ai-parrot 0.3.10__cp311-cp311-manylinux_2_28_x86_64.whl → 0.3.11__cp311-cp311-manylinux_2_28_x86_64.whl

{ai_parrot-0.3.10.dist-info → ai_parrot-0.3.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ai-parrot
-Version: 0.3.10
+Version: 0.3.11
 Summary: Live Chatbots based on Langchain chatbots and Agents     Integrated into Navigator Framework or used into aiohttp applications.
 Home-page: https://github.com/phenobarbital/ai-parrot
 Author: Jesus Lara
@@ -131,6 +131,8 @@ Requires-Dist: ftfy==6.2.3; extra == "loaders"
 Requires-Dist: librosa==0.10.1; extra == "loaders"
 Requires-Dist: XlsxWriter==3.2.0; extra == "loaders"
 Requires-Dist: timm==1.0.9; extra == "loaders"
+Requires-Dist: simsimd==4.3.1; extra == "loaders"
+Requires-Dist: opencv-python==4.10.0.84; extra == "loaders"
 Requires-Dist: easyocr==1.7.1; extra == "loaders"
 Provides-Extra: milvus
 Requires-Dist: langchain-milvus>=0.1.4; extra == "milvus"

{ai_parrot-0.3.10.dist-info → ai_parrot-0.3.11.dist-info}/RECORD

@@ -4,7 +4,7 @@ parrot/exceptions.cpython-311-x86_64-linux-gnu.so,sha256=VNyBh3uLxGQgB0l1bkWjQDq
 parrot/manager.py,sha256=NhzXoWxSgtoWHpmYP8cV2Ujq_SlvCbQYQBaohAeL2TM,5935
 parrot/models.py,sha256=RsVQCqhSXBKRPcu-BCga9Y1wyvENFXDCuq3_ObIKvAo,13452
 parrot/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-parrot/version.py,sha256=HoNVx3mljjW-CBZ6CYPJUMxrG6X1SETBEn5g7YQTv4g,374
+parrot/version.py,sha256=iXWwg_05dEqR8n13PRWz5QqlmSq6_og3HT3moP37RAg,374
 parrot/chatbots/__init__.py,sha256=ypskCnME0xUv6psBEGCEyXCrD0J0ULHSllpVmSxqb4A,200
 parrot/chatbots/abstract.py,sha256=CmDn3k4r9uKImOZRN4L9zxLbCdC-1MPUAorDlfZT-kA,26421
 parrot/chatbots/asktroc.py,sha256=gyWzyvpAnmXwXd-3DEKoIJtAxt6NnP5mUZdZbkFky8s,604
@@ -47,40 +47,40 @@ parrot/llms/pipes.py,sha256=Ns_wh-alkKocZKlbQyQLKOSBxqfRC_hCbz34vpOOyP8,3798
 parrot/llms/vertex.py,sha256=a0UsH9sa_GiMkg31E52cWE8pXFZjyMtIanr7eAA7iyE,2615
 parrot/loaders/__init__.py,sha256=LGEaj54DP3FA5-C2IDaA8u-MF4lj-Lbd_Mx5R19qHYY,665
 parrot/loaders/abstract.py,sha256=_tsGDb7TracwkL20J2VYd5hC9MR262c2mmS9VvYB4vM,15870
-parrot/loaders/audio.py,sha256=0yF5hOgCgjRFjOrYfYfS9kJ5j63J72QD0xHTiaer9Eo,3694
+parrot/loaders/audio.py,sha256=P2tWYKxWLM5TMLMm-5qR35cD_pGQWmf8-UZUTiK4R0o,3698
 parrot/loaders/basepdf.py,sha256=Qh_hzR0JArQEVP31SgWt9utt7qWmbfwVoCzUDyBHcXw,3243
 parrot/loaders/basevideo.py,sha256=WcX-q0Rn_E1dYurbA1eH5NOcUBdOye2iWiFTCY_DVgo,10292
 parrot/loaders/csv.py,sha256=DLcFK3z9boMNH3y9Qca5BWDfYXgXjXsGkzxVN1_2wyo,1103
 parrot/loaders/dir.py,sha256=_CU9kWGCpHnZplUamXLs2yEizA1aCRBASn3F6MggitQ,866
-parrot/loaders/excel.py,sha256=Y1agxm-jG4AgsA2wlPP3p8uBH40wYW1KM2ycTTLKUm4,12441
+parrot/loaders/excel.py,sha256=9cTsMfxR_YOpBHz9Ru0LJsxBXDVBh52XM8hHV63QgYo,12445
 parrot/loaders/github.py,sha256=CscyUIqoHTytqCbRUUTcV3QSxI8XoDntq5aTU0vdhzQ,2593
 parrot/loaders/image.py,sha256=A9KCXXoGuhDoyeJaascY7Q1ZK12Kf1ggE1drzJjS3AU,3946
 parrot/loaders/json.py,sha256=6B43k591OpvoJLbsJa8CxJue_lAt713SCdldn8bFW3c,1481
-parrot/loaders/pdf.py,sha256=YnWXFVJjT76cGcRclAKHmFPeMt7SXAuqywIt0UMI9P4,20722
-parrot/loaders/pdfchapters.py,sha256=YhA8Cdx3qXBR0vuTVnQ12XgH1DXT_rp1Tawzh4V2U3o,5637
-parrot/loaders/pdffn.py,sha256=gA-vJEWUiIUwbMxP8Nmvlzlcb39DVV69vGKtSzavUoI,4004
-parrot/loaders/pdfimages.py,sha256=4Q_HKiAee_hALBsG2qF7PpMgKP1AivHXhmcsCkUa9eE,7899
-parrot/loaders/pdfmark.py,sha256=LG_Vh-Py7RnLkQfmt0_2kWc1J6GpxB6f_jzUE0fsZ98,2956
-parrot/loaders/pdftables.py,sha256=XSanrv40IstQVe5_zOPcPrVH_v0scrdMShOYGgiedmc,4767
+parrot/loaders/pdf.py,sha256=FWeBznFsnBaCwfBEFG64kieDX1C-05ephMNooK6euuE,20730
+parrot/loaders/pdfchapters.py,sha256=YhaURiggOFYmJBL6BL8wutGKV6G0hEcFxvK7v91uQc8,5639
+parrot/loaders/pdffn.py,sha256=BXYPxSCe7Dc-35sHB4BXMZMoAHIPvzCPEubEQu1CqaI,4006
+parrot/loaders/pdfimages.py,sha256=DMI_dWxLRN9aWGiZg4TfQCFLQgfk8K__Z3nS7ng8mcE,7903
+parrot/loaders/pdfmark.py,sha256=HLAgaFcKeHZzQXMAIq0NjNfi69elHPpEgX6chY381VI,2958
+parrot/loaders/pdftables.py,sha256=kbslZp97V8wiesNdKf_4pR-KHSH4mtZsIPkFmz8UKzY,4769
 parrot/loaders/ppt.py,sha256=6XailMQeQBFMzaSCvNJTHtfpzunTJRatytGT6o3v8-c,832
-parrot/loaders/qa.py,sha256=l8Nif3x85TJvNVQsY5XbHB_zrv-PeeytR0OXefAV4lk,2644
+parrot/loaders/qa.py,sha256=3K_2yBxUzj-ifDpAbUsIc-v66004fKPzGavUqrhc3Kc,2646
 parrot/loaders/repo.py,sha256=vBqBAnwU6p3_DCvI9DVhi1Bs8iCDYHwFGp0P9zvGRyw,3737
-parrot/loaders/rtd.py,sha256=oKOC9Qn3iwulYx5BEvXy4_kusKRsy5RLYNHS-e5p-1k,1988
-parrot/loaders/txt.py,sha256=AeGroWffFT--7TYlTSTr5Av5zAr8YIp1fxt8r5qdi-A,2802
+parrot/loaders/rtd.py,sha256=O0h7LDntP_0IBT8LDQi09u-gYVUO5cuvmGsfZLZ4CoU,1990
+parrot/loaders/txt.py,sha256=-xXVSuvkC2LQ2XZ44Nqwk3V8nE4F6UgXylosMCNgeFo,2804
 parrot/loaders/video.py,sha256=pl5Ho69bp5vrWMqg5tLbsnHUus1LByTDoL6NPk57Ays,2929
-parrot/loaders/videolocal.py,sha256=LKtP8YVlI_RWiXi6wYew3_ZB2Up8d8LXlWWDdgU1s7k,5139
-parrot/loaders/vimeo.py,sha256=zOvOOIiaZr_bRswJFI7uIMKISgALOxcSim9ZRUFY1Fc,4114
-parrot/loaders/web.py,sha256=3x06JNpfTGFtvSBPAEBVoVdZkpVXePcJeMtj61B2xJk,8867
-parrot/loaders/web_base.py,sha256=5SjQddT0Vhne8C9s30iU3Ex_9O1PJ8kyDmy8EdhGBo0,4380
-parrot/loaders/word.py,sha256=9rIb1cHWDVTSUqUpwxjwP6lkCEJlEUaH8G6Y86qZ7do,4531
-parrot/loaders/youtube.py,sha256=yNilbmuQs_eeT6eNkvaqLqc6yYu9LvZx-3jMvvGlpZw,7743
+parrot/loaders/videolocal.py,sha256=NwFB6n9sQZxh01L6YKIISpG1tuRsg-ME_qXCDS7Vtkk,5143
+parrot/loaders/vimeo.py,sha256=Cs7FkL2Cr8yV44-Tv5wWkveKzqhOeAIP6kF93SCr_Lk,4118
+parrot/loaders/web.py,sha256=kTi-NtAsbQLKi3wD_2o15Z0HHnYzsEEEGjH0RdvyQqQ,8869
+parrot/loaders/web_base.py,sha256=ZwSFXtJR71cpFGN1WCLUC2W6JjEUV865tRKf8isbJ5M,4382
+parrot/loaders/word.py,sha256=jZdHSL5CtAEn1otBYLNSqKLtO3BNcTObDPgqhzk5-4M,4533
+parrot/loaders/youtube.py,sha256=fVnBBw4IfK6NWP7mO66TgxOzJEcGwE3-3S1WMUApJYg,7751
 parrot/loaders/handlers/__init__.py,sha256=ksEDtUOEJELmyCIi0KNv7tR2fCUyADBVkwCcyqN_sVE,70
 parrot/loaders/handlers/data.py,sha256=olZ2p-wyUMGoazah7tgHY7V9buGX1FOeJ-cv2vGEoH8,7386
 parrot/loaders/utils/__init__.py,sha256=SkDyK3MuPGhp0NM6kHvaxQDe97Gcl3n9t5A741OVh1c,28
 parrot/loaders/utils/models.py,sha256=BHcnFzS7oOKUGG-vPy_TlqeFNAC8puRgsIMX2mSgKxY,1059
 parrot/stores/__init__.py,sha256=ZFjZvcLhcqJqndx9tiEANpyiude1fvjrCxyt2S42VqY,1496
 parrot/stores/abstract.py,sha256=aqDhkVr5VwdKqg7StroIXf32-11MLyyMAlZuh5hJeCY,5138
-parrot/stores/milvus.py,sha256=iRi1dO7kathwep3iLIMIDtAkljc-zETUzON4E0wsrYs,20596
+parrot/stores/milvus.py,sha256=r1PiIf3uFE84l1OeGb_-2oEf09mbu8truY5e6wsDv7I,20606
 parrot/stores/qdrant.py,sha256=y-jG5sB6ICESyxdpyGBhQ-hgTDLxxPtM5xYZTWIRiAY,4720
 parrot/tools/__init__.py,sha256=XKZwogdGr6ObPfAGbzAdyDjFnXI286eapsi180VwdjE,614
 parrot/tools/abstract.py,sha256=pVSZw8MDpbVcQ-CHaGwP6CpqXHIs8hH8Oy1AqUuMmrw,1706
@@ -103,8 +103,8 @@ resources/users/handlers.py,sha256=BGzqBvPY_OaIF_nONWX4b_B5OyyBrdGuSihIsdlFwjk,2
 resources/users/models.py,sha256=glk7Emv7QCi6i32xRFDrGc8UwK23_LPg0XUOJoHnwRU,6799
 settings/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 settings/settings.py,sha256=9ueEvyLNurUX-AaIeRPV8GKX1c4YjDLbksUAeqEq6Ck,1854
-ai_parrot-0.3.10.dist-info/LICENSE,sha256=vRKOoa7onTsLNvSzJtGtMaNhWWh8B3YAT733Tlu6M4o,1070
-ai_parrot-0.3.10.dist-info/METADATA,sha256=Kq5FpMgf-M5vRQ9gNDNyqWCOL_3SrMB6hTsnxWW9Gbg,9728
-ai_parrot-0.3.10.dist-info/WHEEL,sha256=UQ-0qXN3LQUffjrV43_e_ZXj2pgORBqTmXipnkj0E8I,113
-ai_parrot-0.3.10.dist-info/top_level.txt,sha256=qHoO4BhYDfeTkyKnciZSQtn5FSLN3Q-P5xCTkyvbuxg,26
-ai_parrot-0.3.10.dist-info/RECORD,,
+ai_parrot-0.3.11.dist-info/LICENSE,sha256=vRKOoa7onTsLNvSzJtGtMaNhWWh8B3YAT733Tlu6M4o,1070
+ai_parrot-0.3.11.dist-info/METADATA,sha256=zOYFernNOneZdQH-EIXCsmT83ATrzxGA4x9WmOhciX8,9838
+ai_parrot-0.3.11.dist-info/WHEEL,sha256=UQ-0qXN3LQUffjrV43_e_ZXj2pgORBqTmXipnkj0E8I,113
+ai_parrot-0.3.11.dist-info/top_level.txt,sha256=qHoO4BhYDfeTkyKnciZSQtn5FSLN3Q-P5xCTkyvbuxg,26
+ai_parrot-0.3.11.dist-info/RECORD,,

parrot/loaders/audio.py

@@ -28,7 +28,7 @@ class AudioLoader(BaseVideoLoader):
         metadata = {
             "source": f"{path}",
             "url": f"{path.name}",
-            "index": path.stem,
+            # "index": path.stem,
             "filename": f"{path}",
             "question": '',
             "answer": '',
@@ -71,7 +71,7 @@ class AudioLoader(BaseVideoLoader):
             docs = []
             for chunk in dialogs:
                 _meta = {
-                    "index": f"{path.stem}:{chunk['id']}",
+                    # "index": f"{path.stem}:{chunk['id']}",
                     "document_meta": {
                         "start": f"{chunk['start_time']}",
                         "end": f"{chunk['end_time']}",

parrot/loaders/excel.py

@@ -284,7 +284,7 @@ class ExcelLoader(AbstractLoader):
             df = self.unique_columns(df)
             metadata = {
                 "url": '',
-                "index": '',
+                # "index": '',
                 "source": str(path.name),
                 "filename": path.name,
                 "question": '',
@@ -309,7 +309,7 @@ class ExcelLoader(AbstractLoader):
                         idk = row[col]
                         break
                 _data = {
-                    "index": idk,
+                    # "index": idk,
                     "data": rw,
                     "document_meta": {
                         "row_index": idx,

parrot/loaders/pdf.py

@@ -336,7 +336,7 @@ class PDFLoader(BasePDF):
                         "url": f"{path}:#{page_num}",
                         "source": f"{path.name} Page.#{page_num}",
                         "filename": path.name,
-                        "index": f"{page_num}",
+                        # "index": f"{page_num}",
                         "type": 'pdf',
                         "question": '',
                         "answer": '',
@@ -400,7 +400,7 @@ class PDFLoader(BasePDF):
                             "url": url,
                             "source": f"{path.name} Page.#{page_num}",
                             "filename": path.name,
-                            "index": f"{path.name}:{page_num}",
+                            # "index": f"{path.name}:{page_num}",
                             "question": '',
                             "answer": '',
                             "type": 'image',
@@ -430,7 +430,7 @@ class PDFLoader(BasePDF):
                             "url": f"{path.name} Page.#{page_num} Table.#{tab_idx}",
                             "source": f"{path.name} Page.#{page_num} Table.#{tab_idx}",
                             "filename": path.name,
-                            "index": f"{path.name}:{page_num}",
+                            # "index": f"{path.name}:{page_num}",
                             "question": '',
                             "answer": '',
                             "type": 'table',
@@ -476,7 +476,7 @@ class PDFLoader(BasePDF):
                         "url": url,
                         "source": f"{path.name} Page.#{page_num}",
                         "filename": path.name,
-                        "index": f"{path.name}:{page_num}",
+                        # "index": f"{path.name}:{page_num}",
                         "question": '',
                         "answer": '',
                         "type": 'page',

parrot/loaders/pdfchapters.py

@@ -78,7 +78,7 @@ class PDFChapterLoader(BasePDF):
             page_number = page_num + 1
             metadata = {
                 "url": '',
-                "index": f"{path.name} #{page_number}",
+                # "index": f"{path.name} #{page_number}",
                 "source": f"{path.name} #{page_number}",
                 "filename": path.name,
                 "source_type": self._source_type,

parrot/loaders/pdffn.py

@@ -55,7 +55,7 @@ class PDFFnLoader(BasePDF):
         n = page_number + 1
         return {
             "url": '',
-            "index": f"{path.name} #{page_number}",
+            # "index": f"{path.name} #{page_number}",
             "source": f"{path.name} #{page_number}",
             "filename": path.name,
             "source_type": self._source_type,

parrot/loaders/pdfimages.py

@@ -124,7 +124,7 @@ class PDFImageLoader(BasePDF):
                 }
                 for idx, chunk in enumerate(self._splitter.split_text(md_text)):
                     _info = {
-                        "index": f"{idx}",
+                        # "index": f"{idx}",
                         **metadata
                     }
                     docs.append(
@@ -178,7 +178,7 @@ class PDFImageLoader(BasePDF):
                     _meta = {
                         "url": f"{url}",
                         "filename": str(path.name),
-                        "index": f"Page {page_num}, part: {idx}",
+                        # "index": f"Page {page_num}, part: {idx}",
                         "source": str(path.name),
                         "type": 'pdf',
                         "question": prompt_text,

parrot/loaders/pdfmark.py

@@ -74,7 +74,7 @@ class PDFMarkdownLoader(BasePDF):
             }
             for idx, chunk in enumerate(self._splitter.split_text(md_text)):
                 _info = {
-                    "index": f"{idx}",
+                    # "index": f"{idx}",
                     **metadata
                 }
                 docs.append(

parrot/loaders/pdftables.py

@@ -91,7 +91,7 @@ class PDFTablesLoader(BasePDF):
             "url": '',
             "source": f"{path.name} Page.#{page} Table.#{table_idx}",
             "filename": path.name,
-            "index": f"{path.name}:Table:{table_idx}",
+            # "index": f"{path.name}:Table:{table_idx}",
             "question": '',
             "answer": '',
             "type": 'table',

parrot/loaders/qa.py

@@ -46,7 +46,7 @@ class QAFileLoader(AbstractLoader):
                     page_content=f"**Question:** {row[q]}: **Answer:** {row[a]}",
                     metadata={
                         "url": '',
-                        "index": f"{path.name} #{idx}",
+                        # "index": f"{path.name} #{idx}",
                         "source": f"{path.name} Row.#{idx}",
                         "filename": f"{path.name}",
                         "question": row[q],

parrot/loaders/rtd.py

@@ -47,7 +47,7 @@ class ReadTheDocsLoader(AbstractLoader):
             metadata = {
                 "source": url,
                 "url": url,
-                "index": suffix,
+                # "index": suffix,
                 "filename": src,
                 "question": '',
                 "answer": '',

parrot/loaders/txt.py

@@ -44,7 +44,7 @@ class TXTLoader(AbstractLoader):
                     page_content=text,
                     metadata={
                         "url": '',
-                        "index": str(path.name),
+                        # "index": str(path.name),
                         "source": str(path),
                         "filename": str(path.name),
                         "summary": '',

parrot/loaders/videolocal.py

@@ -45,7 +45,7 @@ class VideoLocalLoader(BaseVideoLoader):
             "url": f"{path.name}",
             "source": f"{path}",
             "filename": f"{path}",
-            "index": path.stem,
+            # "index": path.stem,
             "question": '',
             "answer": '',
             'type': 'video_transcript',
@@ -96,7 +96,7 @@ class VideoLocalLoader(BaseVideoLoader):
             docs = []
             for chunk in dialogs:
                 _meta = {
-                    "index": f"{path.stem}:{chunk['id']}",
+                    # "index": f"{path.stem}:{chunk['id']}",
                     "document_meta": {
                         "start": f"{chunk['start_time']}",
                         "end": f"{chunk['end_time']}",

parrot/loaders/vimeo.py

@@ -13,7 +13,7 @@ class VimeoLoader(YoutubeLoader):
         metadata = {
             "source": url,
             "url": url,
-            "index": url,
+            # "index": url,
             "filename": video_title,
             "question": '',
             "answer": '',
@@ -73,7 +73,7 @@ class VimeoLoader(YoutubeLoader):
                 dialogs = self.transcript_to_blocks(transcript_whisper)
                 for chunk in dialogs:
                     _meta = {
-                        "index": f"{video_title}:{chunk['id']}",
+                        # "index": f"{video_title}:{chunk['id']}",
                         "document_meta": {
                             "start": f"{chunk['start_time']}",
                             "end": f"{chunk['end_time']}",

parrot/loaders/web.py

@@ -164,7 +164,7 @@ class WebLoader(AbstractLoader):
             )
             metadata = {
                 "source": url,
-                "index": page_title,
+                # "index": page_title,
                 "url": url,
                 "filename": page_title,
                 "question": '',

parrot/loaders/web_base.py

@@ -75,7 +75,7 @@ class WebBaseLoader(AbstractLoader):
             metadata = {
                 "url": url,
                 "source": url,
-                "index": "",
+                # "index": "",
                 "filename": '',
                 "type": 'webpage',
                 "question": '',

parrot/loaders/word.py

@@ -58,7 +58,7 @@ class MSWordLoader(AbstractLoader):
                         "url": '',
                         "source": path.name,
                         "filename": path.name,
-                        "index": str(path.name),
+                        # "index": str(path.name),
                         "type": 'document',
                         "question": '',
                         "answer": '',

parrot/loaders/youtube.py

@@ -71,7 +71,7 @@ class YoutubeLoader(VideoLoader):
                 metadata = {
                     "url": f"{url}",
                     "source": f"{url}",
-                    "index": video_title,
+                    # "index": video_title,
                     "filename": video_title,
                     "question": '',
                     "answer": '',
@@ -103,7 +103,7 @@ class YoutubeLoader(VideoLoader):
                 dialogs = self.transcript_to_blocks(transcript_whisper)
                 for chunk in dialogs:
                     _meta = {
-                        "index": f"{video_title}:{chunk['id']}",
+                        # "index": f"{video_title}:{chunk['id']}",
                         "document_meta": {
                             "start": f"{chunk['start_time']}",
                             "end": f"{chunk['end_time']}",
@@ -150,7 +150,7 @@ class YoutubeLoader(VideoLoader):
                 for doc in docs:
                     doc.metadata['source_type'] = self._source_type
                     doc.metadata['summary'] = f"{summary!s}"
-                    doc.metadata['index'] = ''
+                    # doc.metadata['index'] = ''
                     doc.metadata['filename'] = ''
                     doc.metadata['question'] = ''
                     doc.metadata['answer'] = ''
@@ -171,7 +171,7 @@ class YoutubeLoader(VideoLoader):
                 metadata = {
                     "source": url,
                     "url": url,
-                    "index": '',
+                    # "index": '',
                     "filename": '',
                     "question": '',
                     "answer": '',

parrot/stores/milvus.py

@@ -350,11 +350,11 @@ class MilvusStore(AbstractStore):
                 auto_id=True,
                 max_length=100
             )
-            schema.add_field(
-                field_name="index",
-                datatype=DataType.VARCHAR,
-                max_length=65535
-            )
+            # schema.add_field(
+            #     field_name="index",
+            #     datatype=DataType.VARCHAR,
+            #     max_length=65535
+            # )
             schema.add_field(
                 field_name="url",
                 datatype=DataType.VARCHAR,

parrot/version.py

@@ -3,7 +3,7 @@
 __title__ = "ai-parrot"
 __description__ = "Live Chatbots based on Langchain chatbots and Agents \
     Integrated into Navigator Framework or used into aiohttp applications."
-__version__ = "0.3.10"
+__version__ = "0.3.11"
 __author__ = "Jesus Lara"
 __author_email__ = "jesuslarag@gmail.com"
 __license__ = "MIT"