2494
+compair_core/api.py,sha256=Xdpu0wFHPRMYy1CpvuAJkc_gOkawbZwm3iPDiK8S_R4,136536
+compair_core/compair/__init__.py,sha256=LEmm8dmLk3J5nuDHyGA1H4k8Z9Xtdl0eukXs5mrp5mg,3265
 compair_core/compair/celery_app.py,sha256=OM_Saza9yC9Q0kz_WXctfswrKkG7ruT52Zl5E4guiT0,640
 compair_core/compair/default_groups.py,sha256=dbacrFkSjqEQZ_uoFU5gYhgIoP_3lmvz6LJNHCJvxlw,498
 compair_core/compair/embeddings.py,sha256=hlDt_C4JWKQCx_pWZZeBSNaF2gvkIUupQyl5Wq4HR34,2754
-compair_core/compair/feedback.py,sha256=FvHefla0bKdyWLNduAVjCxASgZAM-XumElht3JtWHPs,7573
+compair_core/compair/feedback.py,sha256=Z3UkcrtQhrH7rRRGhe5_HAeqkFglK8VkNxs1sTMvBtM,12071
 compair_core/compair/logger.py,sha256=mB9gV3FfC0qE_G9NBErpEAJhyGxDxEVKqWKu3n8hOkc,802
 compair_core/compair/main.py,sha256=d2d7ENXDWKVG_anOG8Kkr-r9W19h__7zwXSo-3zx4rY,8976
 compair_core/compair/models.py,sha256=0ysM2HG1E8j4MmW6P7abEgNFfor_yfFffScYIl8xku8,16590
@@ -22,6 +22,7 @@ compair_core/server/deps.py,sha256=0X-Z5JQGeXwbMooWIOC2kXVmsiJIvgUtqkK2PmDjKpI,1
 compair_core/server/settings.py,sha256=mWE5vgIx3jxm6LzyeH6QL1tCwxQ6bsZIQffVowqtkFQ,1681
 compair_core/server/local_model/__init__.py,sha256=YlzDgorgAjGou9d_W29Xp3TVu08e4t9x8csFxn8cgSE,50
 compair_core/server/local_model/app.py,sha256=943dnixGcaxHixBXVgJmG5G69gisFcwcIh65NJ5scGU,2552
+compair_core/server/local_model/ocr.py,sha256=Nyw3ZsHwGPeqI7iK9SIXqrj8ZFrXfC9AYCPg0XK4KW8,1345
 compair_core/server/providers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 compair_core/server/providers/console_mailer.py,sha256=7ady954yOPlT8t3spkDvdMdO3BTwosJUj1cpVNOwj8U,308
 compair_core/server/providers/contracts.py,sha256=pYA_2AaPHw089O_UP2JtWRHbIiVkoNGhLuesuNATowU,1858
@@ -30,9 +31,9 @@ compair_core/server/providers/noop_analytics.py,sha256=OKw23SObxBlQzFdB0xEBg5qD1
 compair_core/server/providers/noop_billing.py,sha256=V18Cpl1D1reM3xhgw-lShGliVpYO8IsiAPWOAIR34jM,1358
 compair_core/server/providers/noop_ocr.py,sha256=fMaJrivDef38-ECgIuTXUBCIm_avgvZf3nQ3UTdFPNI,341
 compair_core/server/routers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-compair_core/server/routers/capabilities.py,sha256=2U9lEzyQRRYftprrvEeM5Lif_5rhiRGqZhIsvYZBaE4,1349
-compair_core-0.3.15.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-compair_core-0.3.15.dist-info/METADATA,sha256=GPBU-Wg4GLnY3isvgl4z9JTtTQs-iKyneD_rTMNB7hg,6191
-compair_core-0.3.15.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-compair_core-0.3.15.dist-info/top_level.txt,sha256=1dpwoLSY2DWQUVGS05Tq0MuFXg8sabYzg4V2deLzzuo,13
-compair_core-0.3.15.dist-info/RECORD,,
+compair_core/server/routers/capabilities.py,sha256=hM7HNM6efkyZ7xk0-CLI31qMJvbKM1MwC7xBgj_5-Qw,1479
+compair_core-0.4.1.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+compair_core-0.4.1.dist-info/METADATA,sha256=JacoGu-SmPi4pvVGViHOHVHyXzrNvLYPHJbbp5w2yMM,6879
+compair_core-0.4.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+compair_core-0.4.1.dist-info/top_level.txt,sha256=1dpwoLSY2DWQUVGS05Tq0MuFXg8sabYzg4V2deLzzuo,13
+compair_core-0.4.1.dist-info/RECORD,,