sunholo 0.110.4__py3-none-any.whl → 0.112.0__py3-none-any.whl

sunholo/chunker/loaders.py

@@ -11,9 +11,10 @@
 #   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #   See the License for the specific language governing permissions and
 #   limitations under the License.
-from langchain_community.document_loaders import UnstructuredFileLoader
-from langchain_community.document_loaders import UnstructuredAPIFileLoader
-from langchain_community.document_loaders import UnstructuredURLLoader
+try:
+    from langchain_unstructured import UnstructuredLoader
+except ImportError:
+    UnstructuredLoader = None
 
 from langchain_community.document_loaders import GitLoader
 from langchain_community.document_loaders import GoogleDriveLoader
@@ -159,10 +160,12 @@ def read_gdrive_to_document(url: str, metadata: dict = None):
 
 def read_url_to_document(url: str, metadata: dict = None):
 
+    if not  UnstructuredLoader:
+        raise ImportError("UnstructuredLoader requires 'langchain_unstructured' to be installed")
     unstructured_kwargs = {"pdf_infer_table_structure": True,
                             "extract_image_block_types":  ["Image", "Table"]
                             }
-    loader = UnstructuredURLLoader(urls=[url], mode="elements", unstructured_kwargs=unstructured_kwargs)
+    loader = UnstructuredLoader(web_url=url, mode="elements", unstructured_kwargs=unstructured_kwargs)
     docs = loader.load()
     if metadata is not None:
         for doc in docs:
@@ -170,7 +173,7 @@ def read_url_to_document(url: str, metadata: dict = None):
             if not doc.metadata.get("source") and doc.metadata.get("url"):
                 doc.metadata["source"] = doc.metadata["url"]
     
-    log.info(f"UnstructuredURLLoader docs: {docs}")
+    log.info(f"UnstructuredLoader docs: {docs}")
     
     return docs
 
@@ -184,18 +187,21 @@ def read_file_to_documents(gs_file: pathlib.Path, metadata: dict = None):
             log.info(f"Already uploaded to bucket, skipping {pdf_path}")
             return []
 
-    log.info(f"Sending {pdf_path} to UnstructuredAPIFileLoader")
+    log.info(f"Sending {pdf_path} to UnstructuredLoader")
     UNSTRUCTURED_URL = os.getenv("UNSTRUCTURED_URL")
     unstructured_kwargs = {"pdf_infer_table_structure": True,
                             "extract_image_block_types":  ["Image", "Table"]
                             }
     
+    if not  UnstructuredLoader:
+        raise ImportError("UnstructuredLoader requires 'langchain_unstructured' to be installed")
+    
     if UNSTRUCTURED_URL:
         log.debug(f"Found UNSTRUCTURED_URL: {UNSTRUCTURED_URL}")
         the_endpoint = f"{UNSTRUCTURED_URL}/general/v0/general"
         try:
-            loader = UnstructuredAPIFileLoader(
-                pdf_path,
+            loader = UnstructuredLoader(
+                file_path=pdf_path,
                 url=the_endpoint,
                 mode="elements",
                 **unstructured_kwargs)
@@ -206,8 +212,8 @@ def read_file_to_documents(gs_file: pathlib.Path, metadata: dict = None):
             else:
                 raise err
     else:
-        loader = UnstructuredAPIFileLoader(
-            pdf_path,
+        loader = UnstructuredLoader(
+            file_path=pdf_path,
             api_key=UNSTRUCTURED_KEY,
             mode="elements",
             **unstructured_kwargs)
@@ -216,7 +222,7 @@ def read_file_to_documents(gs_file: pathlib.Path, metadata: dict = None):
     try:
         docs = loader.load() # this takes a long time 30m+ for big PDF files
     except ValueError as e:
-        log.info(f"Error for {gs_file} from UnstructuredAPIFileLoader: {str(e)}")
+        log.info(f"Error for {gs_file} from UnstructuredLoader: {str(e)}")
         pdf_path = pathlib.Path(gs_file)
         if pdf_path.suffix == ".pdf":
             local_doc = read_pdf_file(pdf_path, metadata=metadata)
@@ -262,13 +268,16 @@ def read_file_to_documents(gs_file: pathlib.Path, metadata: dict = None):
 
 def convert_to_txt_and_extract(gs_file, split=False):
 
+    if not  UnstructuredLoader:
+        raise ImportError("UnstructuredLoader requires 'langchain_unstructured' to be installed")
+    
     log.info("trying file parsing locally via .txt conversion")
     txt_file = None
     docs = []
     try:
         # Convert the file to .txt and try again
         txt_file = convert_to_txt(gs_file)
-        loader = UnstructuredFileLoader(
+        loader = UnstructuredLoader(
             txt_file, 
             mode="elements")
 

sunholo/database/alloydb_client.py

@@ -302,7 +302,7 @@ class AlloyDBClient:
             SELECT page_content, source, langchain_metadata, images_gsurls, doc_id::text as doc_id
             FROM "{table_name}"
             WHERE source ILIKE '%{source}%'
-            LIMIT 500;
+            LIMIT 1000;
         """
 
         return query
@@ -319,7 +319,7 @@ class AlloyDBClient:
             SELECT page_content, source, langchain_metadata, images_gsurls, doc_id::text as doc_id
             FROM "{table_name}"
             WHERE doc_id = '{doc_id}'
-            LIMIT 50;
+            LIMIT 500;
         """
 
         return query
@@ -362,11 +362,16 @@ class AlloyDBClient:
         conditions = self._and_or_ilike(sources, search_type=search_type)
 
         query = f"""
-            SELECT * 
+            WITH ranked_sources AS (
+            SELECT *,
+                    ROW_NUMBER() OVER (PARTITION BY source ORDER BY doc_id) as chunk_num
             FROM {table_name}
             WHERE {conditions}
-            ORDER BY source ASC
-            LIMIT 50;
+            )
+            SELECT *
+            FROM ranked_sources
+            ORDER BY source ASC, chunk_num ASC
+            LIMIT 1000;
         """
 
         return query
@@ -378,10 +383,9 @@ class AlloyDBClient:
         if sources:
             conditions = self._and_or_ilike(sources, search_type=search_type)
             query = f"""
-                SELECT source AS objectId
+                SELECT DISTINCT source AS objectId
                 FROM {table_name}
                 WHERE {conditions}
-                GROUP BY source
                 ORDER BY source ASC
                 LIMIT 500;
             """

sunholo-0.112.0.dist-info/METADATA

@@ -0,0 +1,211 @@
+Metadata-Version: 2.1
+Name: sunholo
+Version: 0.112.0
+Summary: Large Language Model DevOps - a package to help deploy LLMs to the Cloud.
+Home-page: https://github.com/sunholo-data/sunholo-py
+Download-URL: https://github.com/sunholo-data/sunholo-py/archive/refs/tags/v0.112.0.tar.gz
+Author: Holosun ApS
+Author-email: multivac@sunholo.com
+License: Apache License, Version 2.0
+Keywords: llms,devops,google_cloud_platform
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Software Development :: Build Tools
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+Requires-Dist: google-auth
+Requires-Dist: ruamel.yaml
+Requires-Dist: langchain==0.2.16
+Requires-Dist: langchain_experimental==0.0.65
+Requires-Dist: langchain-community==0.2.17
+Requires-Dist: langsmith==0.1.143
+Provides-Extra: all
+Requires-Dist: anthropic[vertex]; extra == "all"
+Requires-Dist: asyncpg; extra == "all"
+Requires-Dist: azure-identity; extra == "all"
+Requires-Dist: azure-storage-blob; extra == "all"
+Requires-Dist: fastapi; extra == "all"
+Requires-Dist: flask; extra == "all"
+Requires-Dist: google-auth; extra == "all"
+Requires-Dist: google-auth-httplib2; extra == "all"
+Requires-Dist: google-auth-oauthlib; extra == "all"
+Requires-Dist: google-cloud-aiplatform>=1.58.0; extra == "all"
+Requires-Dist: google-api-python-client; extra == "all"
+Requires-Dist: google-cloud-alloydb-connector[pg8000]; extra == "all"
+Requires-Dist: google-cloud-bigquery; extra == "all"
+Requires-Dist: google-cloud-build; extra == "all"
+Requires-Dist: google-cloud-service-control; extra == "all"
+Requires-Dist: google-cloud-logging; extra == "all"
+Requires-Dist: google-cloud-storage; extra == "all"
+Requires-Dist: google-cloud-pubsub; extra == "all"
+Requires-Dist: google-cloud-discoveryengine; extra == "all"
+Requires-Dist: google-cloud-texttospeech; extra == "all"
+Requires-Dist: google-generativeai>=0.7.1; extra == "all"
+Requires-Dist: gunicorn; extra == "all"
+Requires-Dist: httpcore; extra == "all"
+Requires-Dist: httpx; extra == "all"
+Requires-Dist: jsonschema; extra == "all"
+Requires-Dist: lancedb; extra == "all"
+Requires-Dist: langchain>=0.2.16; extra == "all"
+Requires-Dist: langchain-experimental>=0.0.61; extra == "all"
+Requires-Dist: langchain-community>=0.2.11; extra == "all"
+Requires-Dist: langchain-openai==0.1.25; extra == "all"
+Requires-Dist: langchain-google-genai==1.0.10; extra == "all"
+Requires-Dist: langchain_google_alloydb_pg; extra == "all"
+Requires-Dist: langchain-anthropic==0.1.23; extra == "all"
+Requires-Dist: langchain-google-vertexai; extra == "all"
+Requires-Dist: langchain-unstructured; extra == "all"
+Requires-Dist: langfuse; extra == "all"
+Requires-Dist: numpy; extra == "all"
+Requires-Dist: pg8000; extra == "all"
+Requires-Dist: pgvector; extra == "all"
+Requires-Dist: pillow; extra == "all"
+Requires-Dist: playwright; extra == "all"
+Requires-Dist: psutil; extra == "all"
+Requires-Dist: psycopg2-binary; extra == "all"
+Requires-Dist: pypdf; extra == "all"
+Requires-Dist: python-hcl2; extra == "all"
+Requires-Dist: python-socketio; extra == "all"
+Requires-Dist: pytesseract; extra == "all"
+Requires-Dist: rich; extra == "all"
+Requires-Dist: sounddevice; extra == "all"
+Requires-Dist: supabase; extra == "all"
+Requires-Dist: tabulate; extra == "all"
+Requires-Dist: tantivy; extra == "all"
+Requires-Dist: tenacity; extra == "all"
+Requires-Dist: tiktoken; extra == "all"
+Requires-Dist: unstructured[all-docs,local-inference]; extra == "all"
+Requires-Dist: xlwings; extra == "all"
+Provides-Extra: azure
+Requires-Dist: azure-identity; extra == "azure"
+Requires-Dist: azure-storage-blob; extra == "azure"
+Provides-Extra: cli
+Requires-Dist: jsonschema>=4.21.1; extra == "cli"
+Requires-Dist: rich; extra == "cli"
+Provides-Extra: database
+Requires-Dist: asyncpg; extra == "database"
+Requires-Dist: supabase; extra == "database"
+Requires-Dist: sqlalchemy; extra == "database"
+Requires-Dist: pg8000; extra == "database"
+Requires-Dist: pgvector; extra == "database"
+Requires-Dist: psycopg2-binary; extra == "database"
+Requires-Dist: lancedb; extra == "database"
+Requires-Dist: tantivy; extra == "database"
+Provides-Extra: pipeline
+Requires-Dist: GitPython; extra == "pipeline"
+Requires-Dist: lark; extra == "pipeline"
+Requires-Dist: langchain-unstructured; extra == "pipeline"
+Requires-Dist: psutil; extra == "pipeline"
+Requires-Dist: pypdf; extra == "pipeline"
+Requires-Dist: pytesseract; extra == "pipeline"
+Requires-Dist: tabulate; extra == "pipeline"
+Requires-Dist: unstructured[all-docs,local-inference]; extra == "pipeline"
+Provides-Extra: gcp
+Requires-Dist: anthropic[vertex]; extra == "gcp"
+Requires-Dist: google-api-python-client; extra == "gcp"
+Requires-Dist: google-cloud-alloydb-connector[pg8000]; extra == "gcp"
+Requires-Dist: google-auth-httplib2; extra == "gcp"
+Requires-Dist: google-auth-oauthlib; extra == "gcp"
+Requires-Dist: google-cloud-aiplatform>=1.58.0; extra == "gcp"
+Requires-Dist: google-cloud-bigquery; extra == "gcp"
+Requires-Dist: google-cloud-build; extra == "gcp"
+Requires-Dist: google-cloud-service-control; extra == "gcp"
+Requires-Dist: google-cloud-storage; extra == "gcp"
+Requires-Dist: google-cloud-logging; extra == "gcp"
+Requires-Dist: google-cloud-pubsub; extra == "gcp"
+Requires-Dist: google-cloud-discoveryengine; extra == "gcp"
+Requires-Dist: google-cloud-texttospeech; extra == "gcp"
+Requires-Dist: google-generativeai>=0.7.1; extra == "gcp"
+Requires-Dist: langchain-google-genai==1.0.10; extra == "gcp"
+Requires-Dist: langchain_google_alloydb_pg>=0.2.2; extra == "gcp"
+Requires-Dist: langchain-google-vertexai; extra == "gcp"
+Requires-Dist: pillow; extra == "gcp"
+Provides-Extra: openai
+Requires-Dist: langchain-openai==0.1.25; extra == "openai"
+Requires-Dist: tiktoken; extra == "openai"
+Provides-Extra: anthropic
+Requires-Dist: langchain-anthropic==0.1.23; extra == "anthropic"
+Provides-Extra: tools
+Requires-Dist: openapi-spec-validator; extra == "tools"
+Requires-Dist: playwright; extra == "tools"
+Provides-Extra: http
+Requires-Dist: fastapi; extra == "http"
+Requires-Dist: flask; extra == "http"
+Requires-Dist: gunicorn; extra == "http"
+Requires-Dist: httpcore; extra == "http"
+Requires-Dist: httpx; extra == "http"
+Requires-Dist: langfuse; extra == "http"
+Requires-Dist: python-socketio; extra == "http"
+Requires-Dist: requests; extra == "http"
+Requires-Dist: tenacity; extra == "http"
+Provides-Extra: excel
+Requires-Dist: xlwings; extra == "excel"
+Requires-Dist: requests; extra == "excel"
+Requires-Dist: rich; extra == "excel"
+Provides-Extra: iac
+Requires-Dist: python-hcl2; extra == "iac"
+Provides-Extra: tts
+Requires-Dist: google-cloud-texttospeech; extra == "tts"
+Requires-Dist: numpy; extra == "tts"
+Requires-Dist: sounddevice; extra == "tts"
+
+## Introduction
+This is the Sunholo Python project, a comprehensive toolkit for working with language models and vector stores on Google Cloud Platform. It provides a wide range of functionalities and utilities to facilitate the development and deployment of language model applications.
+
+Please refer to the website for full documentation at https://dev.sunholo.com/
+
+## Listen to the audio file:
+
+A [NotebookLM](https://notebooklm.google/) generated podcast of the codebase that may help give you an overview of what the library is capable of:
+
+[Listen to the audio file from Google Drive](https://drive.google.com/file/d/1GvwRmiYDjPjN2hXQ8plhnVDByu6TmgCQ/view?usp=drive_link) or on the website at https://dev.sunholo.com/docs/ 
+
+> "Ever wish you could build your own AI?..."
+
+## Tests via pytest
+
+If loading from GitHub, run tests:
+
+```bash
+pip install pytest
+pip install . --use-feature=in-tree-build
+pytest tests
+```
+
+## Demos
+
+Using https://github.com/charmbracelet/vhs
+
+```sh
+vhs record > cassette.tape
+```
+
+Then make gif:
+
+```sh
+vhs docs/tapes/config-list.tape
+```
+
+
+
+```
+   Copyright [2024] [Holosun ApS]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+```
+

{sunholo-0.110.4.dist-info → sunholo-0.112.0.dist-info}/RECORD

@@ -34,7 +34,7 @@ sunholo/chunker/azure.py,sha256=MVF9_-QdKUoJqlpEJ49pv2sdjMDxEiMNxzmO7w5nWDQ,3270
 sunholo/chunker/doc_handling.py,sha256=UAf9BmUMpKCKRlAMl1qNZK6xDNYWk1z3ARoftWoa_54,8734
 sunholo/chunker/encode_metadata.py,sha256=hxxd9KU35Xi0Z_EL8kt_oD66pKfBLhEjBImC16ew-Eo,1919
 sunholo/chunker/images.py,sha256=id2PBu6XyGEOtgafq2v0c9_O6kxaC_pYFMnbsIitkSg,1868
-sunholo/chunker/loaders.py,sha256=n64UgXDB8ZkApnqJwb3VKc8lGTVo8TC1AXmARiaCsQY,10269
+sunholo/chunker/loaders.py,sha256=QaM-M1wmbA2iLIDvBKpC5-TPKMlQIxS01gMKj5n9RyM,10547
 sunholo/chunker/message_data.py,sha256=EaiY7_HClpcfPUAYaAm6Zk5ReeZ9s9F_jBVd0kDgI-4,10836
 sunholo/chunker/pdfs.py,sha256=njDPop751GMHi3cOwIKd2Yct-_lWR2gqcB7WykfHphs,2480
 sunholo/chunker/process_chunker_data.py,sha256=uO-YOEHIjAOy0ZMJ0vea9OMNsQBISHfhbtgoyuHiP6s,3598
@@ -59,7 +59,7 @@ sunholo/components/retriever.py,sha256=bKIVT7_18Ut3OJd0E0jyiISPnD9qkHWVjcQPT4i1_
 sunholo/components/vectorstore.py,sha256=xKk7micTRwZckaI7U6PxvFz_ZSjCH48xPTDYiDcv2tc,5913
 sunholo/database/__init__.py,sha256=bpB5Nk21kwqYj-qdVnvNgXjLsbflnH4g-San7OHMqR4,283
 sunholo/database/alloydb.py,sha256=x1zUMB-EVWbE2Zvp4nAs2Z-tB_kOZmS45H2lwVHdYnk,11678
-sunholo/database/alloydb_client.py,sha256=kg6J8pCqBkjfEkXdhU8mwxdaI7w-cSE9AxKHWuYmzaM,18943
+sunholo/database/alloydb_client.py,sha256=q732tmRdSDutnUk7vRUPUPpi-yU5FK5rQko8co6yke0,19132
 sunholo/database/database.py,sha256=VqhZdkXUNdvWn8sUcUV3YNby1JDVf7IykPVXWBtxo9U,7361
 sunholo/database/lancedb.py,sha256=DyfZntiFKBlVPaFooNN1Z6Pl-LAs4nxWKKuq8GBqN58,715
 sunholo/database/static_dbs.py,sha256=8cvcMwUK6c32AS2e_WguKXWMkFf5iN3g9WHzsh0C07Q,442
@@ -150,9 +150,9 @@ sunholo/vertex/init.py,sha256=1OQwcPBKZYBTDPdyU7IM4X4OmiXLdsNV30C-fee2scQ,2875
 sunholo/vertex/memory_tools.py,sha256=tBZxqVZ4InTmdBvLlOYwoSEWu4-kGquc-gxDwZCC4FA,7667
 sunholo/vertex/safety.py,sha256=S9PgQT1O_BQAkcqauWncRJaydiP8Q_Jzmu9gxYfy1VA,2482
 sunholo/vertex/type_dict_to_json.py,sha256=uTzL4o9tJRao4u-gJOFcACgWGkBOtqACmb6ihvCErL8,4694
-sunholo-0.110.4.dist-info/LICENSE.txt,sha256=SdE3QjnD3GEmqqg9EX3TM9f7WmtOzqS1KJve8rhbYmU,11345
-sunholo-0.110.4.dist-info/METADATA,sha256=4EZvfegaiERNSi6qN-RUVWy1CojNXbCjGg4sZ89g2cI,8705
-sunholo-0.110.4.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
-sunholo-0.110.4.dist-info/entry_points.txt,sha256=bZuN5AIHingMPt4Ro1b_T-FnQvZ3teBes-3OyO0asl4,49
-sunholo-0.110.4.dist-info/top_level.txt,sha256=wt5tadn5--5JrZsjJz2LceoUvcrIvxjHJe-RxuudxAk,8
-sunholo-0.110.4.dist-info/RECORD,,
+sunholo-0.112.0.dist-info/LICENSE.txt,sha256=SdE3QjnD3GEmqqg9EX3TM9f7WmtOzqS1KJve8rhbYmU,11345
+sunholo-0.112.0.dist-info/METADATA,sha256=kiphk-fAQurwpMyZVdgAqVdhS4yUr8AJPLjUAZze2_I,8685
+sunholo-0.112.0.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+sunholo-0.112.0.dist-info/entry_points.txt,sha256=bZuN5AIHingMPt4Ro1b_T-FnQvZ3teBes-3OyO0asl4,49
+sunholo-0.112.0.dist-info/top_level.txt,sha256=wt5tadn5--5JrZsjJz2LceoUvcrIvxjHJe-RxuudxAk,8
+sunholo-0.112.0.dist-info/RECORD,,

{sunholo-0.110.4.dist-info → sunholo-0.112.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.5.0)
+Generator: setuptools (75.6.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

sunholo-0.110.4.dist-info/METADATA

@@ -1,209 +0,0 @@
-Metadata-Version: 2.1
-Name: sunholo
-Version: 0.110.4
-Summary: Large Language Model DevOps - a package to help deploy LLMs to the Cloud.
-Home-page: https://github.com/sunholo-data/sunholo-py
-Download-URL: https://github.com/sunholo-data/sunholo-py/archive/refs/tags/v0.110.4.tar.gz
-Author: Holosun ApS
-Author-email: multivac@sunholo.com
-License: Apache License, Version 2.0
-Keywords: llms,devops,google_cloud_platform
-Classifier: Development Status :: 3 - Alpha
-Classifier: Intended Audience :: Developers
-Classifier: Topic :: Software Development :: Build Tools
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Description-Content-Type: text/markdown
-License-File: LICENSE.txt
-Requires-Dist: google-auth
-Requires-Dist: ruamel.yaml
-Requires-Dist: langchain ==0.2.16
-Requires-Dist: langchain-experimental ==0.0.65
-Requires-Dist: langchain-community ==0.2.17
-Requires-Dist: langsmith ==0.1.143
-Provides-Extra: all
-Requires-Dist: anthropic[vertex] ; extra == 'all'
-Requires-Dist: asyncpg ; extra == 'all'
-Requires-Dist: azure-identity ; extra == 'all'
-Requires-Dist: azure-storage-blob ; extra == 'all'
-Requires-Dist: fastapi ; extra == 'all'
-Requires-Dist: flask ; extra == 'all'
-Requires-Dist: google-auth ; extra == 'all'
-Requires-Dist: google-auth-httplib2 ; extra == 'all'
-Requires-Dist: google-auth-oauthlib ; extra == 'all'
-Requires-Dist: google-cloud-aiplatform >=1.58.0 ; extra == 'all'
-Requires-Dist: google-api-python-client ; extra == 'all'
-Requires-Dist: google-cloud-alloydb-connector[pg8000] ; extra == 'all'
-Requires-Dist: google-cloud-bigquery ; extra == 'all'
-Requires-Dist: google-cloud-build ; extra == 'all'
-Requires-Dist: google-cloud-service-control ; extra == 'all'
-Requires-Dist: google-cloud-logging ; extra == 'all'
-Requires-Dist: google-cloud-storage ; extra == 'all'
-Requires-Dist: google-cloud-pubsub ; extra == 'all'
-Requires-Dist: google-cloud-discoveryengine ; extra == 'all'
-Requires-Dist: google-cloud-texttospeech ; extra == 'all'
-Requires-Dist: google-generativeai >=0.7.1 ; extra == 'all'
-Requires-Dist: gunicorn ; extra == 'all'
-Requires-Dist: httpcore ; extra == 'all'
-Requires-Dist: httpx ; extra == 'all'
-Requires-Dist: jsonschema ; extra == 'all'
-Requires-Dist: lancedb ; extra == 'all'
-Requires-Dist: langchain >=0.2.16 ; extra == 'all'
-Requires-Dist: langchain-experimental >=0.0.61 ; extra == 'all'
-Requires-Dist: langchain-community >=0.2.11 ; extra == 'all'
-Requires-Dist: langchain-openai ==0.1.25 ; extra == 'all'
-Requires-Dist: langchain-google-genai ==1.0.10 ; extra == 'all'
-Requires-Dist: langchain-google-alloydb-pg ; extra == 'all'
-Requires-Dist: langchain-anthropic ==0.1.23 ; extra == 'all'
-Requires-Dist: langchain-google-vertexai ; extra == 'all'
-Requires-Dist: langfuse ; extra == 'all'
-Requires-Dist: numpy ; extra == 'all'
-Requires-Dist: pg8000 ; extra == 'all'
-Requires-Dist: pgvector ; extra == 'all'
-Requires-Dist: pillow ; extra == 'all'
-Requires-Dist: playwright ; extra == 'all'
-Requires-Dist: psutil ; extra == 'all'
-Requires-Dist: psycopg2-binary ; extra == 'all'
-Requires-Dist: pypdf ; extra == 'all'
-Requires-Dist: python-hcl2 ; extra == 'all'
-Requires-Dist: python-socketio ; extra == 'all'
-Requires-Dist: pytesseract ; extra == 'all'
-Requires-Dist: rich ; extra == 'all'
-Requires-Dist: sounddevice ; extra == 'all'
-Requires-Dist: supabase ; extra == 'all'
-Requires-Dist: tabulate ; extra == 'all'
-Requires-Dist: tantivy ; extra == 'all'
-Requires-Dist: tenacity ; extra == 'all'
-Requires-Dist: tiktoken ; extra == 'all'
-Requires-Dist: unstructured[local-inference] ==0.14.9 ; extra == 'all'
-Requires-Dist: xlwings ; extra == 'all'
-Provides-Extra: anthropic
-Requires-Dist: langchain-anthropic ==0.1.23 ; extra == 'anthropic'
-Provides-Extra: azure
-Requires-Dist: azure-identity ; extra == 'azure'
-Requires-Dist: azure-storage-blob ; extra == 'azure'
-Provides-Extra: cli
-Requires-Dist: jsonschema >=4.21.1 ; extra == 'cli'
-Requires-Dist: rich ; extra == 'cli'
-Provides-Extra: database
-Requires-Dist: asyncpg ; extra == 'database'
-Requires-Dist: supabase ; extra == 'database'
-Requires-Dist: sqlalchemy ; extra == 'database'
-Requires-Dist: pg8000 ; extra == 'database'
-Requires-Dist: pgvector ; extra == 'database'
-Requires-Dist: psycopg2-binary ; extra == 'database'
-Requires-Dist: lancedb ; extra == 'database'
-Requires-Dist: tantivy ; extra == 'database'
-Provides-Extra: excel
-Requires-Dist: xlwings ; extra == 'excel'
-Requires-Dist: requests ; extra == 'excel'
-Requires-Dist: rich ; extra == 'excel'
-Provides-Extra: gcp
-Requires-Dist: anthropic[vertex] ; extra == 'gcp'
-Requires-Dist: google-api-python-client ; extra == 'gcp'
-Requires-Dist: google-cloud-alloydb-connector[pg8000] ; extra == 'gcp'
-Requires-Dist: google-auth-httplib2 ; extra == 'gcp'
-Requires-Dist: google-auth-oauthlib ; extra == 'gcp'
-Requires-Dist: google-cloud-aiplatform >=1.58.0 ; extra == 'gcp'
-Requires-Dist: google-cloud-bigquery ; extra == 'gcp'
-Requires-Dist: google-cloud-build ; extra == 'gcp'
-Requires-Dist: google-cloud-service-control ; extra == 'gcp'
-Requires-Dist: google-cloud-storage ; extra == 'gcp'
-Requires-Dist: google-cloud-logging ; extra == 'gcp'
-Requires-Dist: google-cloud-pubsub ; extra == 'gcp'
-Requires-Dist: google-cloud-discoveryengine ; extra == 'gcp'
-Requires-Dist: google-cloud-texttospeech ; extra == 'gcp'
-Requires-Dist: google-generativeai >=0.7.1 ; extra == 'gcp'
-Requires-Dist: langchain-google-genai ==1.0.10 ; extra == 'gcp'
-Requires-Dist: langchain-google-alloydb-pg >=0.2.2 ; extra == 'gcp'
-Requires-Dist: langchain-google-vertexai ; extra == 'gcp'
-Requires-Dist: pillow ; extra == 'gcp'
-Provides-Extra: http
-Requires-Dist: fastapi ; extra == 'http'
-Requires-Dist: flask ; extra == 'http'
-Requires-Dist: gunicorn ; extra == 'http'
-Requires-Dist: httpcore ; extra == 'http'
-Requires-Dist: httpx ; extra == 'http'
-Requires-Dist: langfuse ; extra == 'http'
-Requires-Dist: python-socketio ; extra == 'http'
-Requires-Dist: requests ; extra == 'http'
-Requires-Dist: tenacity ; extra == 'http'
-Provides-Extra: iac
-Requires-Dist: python-hcl2 ; extra == 'iac'
-Provides-Extra: openai
-Requires-Dist: langchain-openai ==0.1.25 ; extra == 'openai'
-Requires-Dist: tiktoken ; extra == 'openai'
-Provides-Extra: pipeline
-Requires-Dist: GitPython ; extra == 'pipeline'
-Requires-Dist: lark ; extra == 'pipeline'
-Requires-Dist: psutil ; extra == 'pipeline'
-Requires-Dist: pypdf ; extra == 'pipeline'
-Requires-Dist: pytesseract ; extra == 'pipeline'
-Requires-Dist: tabulate ; extra == 'pipeline'
-Requires-Dist: unstructured[local-inference] ==0.14.9 ; extra == 'pipeline'
-Provides-Extra: tools
-Requires-Dist: openapi-spec-validator ; extra == 'tools'
-Requires-Dist: playwright ; extra == 'tools'
-Provides-Extra: tts
-Requires-Dist: google-cloud-texttospeech ; extra == 'tts'
-Requires-Dist: numpy ; extra == 'tts'
-Requires-Dist: sounddevice ; extra == 'tts'
-
-## Introduction
-This is the Sunholo Python project, a comprehensive toolkit for working with language models and vector stores on Google Cloud Platform. It provides a wide range of functionalities and utilities to facilitate the development and deployment of language model applications.
-
-Please refer to the website for full documentation at https://dev.sunholo.com/
-
-## Listen to the audio file:
-
-A [NotebookLM](https://notebooklm.google/) generated podcast of the codebase that may help give you an overview of what the library is capable of:
-
-[Listen to the audio file from Google Drive](https://drive.google.com/file/d/1GvwRmiYDjPjN2hXQ8plhnVDByu6TmgCQ/view?usp=drive_link) or on the website at https://dev.sunholo.com/docs/ 
-
-> "Ever wish you could build your own AI?..."
-
-## Tests via pytest
-
-If loading from GitHub, run tests:
-
-```bash
-pip install pytest
-pip install . --use-feature=in-tree-build
-pytest tests
-```
-
-## Demos
-
-Using https://github.com/charmbracelet/vhs
-
-```sh
-vhs record > cassette.tape
-```
-
-Then make gif:
-
-```sh
-vhs docs/tapes/config-list.tape
-```
-
-
-
-```
-   Copyright [2024] [Holosun ApS]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.
-```
-