feat(integrations): added arxiv + updated readme/llamaparse/cloudinary

Author: Vedantsahai18

Diff for: README.md

@@ -1402,7 +1402,7 @@ output:
 ```yaml
 arguments:
   query: string # The search query string
-  load_max_docs: integer # Maximum number of documents to load (default: 2)
+  load_max_docs: integer # (Optional) Maximum number of documents to load. Default is 2.
 
 output:
   documents: list # The documents returned from the Wikipedia search
@@ -1443,10 +1443,13 @@ output:
 ```yaml
 setup:
   llamaparse_api_key: string # The API key for Llama Parse
+  params: dict # (Optional) Additional parameters for the Llama Parse integration
 
 arguments:
-  file: string # The base64 encoded file to parse
-  filename: string # The filename of the file
+  file: string | Array<string> # The base64 encoded file to parse or an array of URLs to load.
+  filename: string # (Optional). The filename of the file. Default is a random UUID. Only used if file is a base64 encoded string.
+  params: dict # (Optional) Additional parameters for the Llama Parse integration. Overrides the setup parameters.
+  base64: boolean # Whether the input file is base64 encoded. Default is false.
 
 output:
   documents: list # The parsed data from the document
@@ -1468,20 +1471,21 @@ setup:
   cloudinary_cloud_name: string # Your Cloudinary cloud name
   cloudinary_api_key: string # Your Cloudinary API key
   cloudinary_api_secret: string # Your Cloudinary API secret
+  params: dict # (Optional) Additional parameters for the Cloudinary integration
 
 arguments:
   file: string # The URL of the file upload. Only available for media_upload method.
-  upload_params: dict # Additional parameters for the upload. Only available for media_upload method.
-  public_id: string # The public ID for the file. For media_edit method it is MANDATORY. For media_upload method it is optional.
-  transformation: list[dict] # The transformations to apply to the file
-  return_base64: boolean # Whether to return the file in base64 encoding
+  upload_params: dict # (Optional) Additional parameters for the upload. Only available for media_upload method.
+  public_id: string # (Optional) The public ID for the file. For media_edit method it is MANDATORY. For media_upload method it is optional. Default is a random UUID.
+  transformation: list[dict] # The transformations to apply to the file. Only available for media_edit method.
+  return_base64: boolean # Whether to return the file in base64 encoding. Default is false.
 
 output:
   url: string # The URL of the uploaded file. Only available for media_upload method.
   meta_data: dict # Additional metadata from the upload response. Only available for media_upload method.
   public_id: string # The public ID of the uploaded file. Only available for media_upload method.
-  transformed_url: string # The transformed URL. Only available for media_edit method.
-  base64: string # The base64 encoded file. Only available for media_edit method.
+  transformed_url: string # (Optional) The transformed URL. Only available for media_edit method.
+  base64: string # (Optional) The base64 encoded file if return_base64 is true.
 ```
 
 </td>

Diff for: agents-api/agents_api/autogen/Tasks.py

@@ -9,6 +9,7 @@
 from pydantic import AwareDatetime, BaseModel, ConfigDict, Field, StrictBool
 
 from .Chat import ChatSettings
+from .Common import JinjaTemplate
 from .Tools import (
     ChosenBash20241022,
     ChosenComputer20241022,

Diff for: agents-api/agents_api/autogen/Tools.py

@@ -12,6 +12,7 @@
     BaseModel,
     ConfigDict,
     Field,
+    RootModel,
     StrictBool,
 )
 
@@ -147,6 +148,74 @@ class ApiCallDefUpdate(BaseModel):
     """
 
 
+class ArxivSearchArguments(BaseModel):
+    """
+    Arguments for Arxiv Search
+    """
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+    )
+    query: str
+    """
+    The search query for searching with Arxiv
+    """
+    id_list: list[str] | None = None
+    """
+    The list of Arxiv IDs to search with
+    """
+    max_results: Annotated[int, Field(ge=1, le=300000)] = 10
+    """
+    The maximum number of results to return
+    """
+    download_pdf: StrictBool = False
+    """
+    The download the pdf of the results
+    """
+    sort_by: Literal["relevance", "lastUpdatedDate", "submittedDate"] = "relevance"
+    """
+    The sort criterion for the results
+    """
+    sort_order: Literal["ascending", "descending"] = "descending"
+    """
+    The sort order for the results
+    """
+
+
+class ArxivSearchArgumentsUpdate(BaseModel):
+    """
+    Arguments for Arxiv Search
+    """
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+    )
+    query: str | None = None
+    """
+    The search query for searching with Arxiv
+    """
+    id_list: list[str] | None = None
+    """
+    The list of Arxiv IDs to search with
+    """
+    max_results: Annotated[int, Field(ge=1, le=300000)] = 10
+    """
+    The maximum number of results to return
+    """
+    download_pdf: StrictBool = False
+    """
+    The download the pdf of the results
+    """
+    sort_by: Literal["relevance", "lastUpdatedDate", "submittedDate"] = "relevance"
+    """
+    The sort criterion for the results
+    """
+    sort_order: Literal["ascending", "descending"] = "descending"
+    """
+    The sort order for the results
+    """
+
+
 class BaseChosenToolCall(BaseModel):
     """
     The response tool value generated by the model
@@ -200,6 +269,7 @@ class BaseIntegrationDef(BaseModel):
         "llama_parse",
         "ffmpeg",
         "cloudinary",
+        "arxiv",
     ]
     """
     The provider of the integration
@@ -239,6 +309,7 @@ class BaseIntegrationDefUpdate(BaseModel):
             "llama_parse",
             "ffmpeg",
             "cloudinary",
+            "arxiv",
         ]
         | None
     ) = None
@@ -886,6 +957,7 @@ class CreateToolRequest(BaseModel):
         | FfmpegIntegrationDef
         | CloudinaryUploadIntegrationDef
         | CloudinaryEditIntegrationDef
+        | ArxivIntegrationDef
         | None
     ) = None
     """
@@ -1209,29 +1281,21 @@ class LlamaParseFetchArguments(BaseModel):
     model_config = ConfigDict(
         populate_by_name=True,
     )
-    result_format: Literal["text", "markdown"] = "text"
-    """
-    The format of the result. Can be "text" or "markdown". Default is "text".
-    """
-    num_workers: Annotated[int, Field(ge=1, le=10)] = 2
-    """
-    Number of workers for parallel processing. Default is 2, but can be set between 1 and 10.
-    """
-    verbose: StrictBool = True
+    filename: str | None = None
     """
-    Verbose mode for detailed logging. Default is true.
+    File Name. If not provided, a random name will be generated.
     """
-    language: str = "en"
+    file: str | list[str]
     """
-    Language of the text. Default is English.
+    The base64 string of the file, which can be a single string or a list of strings
     """
-    filename: str | None = None
+    params: dict[str, Any] | None = None
     """
-    File Name. If not provided, a random name will be generated.
+    Optional upload parameters
     """
-    file: str
+    base64: StrictBool = False
     """
-    The base64 string of the file
+    The input file is base64
     """
 
 
@@ -1243,29 +1307,21 @@ class LlamaParseFetchArgumentsUpdate(BaseModel):
     model_config = ConfigDict(
         populate_by_name=True,
     )
-    result_format: Literal["text", "markdown"] = "text"
-    """
-    The format of the result. Can be "text" or "markdown". Default is "text".
-    """
-    num_workers: Annotated[int, Field(ge=1, le=10)] = 2
-    """
-    Number of workers for parallel processing. Default is 2, but can be set between 1 and 10.
-    """
-    verbose: StrictBool = True
+    filename: str | None = None
     """
-    Verbose mode for detailed logging. Default is true.
+    File Name. If not provided, a random name will be generated.
     """
-    language: str = "en"
+    file: str | list[str] | None = None
     """
-    Language of the text. Default is English.
+    The base64 string of the file, which can be a single string or a list of strings
     """
-    filename: str | None = None
+    params: dict[str, Any] | None = None
     """
-    File Name. If not provided, a random name will be generated.
+    Optional upload parameters
     """
-    file: str | None = None
+    base64: StrictBool = False
     """
-    The base64 string of the file
+    The input file is base64
     """
 
 
@@ -1333,6 +1389,10 @@ class LlamaParseSetup(BaseModel):
     """
     The API key for LlamaParse
     """
+    params: dict[str, Any] | None = None
+    """
+    Optional upload parameters
+    """
 
 
 class LlamaParseSetupUpdate(BaseModel):
@@ -1347,6 +1407,10 @@ class LlamaParseSetupUpdate(BaseModel):
     """
     The API key for LlamaParse
     """
+    params: dict[str, Any] | None = None
+    """
+    Optional upload parameters
+    """
 
 
 class NamedToolChoice(BaseModel):
@@ -1411,6 +1475,7 @@ class PatchToolRequest(BaseModel):
         | FfmpegIntegrationDefUpdate
         | CloudinaryUploadIntegrationDefUpdate
         | CloudinaryEditIntegrationDefUpdate
+        | ArxivIntegrationDefUpdate
         | None
     ) = None
     """
@@ -1838,6 +1903,7 @@ class Tool(BaseModel):
         | FfmpegIntegrationDef
         | CloudinaryUploadIntegrationDef
         | CloudinaryEditIntegrationDef
+        | ArxivIntegrationDef
         | None
     ) = None
     """
@@ -1931,6 +1997,7 @@ class UpdateToolRequest(BaseModel):
         | FfmpegIntegrationDef
         | CloudinaryUploadIntegrationDef
         | CloudinaryEditIntegrationDef
+        | ArxivIntegrationDef
         | None
     ) = None
     """
@@ -2148,6 +2215,58 @@ class WikipediaSearchArgumentsUpdate(BaseModel):
     """
 
 
+class ArxivIntegrationDef(BaseIntegrationDef):
+    """
+    Arxiv integration definition
+    """
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+    )
+    provider: Literal["arxiv"] = "arxiv"
+    """
+    The provider must be "arxiv"
+    """
+    method: str | None = None
+    """
+    The specific method of the integration to call
+    """
+    setup: Any | None = None
+    """
+    The setup parameters for Arxiv
+    """
+    arguments: ArxivSearchArguments | None = None
+    """
+    The arguments for Arxiv Search
+    """
+
+
+class ArxivIntegrationDefUpdate(BaseIntegrationDefUpdate):
+    """
+    Arxiv integration definition
+    """
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+    )
+    provider: Literal["arxiv"] = "arxiv"
+    """
+    The provider must be "arxiv"
+    """
+    method: str | None = None
+    """
+    The specific method of the integration to call
+    """
+    setup: Any | None = None
+    """
+    The setup parameters for Arxiv
+    """
+    arguments: ArxivSearchArgumentsUpdate | None = None
+    """
+    The arguments for Arxiv Search
+    """
+
+
 class BaseBrowserbaseIntegrationDef(BaseIntegrationDef):
     """
     The base definition for a browserbase integration