Merge pull request #843 from larinam/fix_application

Fix application + script requirements.txt

application/parser/file/bulk.py

@@ -62,7 +62,6 @@ class SimpleDirectoryReader(BaseReader):
             file_extractor: Optional[Dict[str, BaseParser]] = None,
             num_files_limit: Optional[int] = None,
             file_metadata: Optional[Callable[[str], Dict]] = None,
-            chunk_size_max: int = 2048,
     ) -> None:
         """Initialize with parameters."""
         super().__init__()

application/parser/open_ai_func.py

@@ -6,9 +6,9 @@ from application.core.settings import settings
 from retry import retry
 
 
-# from langchain.embeddings import HuggingFaceEmbeddings
-# from langchain.embeddings import HuggingFaceInstructEmbeddings
-# from langchain.embeddings import CohereEmbeddings
+# from langchain_community.embeddings import HuggingFaceEmbeddings
+# from langchain_community.embeddings import HuggingFaceInstructEmbeddings
+# from langchain_community.embeddings import CohereEmbeddings
 
 
 def num_tokens_from_string(string: str, encoding_name: str) -> int:

application/requirements.txt

@@ -1,145 +1,33 @@
-aiodns==3.1.1
-aiohttp==3.9.1
-aiohttp-retry==2.8.3
-aiosignal==1.3.1
-amqp==5.2.0
-annotated-types==0.6.0
-anthropic==0.8.0
-anyio==4.2.0
-async-timeout==4.0.3
-attrs==23.1.0
-billiard==4.2.0
-blinker==1.7.0
-blobfile==2.1.1
+anthropic==0.12.0
 boto3==1.34.6
-botocore==1.34.6
 celery==5.3.6
-certifi==2023.11.17
-cffi==1.16.0
-chardet==5.2.0
-charset-normalizer==3.3.2
-click==8.1.7
-click-didyoumean==0.3.0
-click-plugins==1.1.1
-click-repl==0.3.0
-cryptography==41.0.7
-dataclasses-json==0.6.3
-decorator==5.1.1
-dill==0.3.7
-distro==1.8.0
-dnspython==2.4.2
+dataclasses_json==0.6.3
 docx2txt==0.8
-ecdsa==0.18.0
-elastic-transport==8.11.0
-elasticsearch==8.11.1
-entrypoints==0.4
+EbookLib==0.18
+elasticsearch==8.12.0
+escodegen==1.0.11
+esprima==4.0.1
 faiss-cpu==1.7.4
-filelock==3.13.1
-Flask==3.0.0
-Flask-Cors==4.0.0
-frozenlist==1.4.1
-fsspec==2023.12.2
-geojson==2.5.0
-greenlet==3.0.3
+Flask==3.0.1
 gunicorn==21.2.0
-h11==0.14.0
-httpcore==1.0.2
-httpx==0.26.0
-huggingface-hub==0.20.1
-humbug==0.3.2
-idna==3.6
-iniconfig==2.0.0
-itsdangerous==2.1.2
-Jinja2==3.1.2
-jmespath==1.0.1
-joblib==1.3.2
-jsonpatch==1.33
-jsonpointer==2.4
-kombu==5.3.4
-langchain==0.0.352
-langchain-community==0.0.6
-langchain-core==0.1.3
-langsmith==0.0.74
-lazy-object-proxy==1.10.0
-loguru==0.7.2
-lxml==4.9.4
-MarkupSafe==2.1.3
-marshmallow==3.20.1
-marshmallow-enum==1.5.1
-mpmath==1.3.0
-multidict==6.0.4
-multiprocess==0.70.15
-mypy-extensions==1.0.0
-networkx==3.2.1
+html2text==2020.1.16
+javalang==0.13.0
+langchain==0.1.4
+langchain-openai==0.0.5
 nltk==3.8.1
-npx==0.1.1
-numcodecs==0.12.1
-numpy==1.26.2
-openai==1.6.1
-openapi-schema-validator==0.6.2
-openapi-spec-validator==0.6.0
-openapi3-parser==1.1.16
-packaging==23.2
-pathable==0.4.3
-pathos==0.3.1
-Pillow==10.1.0
-pluggy==1.3.0
-pox==0.3.3
-ppft==1.7.6.7
-prance==23.6.21.0
-prompt-toolkit==3.0.43
-pyasn1==0.5.1
-pycares==4.4.0
-pycparser==2.21
-pycryptodome==3.19.0
-pycryptodomex==3.19.0
-pydantic==2.5.3
-pydantic_core==2.14.6
+openapi3_parser==1.1.16
+pandas==2.2.0
 pydantic_settings==2.1.0
-PyJWT==2.8.0
 pymongo==4.6.1
-pyowm==3.3.0
 PyPDF2==3.0.1
-PySocks==1.7.1
-pytest==7.4.3
-python-dateutil==2.8.2
-python-dotenv==1.0.0
-python-jose==3.3.0
-python-liquid==1.10.2
-pytz==2023.3.post1
-PyYAML==6.0.1
+python-dotenv==1.0.1
 redis==5.0.1
-regex==2023.10.3
-requests==2.31.0
+Requests==2.31.0
 retry==0.9.2
-rfc3339-validator==0.1.4
-rpds-py==0.15.2
-rsa==4.9
-ruamel.yaml==0.18.5
-ruamel.yaml.clib==0.2.8
-s3transfer==0.10.0
-safetensors==0.4.1
-scikit-learn==1.3.2
-scipy==1.11.4
 sentence-transformers
-sentencepiece==0.1.99
-six==1.16.0
-sniffio==1.3.0
-SQLAlchemy==2.0.23
-sympy==1.12
-tenacity==8.2.3
-threadpoolctl==3.2.0
-tiktoken
-tokenizers==0.15.0
+tiktoken==0.5.2
 torch==2.1.2
-torchvision==0.16.2
 tqdm==4.66.1
 transformers==4.36.2
-typer==0.9.0
-typing-inspect==0.9.0
-typing_extensions==4.9.0
-tzdata==2023.3
-vine==5.1.0
-wcwidth==0.2.12
+unstructured==0.12.2
 Werkzeug==3.0.1
-yarl==1.9.4

application/vectorstore/base.py

@@ -1,11 +1,11 @@
 from abc import ABC, abstractmethod
 import os
-from langchain.embeddings import (
-    OpenAIEmbeddings,
+from langchain_community.embeddings import (
     HuggingFaceEmbeddings,
     CohereEmbeddings,
     HuggingFaceInstructEmbeddings,
 )
+from langchain_openai import OpenAIEmbeddings
 from application.core.settings import settings
 
 class BaseVectorStore(ABC):
@@ -46,7 +46,7 @@ class BaseVectorStore(ABC):
             )
         elif embeddings_name == "huggingface_sentence-transformers/all-mpnet-base-v2":
             embedding_instance = embeddings_factory[embeddings_name](
-                model_name="./model/all-mpnet-base-v2",
+                #model_name="./model/all-mpnet-base-v2",
                 model_kwargs={"device": "cpu"},
             )
         else:

application/vectorstore/faiss.py

@@ -1,4 +1,4 @@
-from langchain.vectorstores import FAISS
+from langchain_community.vectorstores import FAISS
 from application.vectorstore.base import BaseVectorStore
 from application.core.settings import settings
 

scripts/code_docs_gen.py

@@ -3,7 +3,7 @@ import json
 from pathlib import Path
 
 import dotenv
-from langchain.llms import OpenAI
+from langchain_community.llms import OpenAI
 from langchain.prompts import PromptTemplate
 
 dotenv.load_dotenv()

scripts/old/ingest_rst.py

@@ -6,7 +6,7 @@ from pathlib import Path
 import dotenv
 import faiss
 import tiktoken
-from langchain.embeddings import OpenAIEmbeddings
+from langchain_openai import OpenAIEmbeddings
 from langchain.text_splitter import CharacterTextSplitter
 from langchain.vectorstores import FAISS
 

scripts/old/ingest_rst_sphinx.py

@@ -8,7 +8,7 @@ from pathlib import Path
 import dotenv
 import faiss
 import tiktoken
-from langchain.embeddings import OpenAIEmbeddings
+from langchain_openai import OpenAIEmbeddings
 from langchain.text_splitter import CharacterTextSplitter
 from langchain.vectorstores import FAISS
 from sphinx.cmd.build import main as sphinx_main

scripts/parser/file/bulk.py

@@ -61,7 +61,6 @@ class SimpleDirectoryReader(BaseReader):
             file_extractor: Optional[Dict[str, BaseParser]] = None,
             num_files_limit: Optional[int] = None,
             file_metadata: Optional[Callable[[str], Dict]] = None,
-            chunk_size_max: int = 2048,
     ) -> None:
         """Initialize with parameters."""
         super().__init__()

scripts/parser/open_ai_func.py

@@ -1,8 +1,8 @@
 import os
 
 import tiktoken
-from langchain.embeddings import OpenAIEmbeddings
-from langchain.vectorstores import FAISS
+from langchain_openai import OpenAIEmbeddings
+from langchain_community.vectorstores import FAISS
 from retry import retry
 
 

scripts/parser/py2doc.py

@@ -3,7 +3,7 @@ import os
 from pathlib import Path
 
 import tiktoken
-from langchain.llms import OpenAI
+from langchain_community.llms import OpenAI
 from langchain.prompts import PromptTemplate
 
 

scripts/requirements.txt

@@ -1,145 +1,22 @@
-aiodns==3.1.1
-aiohttp==3.9.1
-aiohttp-retry==2.8.3
-aiosignal==1.3.1
-amqp==5.2.0
-annotated-types==0.6.0
-anthropic==0.8.0
-anyio==4.2.0
-async-timeout==4.0.3
-attrs==23.1.0
-billiard==4.2.0
-blinker==1.7.0
-blobfile==2.1.1
-boto3==1.34.6
-botocore==1.34.6
-celery==5.3.6
-certifi==2023.11.17
-cffi==1.16.0
-chardet==5.2.0
-charset-normalizer==3.3.2
-click==8.1.7
-click-didyoumean==0.3.0
-click-plugins==1.1.1
-click-repl==0.3.0
-cryptography==41.0.7
-dataclasses-json==0.6.3
-decorator==5.1.1
-dill==0.3.7
-distro==1.8.0
-dnspython==2.4.2
+dataclasses_json==0.6.3
 docx2txt==0.8
-ecdsa==0.18.0
-elastic-transport==8.11.0
-elasticsearch==8.11.1
-entrypoints==0.4
-faiss-cpu==1.7.4
-filelock==3.13.1
-Flask==3.0.0
-Flask-Cors==4.0.0
-frozenlist==1.4.1
-fsspec==2023.12.2
-geojson==2.5.0
-greenlet==3.0.3
-gunicorn==21.2.0
-h11==0.14.0
-httpcore==1.0.2
-httpx==0.26.0
-huggingface-hub==0.20.1
-humbug==0.3.2
-idna==3.6
-iniconfig==2.0.0
-itsdangerous==2.1.2
-Jinja2==3.1.2
-jmespath==1.0.1
-joblib==1.3.2
-jsonpatch==1.33
-jsonpointer==2.4
-kombu==5.3.4
-langchain==0.0.352
-langchain-community==0.0.6
-langchain-core==0.1.3
-langsmith==0.0.74
-lazy-object-proxy==1.10.0
-loguru==0.7.2
-lxml==4.9.4
-MarkupSafe==2.1.3
-marshmallow==3.20.1
-marshmallow-enum==1.5.1
-mpmath==1.3.0
-multidict==6.0.4
-multiprocess==0.70.15
-mypy-extensions==1.0.0
-networkx==3.2.1
+EbookLib==0.18
+escodegen==1.0.11
+esprima==4.0.1
+faiss_cpu==1.7.4
+html2text==2020.1.16
+javalang==0.13.0
+langchain==0.1.4
+langchain_community==0.0.16
+langchain-openai==0.0.5
 nltk==3.8.1
-npx==0.1.1
-numcodecs==0.12.1
-numpy==1.26.2
-openai==1.6.1
-openapi-schema-validator==0.6.2
-openapi-spec-validator==0.6.0
-openapi3-parser==1.1.16
-packaging==23.2
-pathable==0.4.3
-pathos==0.3.1
-Pillow==10.1.0
-pluggy==1.3.0
-pox==0.3.3
-ppft==1.7.6.7
-prance==23.6.21.0
-prompt-toolkit==3.0.43
-pyasn1==0.5.1
-pycares==4.4.0
-pycparser==2.21
-pycryptodome==3.19.0
-pycryptodomex==3.19.0
-pydantic==2.5.3
-pydantic_core==2.14.6
-pydantic_settings==2.1.0
-PyJWT==2.8.0
-pymongo==4.6.1
-pyowm==3.3.0
+openapi3_parser==1.1.16
+pandas==2.2.0
 PyPDF2==3.0.1
-PySocks==1.7.1
-pytest==7.4.3
-python-dateutil==2.8.2
-python-dotenv==1.0.0
-python-jose==3.3.0
-python-liquid==1.10.2
-pytz==2023.3.post1
-PyYAML==6.0.1
-redis==5.0.1
-regex==2023.10.3
-requests==2.31.0
+python-dotenv==1.0.1
 retry==0.9.2
-rfc3339-validator==0.1.4
-rpds-py==0.15.2
-rsa==4.9
-ruamel.yaml==0.18.5
-ruamel.yaml.clib==0.2.8
-s3transfer==0.10.0
-safetensors==0.4.1
-scikit-learn==1.3.2
-scipy==1.11.4
-sentence-transformers
-sentencepiece==0.1.99
-six==1.16.0
-sniffio==1.3.0
-SQLAlchemy==2.0.23
-sympy==1.12
-tenacity==8.2.3
-threadpoolctl==3.2.0
-tiktoken
-tokenizers==0.15.0
-torch==2.1.2
-torchvision==0.16.2
+Sphinx==7.2.6
+tiktoken==0.5.2
 tqdm==4.66.1
-transformers==4.36.2
 typer==0.9.0
-typing-inspect==0.9.0
-typing_extensions==4.9.0
-tzdata==2023.3
-vine==5.1.0
-wcwidth==0.2.12
-Werkzeug==3.0.1
-yarl==1.9.4
+unstructured==0.12.2