Commit Graph

  • e2d7bd3902 Merge branch 'main' into docs-init NirantK 2023-08-21 17:58:11 +05:30
  • 0d6f313f30 * feat(docs): add initial documentation files * feat(docs): add override for main.html template NirantK 2023-08-21 17:51:29 +05:30
  • 49aa267d05 * feat(ci.yml): add CI workflow for continuous integration * * This commit adds a new file .github/workflows/ci.yml which contains the configuration for the CI workflow. The workflow is triggered on push events to the master and main branches. It runs on an Ubuntu environment and consists NirantK 2023-08-21 17:51:19 +05:30
  • ee0e6a0011 * feat(mkdocs.yml): add mkdocs.yml configuration file with site name, theme, and markdown extensions NirantK 2023-08-21 17:51:13 +05:30
  • 7c13395c96 * chore(pyproject.toml): add mkdocs-material as a dev dependency NirantK 2023-08-21 17:29:49 +05:30
  • 4a381e03b9 Merge pull request #1 from qdrant/refactoring Nirant 2023-08-18 14:35:25 +05:30
  • 770beb1023 refactoring generall 2023-08-18 01:36:36 +02:00
  • 29834997ad * feat(02_Usage.ipynb): update examples * feat(02_Usage.ipynb): add comment to clarify casting generator to a list NirantK 2023-08-17 16:36:55 +05:30
  • 52d03a3db3 * chore(02_Usage.ipynb): update notebook with installation of fastembed package NirantK 2023-08-17 16:35:34 +05:30
  • bc9416aad1 Refactor for readability NirantK 2023-08-17 12:48:19 +05:30
  • 6d33b85f37 * chore(.gitignore): add missing newline at the end of the file * chore(.gitignore): add nbs/fast-*/* to the ignore list NirantK 2023-08-17 12:47:36 +05:30
  • a664dfffd2 * docs(README.md): add details about the lightness of FastEmbed library * docs(README.md): mention accuracy/recall performance of FastEmbed library compared to OpenAI Ada-002 NirantK 2023-08-17 12:47:27 +05:30
  • ae86299ede * feat(01_ONNX_Port.ipynb): update input_texts with sample queries and passages NirantK 2023-08-17 12:15:56 +05:30
  • a2a83a772b *chore: Cleanup imports NirantK 2023-08-17 12:08:38 +05:30
  • 5b213ce75b * chore(pyproject.toml): update onnx version to 1.11.0 * feat(pyproject.toml): add notebook dependency with version >=7.0.2 NirantK 2023-08-17 10:47:55 +05:30
  • 7b1f1b5989 * feat(pyproject.toml): add onnx to dev dependency NirantK 2023-08-17 10:40:49 +05:30
  • d507f20c1d * feat(pyproject.toml): add optimum dependency NirantK 2023-08-17 10:39:29 +05:30
  • e7a002f8dd Add Accurate and Fast Nirant 2023-08-17 10:36:20 +05:30
  • 9fb7c0678f Update README.md Nirant 2023-08-17 10:32:29 +05:30
  • 1ba8f79ff8 * chore(pyproject.toml): update version to 0.0.2 and description to "Fast, State of the Art Quantized Embedding Models" NirantK 2023-08-16 18:49:45 +05:30
  • ff1936545c * feat(02_Usage.ipynb): add notebook file for usage examples NirantK 2023-08-16 17:28:00 +05:30
  • f7a3254ce4 * refactor(embedding.py): remove print statement for decompression message * fix(embedding.py): add default value for onnx_providers parameter in FlagEmbedding constructor NirantK 2023-08-16 17:27:52 +05:30
  • aaf1aacf15 poetry lock fix NirantK 2023-08-16 17:27:41 +05:30
  • 3f2c96a6e8 * chore(pyproject.toml): remove sentence-transformers and pre-commit dependencies * feat(pyproject.toml): add onnxruntime-silicon dependency NirantK 2023-08-10 22:05:12 +05:30
  • 6fca49781e * feat(embedding.py): add download_file_from_gcs method with documentation NirantK 2023-08-10 22:01:41 +05:30
  • 4ea33a7140 * docs(embedding.py): add docstring for decompress_to_cache method * docs(embedding.py): add docstring for FlagEmbedding class constructor NirantK 2023-08-10 21:49:58 +05:30
  • c2927becce * chore(qdrant_client.py): remove unused qdrant_client.py file NirantK 2023-08-10 21:40:53 +05:30
  • d32d45c39b * fix(embedding.py): add missing comma after max_length parameter in DefaultEmbedding constructor NirantK 2023-08-10 21:40:27 +05:30
  • fa3fc08528 * refactor(embedding.py): remove unused SentenceTransformersEmbedding class * feat(embedding.py): add NotImplementedError to abstract method encode() in Embedding class NirantK 2023-08-10 21:39:59 +05:30
  • 7eba8cb187 * feat(embedding.py): add DefaultEmbedding class as a subclass of FlagEmbedding * fix(embedding.py): fix indentation in DefaultEmbedding class constructor NirantK 2023-08-10 21:39:33 +05:30
  • 0537e80d35 * fix(embedding.py): fix linting issues and add FlagEmbedding class for handling flag embeddings * feat(embedding.py): add support for flag-based embeddings using ONNX models NirantK 2023-08-10 21:39:10 +05:30
  • 809c60bcc9 * refactor(embedding.py): remove unnecessary cache_dir initialization in DefaultEmbedding constructor * feat(embedding.py): add optional cache_dir parameter to decompress_to_cache method NirantK 2023-08-10 19:19:41 +05:30
  • c9b0811b57 * chore(.gitignore): add nbs/local_cache/*/* and local_cache/*/* to ignore list NirantK 2023-08-10 19:19:28 +05:30
  • 3ec012a17e * refactor(embedding.py): remove unused import of tempfile NirantK 2023-08-10 19:15:03 +05:30
  • 8ede18cc6e * fix(embedding.py): change cache directory path from using tempfile.gettempdir() to using a local_cache directory in the current working directory * refactor(embedding.py): remove unnecessary check for cache directory existence and creation, as it is already handled by the mkdir() method NirantK 2023-08-10 19:13:26 +05:30
  • 1f403f9a2c * chore(embedding.py): fix indentation in ONNXProviders class * fix(embedding.py): change default onnx_providers value to [ONNXProviders.CPU] * fix(embedding.py): raise PermissionError with specific error message when encountering 403 status code NirantK 2023-08-10 19:07:34 +05:30
  • 0b14ed84b7 * chore(embedding.py): update GPU support comment in ONNXProviders class NirantK 2023-08-10 10:56:06 +05:30
  • a917a5f202 * fix(embedding.py): change default model_name from "BAAI/bge-base-en" to "BAAI/bge-small-en" NirantK 2023-08-10 10:56:00 +05:30
  • 4adb430bb2 * fix(embedding.py): change batch_size default value from 32 to 256 * chore(embedding.py): add TODO comment about normalizing embeddings after all batches are done NirantK 2023-08-10 10:50:11 +05:30
  • 98e95e8af6 * reformat NirantK 2023-08-10 10:47:14 +05:30
  • 5b46cb81e3 * refactor(embedding.py): Remove unused imports and fix typing import * fix(qdrant_mixin.py): Fix syntax error in dict() method call * chore(speculative.py): Remove speculative.py file NirantK 2023-08-10 10:46:13 +05:30
  • f01a778638 * refactor(embedding.py): Remove GeneralTextEmbedding class from embedding.py * feat(speculative.py): Add GeneralTextEmbedding class to speculative.py NirantK 2023-08-10 10:45:34 +05:30
  • 11734b2e8b * feat(embedding.py): add docstring to the encode method explaining its functionality NirantK 2023-08-10 10:44:50 +05:30
  • 8e876dd330 * fix(embedding.py): fix model_name format assertion error * feat(embedding.py): add support for custom model names and download from GCS using the model name * refactor(embedding.py): refactor tokenizer and model initialization to use max_length and onnx_providers variables NirantK 2023-08-10 10:44:19 +05:30
  • 885a738751 * feat(embedding.py): add support for custom model name, onnx providers, and max length in DefaultEmbedding constructor NirantK 2023-08-10 10:43:50 +05:30
  • 6cce4e0b9a * chore(01_ONNX_Port.ipynb): clean up notebook formatting and imports * feat(01_ONNX_Port.ipynb): add imports for pipeline and ONNX-related modules NirantK 2023-08-10 10:43:18 +05:30
  • 17d05087ef * chore(usage.py): remove unused usage.py file NirantK 2023-08-10 10:42:37 +05:30
  • 63581a0a56 * chore(dev-requirements.txt): add google-cloud-storage to dev requirements NirantK 2023-08-10 10:42:30 +05:30
  • 4bfd5a13e1 * chore(embedding.py): add ONNXProviders class with CPU, GPU, and Metal execution providers * feat(embedding.py): add DefaultEmbedding class with model_name parameter NirantK 2023-08-10 10:42:21 +05:30
  • bc8e160657 * chore(dev-requirements.txt): add dev dependencies for jupyter, jupyter_nbextensions_configurator, black[jupyter], isort, and ruff NirantK 2023-08-05 16:40:54 +05:30
  • 0721f6a447 * chore(embedding.py): set default logger severity to ERROR level NirantK 2023-08-03 13:25:57 +05:30
  • b353a1d7e1 * fix(qdrant_client.py): change import statement from QdrantClientMixin to QdrantAPIExtensions * fix(qdrant_mixin.py): change class name from QdrantClientMixin to QdrantAPIExtensions * fix(qdrant_mixin.py): change method name NirantK 2023-08-03 13:03:48 +05:30
  • a0a57c3387 * chore: reformat with black NirantK 2023-08-03 13:02:33 +05:30
  • 63979dedb7 * chore(pyproject.toml): update project version to 0.0.1 and description to "Fast Embedding Creation and Simpler API for Qdrant" * docs(pyproject.toml): update homepage and repository URLs * feat(pyproject.toml): add "sentence-transformers" NirantK 2023-07-31 17:37:57 +05:30
  • 0a861ba5e1 * chore(pyproject.toml): update version from 0.0.1.alpha2 to 0.0.1.alpha3 NirantK 2023-07-31 16:48:23 +05:30
  • 1c684b1208 * chore(.gitignore): add *.tar.gz to the list of ignored files NirantK 2023-07-31 16:42:45 +05:30
  • 6c0be8b9d1 * fix(embedding.py): fix method signature of download_file_from_gcs to include self parameter * fix(embedding.py): fix method signature of decompress_to_cache to include self parameter * fix(embedding.py): update path handling in DefaultEmbedding's __init__ method NirantK 2023-07-31 16:42:18 +05:30
  • 538c63d2ee * chore(qdrant_mixin.py): refactor QdrantClientMixin to use DefaultEmbedding instead of SentenceTransformersEmbedding NirantK 2023-07-31 16:28:32 +05:30
  • 81956c371b * chore(embedding.py): add normalize function for division by zero * fix(embedding.py): remove print statement NirantK 2023-07-31 16:28:26 +05:30
  • 36e276fa8b * feat(embedding.py): add support for tokenization and encoding of documents using the model * chore(pyproject.toml): add tokenizers as a dependency NirantK 2023-07-31 16:27:39 +05:30
  • f2e711eeda * fix(embedding.py): add type hinting to the encode method in the Embedding class NirantK 2023-07-31 16:26:53 +05:30
  • bb01f26031 * feat(embedding.py): add import statements for os, shutil, tarfile, tempfile, typing, requests, tqdm NirantK 2023-07-31 16:10:51 +05:30
  • 7a23c6a25d * chore(.gitignore): add nbs/*.tar.gz to ignore list NirantK 2023-07-31 16:10:42 +05:30
  • 247a03fe62 * feat(embedding.py): add DefaultEmbedding class with methods for downloading file from GCS and decompressing to cache * fix(embedding.py): fix missing self parameter in DefaultEmbedding class methods NirantK 2023-07-31 16:10:35 +05:30
  • c1048b5e38 * feat(embedding.py): add GeneralTextEmbedding class for SoTA text embedding model * fix(embedding.py): fix average_pool method signature in GeneralTextEmbedding class NirantK 2023-07-31 16:10:13 +05:30
  • 31b0f6e929 * refactor(ONNX_Port.ipynb): rename notebook file from ONNX_Port.ipynb to 01_ONNX_Port.ipynb * chore(ONNX_Port.ipynb): comment out timeit magic command in code cells NirantK 2023-07-31 16:07:52 +05:30
  • 2746ebbdca * chore(pyproject.toml): add tqdm and requests dependencies NirantK 2023-07-31 16:06:04 +05:30
  • 1640e6f40e * chore(.gitignore): add .DS_Store to the ignore list NirantK 2023-07-31 13:52:42 +05:30
  • 58d88b923a * feat(ONNX_Port.ipynb): add notebook for ONNX porting process * chore(ONNX_Port.ipynb): remove unnecessary commented code NirantK 2023-07-31 13:52:35 +05:30
  • caf2c28d7d * chore(pyproject.toml): update version from 0.0.1.alpha1 to 0.0.1.alpha2 NirantK 2023-07-31 13:51:44 +05:30
  • 6500bd06ac * refactor(embedding.py): Rename fastvector directory to fastembed * refactor(qdrant_client.py): Rename fastvector directory to fastembed * refactor(qdrant_mixin.py): Rename fastvector directory to fastembed NirantK 2023-07-17 14:59:59 +05:30
  • b7a21ef713 * chore(README.md): change library name from FastVector to FastEmbed * docs(README.md): update installation instructions to use FastEmbed instead of FastVector NirantK 2023-07-17 14:59:46 +05:30
  • e3e310d73c * chore(pyproject.toml): update project name from "fastvector" to "fastembed" * chore(pyproject.toml): update version from "0.0.1" to "0.0.1.alpha1" NirantK 2023-07-17 14:59:38 +05:30
  • c9a21837da * chore(usage.py): update metadata source from "Linkedin-docs" to "LlamaIndex-docs" NirantK 2023-07-13 08:56:31 +05:30
  • 4a368f89b5 * chore(pyproject.toml): remove qdrant-client dependency NirantK 2023-07-13 08:56:24 +05:30
  • fc46684d0c * chore(README.md): clean up and reformat code examples in README.md * feat(README.md): update metadata sources in example code NirantK 2023-07-12 19:42:04 +05:30
  • 9638de0a40 * chore(usage.py): remove unused code and comments * feat(usage.py): update add method to remove batch_size and wait parameters * feat(usage.py): update query method to remove n_results parameter NirantK 2023-07-12 19:41:58 +05:30
  • 67c2e1838e Lockfile updates NirantK 2023-07-12 19:14:50 +05:30
  • 5c61ff5347 * chore(pyproject.toml): update python dependency version to >=3.8.0,<3.12 * feat(pyproject.toml): add packages, homepage, repository, and keywords NirantK 2023-07-12 19:14:34 +05:30
  • 23e16b5498 * chore(pyproject.toml): remove empty lines NirantK 2023-07-12 19:08:37 +05:30
  • 0b15cee945 * refactor(pyproject.toml): update dependencies and create dev-dependencies * feat(pyproject.toml): add onnxruntime-silicon as a dependency with macOS specific marker NirantK 2023-07-12 19:08:17 +05:30
  • 3e36f1fde4 * refactor(qdrant_mixin.py): remove unused import statement * refactor(qdrant_mixin.py): remove warning message when creating collection NirantK 2023-07-12 19:07:59 +05:30
  • 16a05c561d * docs(README.md): update installation instructions to include Qdrant client installation NirantK 2023-07-12 18:50:14 +05:30
  • 1f59b7c494 * chore(README.md): add installation and usage instructions * feat(README.md): add features section NirantK 2023-07-12 18:48:36 +05:30
  • f0162731dd * fix(qdrant_mixin.py): make embeddings field in QueryResponse optional * feat(qdrant_mixin.py): add with_payload parameter to QdrantClientMixin.search method * fix(usage.py): remove with_vectors and with_payload parameters from client.query method NirantK 2023-07-12 18:47:12 +05:30
  • 6e2b7c8bb3 * fix(qdrant_mixin.py): change method call from create_collection to recreate_collection * fix(qdrant_mixin.py): change method call from recreate_collection to create_collection * fix(usage.py): change method call from add to upsert_docs NirantK 2023-07-12 18:37:42 +05:30
  • 0d15e14886 * chore(usage.py): update document IDs in the ids list * docs(usage.py): add usage of the upsert_docs method NirantK 2023-07-12 18:36:39 +05:30
  • 334221ae54 * refactor(qdrant_mixin.py): remove unused imports, explicit imports from http.models NirantK 2023-07-12 18:35:44 +05:30
  • fd44f7fd22 * chore(qdrant_mixin.py): remove unused code in search_docs method * feat(qdrant_mixin.py): add aliases for add and query methods NirantK 2023-07-12 18:27:25 +05:30
  • b85bcf0203 * fix(usage.py): change method name from upsert_docs to add in client method call NirantK 2023-07-12 18:27:17 +05:30
  • dbfb70290c * chore(qdrant_mixin.py): add aliases for the upsert_docs and search_docs methods NirantK 2023-07-12 18:27:04 +05:30
  • 0f513b3f61 * feat(qdrant_mixin.py): add docstring and update default values for search_params and embedding_model in the search method NirantK 2023-07-12 18:25:25 +05:30
  • a05723ec40 * fix(qdrant_mixin.py): rename query method to search_docs for clarity and consistency NirantK 2023-07-12 18:23:26 +05:30
  • a789766574 * feat(qdrant_mixin.py): add docstring to the constructor of QdrantClientMixin class NirantK 2023-07-12 18:23:14 +05:30
  • 1c683d6a17 * fix(qdrant_mixin.py): change default value of embedding_model parameter from None to SentenceTransformersEmbedding NirantK 2023-07-12 18:23:05 +05:30
  • 81dcb3ae05 * chore(usage.py): update comment to clarify the behavior of the ids list * fix(usage.py): change comment to reflect that random IDs can lead to duplicates NirantK 2023-07-12 16:49:38 +05:30
  • d077bcb67f * refactor(qdrant_mixin.py): remove unused variable 'n' in QdrantClientMixin class NirantK 2023-07-12 16:48:42 +05:30
  • 71549ac299 * refactor(qdrant_mixin.py): refactor QdrantClientMixin's search method to return QueryResponse objects instead of a list of dictionaries NirantK 2023-07-12 16:48:29 +05:30
  • d4e62fcf57 * refactor(qdrant_mixin.py): refactor search functionality to support batch processing of query texts * fix(qdrant_mixin.py): fix variable name in loop to iterate over query_texts_batch NirantK 2023-07-12 16:47:51 +05:30
  • e65b2256d2 * feat(qdrant_mixin.py): add batch_iterable method to QdrantClientMixin class * fix(qdrant_mixin.py): fix typo in method name, change "upsert_docs" to "upsert_documents" NirantK 2023-07-12 16:47:20 +05:30