feat: add create-memory and remember API endpoints

Add possibility to create a new Vector memory and store text data points using openai embeddings.

.gitignore

@@ -163,3 +163,4 @@ cython_debug/
 #.idea/
 
 .vscode/
+database/data/

.pylintrc

@@ -0,0 +1,638 @@
+[MAIN]
+
+# Analyse import fallback blocks. This can be used to support both Python 2 and
+# 3 compatible code, which means that the block might have code that exists
+# only in one or another interpreter, leading to false positives when analysed.
+analyse-fallback-blocks=no
+
+# Clear in-memory caches upon conclusion of linting. Useful if running pylint
+# in a server-like mode.
+clear-cache-post-run=no
+
+# Load and enable all available extensions. Use --list-extensions to see a list
+# all available extensions.
+#enable-all-extensions=
+
+# In error mode, messages with a category besides ERROR or FATAL are
+# suppressed, and no reports are done by default. Error mode is compatible with
+# disabling specific errors.
+#errors-only=
+
+# Always return a 0 (non-error) status code, even if lint errors are found.
+# This is primarily useful in continuous integration scripts.
+#exit-zero=
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code.
+extension-pkg-allow-list=
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code. (This is an alternative name to extension-pkg-allow-list
+# for backward compatibility.)
+extension-pkg-whitelist=
+
+# Return non-zero exit code if any of these messages/categories are detected,
+# even if score is above --fail-under value. Syntax same as enable. Messages
+# specified are enabled, while categories only check already-enabled messages.
+fail-on=
+
+# Specify a score threshold under which the program will exit with error.
+fail-under=10
+
+# Interpret the stdin as a python script, whose filename needs to be passed as
+# the module_or_package argument.
+#from-stdin=
+
+# Files or directories to be skipped. They should be base names, not paths.
+ignore=CVS
+
+# Add files or directories matching the regular expressions patterns to the
+# ignore-list. The regex matches against paths and can be in Posix or Windows
+# format. Because '\\' represents the directory delimiter on Windows systems,
+# it can't be used as an escape character.
+ignore-paths=
+
+# Files or directories matching the regular expression patterns are skipped.
+# The regex matches against base names, not paths. The default value ignores
+# Emacs file locks
+ignore-patterns=^\.#
+
+# List of module names for which member attributes should not be checked
+# (useful for modules/projects where namespaces are manipulated during runtime
+# and thus existing member attributes cannot be deduced by static analysis). It
+# supports qualified module names, as well as Unix pattern matching.
+ignored-modules=
+
+# Python code to execute, usually for sys.path manipulation such as
+# pygtk.require().
+#init-hook=
+
+# Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
+# number of processors available to use, and will cap the count on Windows to
+# avoid hangs.
+jobs=1
+
+# Control the amount of potential inferred values when inferring a single
+# object. This can help the performance when dealing with large functions or
+# complex, nested conditions.
+limit-inference-results=100
+
+# List of plugins (as comma separated values of python module names) to load,
+# usually to register additional checkers.
+load-plugins=
+
+# Pickle collected data for later comparisons.
+persistent=yes
+
+# Minimum Python version to use for version dependent checks. Will default to
+# the version used to run pylint.
+py-version=3.12
+
+# Discover python modules and packages in the file system subtree.
+recursive=no
+
+# Add paths to the list of the source roots. Supports globbing patterns. The
+# source root is an absolute path or a path relative to the current working
+# directory used to determine a package namespace for modules located under the
+# source root.
+source-roots=
+
+# When enabled, pylint would attempt to guess common misconfiguration and emit
+# user-friendly hints instead of false-positive error messages.
+suggestion-mode=yes
+
+# Allow loading of arbitrary C extensions. Extensions are imported into the
+# active Python interpreter and may run arbitrary code.
+unsafe-load-any-extension=no
+
+# In verbose mode, extra non-checker-related info will be displayed.
+#verbose=
+
+
+[BASIC]
+
+# Naming style matching correct argument names.
+argument-naming-style=snake_case
+
+# Regular expression matching correct argument names. Overrides argument-
+# naming-style. If left empty, argument names will be checked with the set
+# naming style.
+#argument-rgx=
+
+# Naming style matching correct attribute names.
+attr-naming-style=snake_case
+
+# Regular expression matching correct attribute names. Overrides attr-naming-
+# style. If left empty, attribute names will be checked with the set naming
+# style.
+#attr-rgx=
+
+# Bad variable names which should always be refused, separated by a comma.
+bad-names=foo,
+          bar,
+          baz,
+          toto,
+          tutu,
+          tata
+
+# Bad variable names regexes, separated by a comma. If names match any regex,
+# they will always be refused
+bad-names-rgxs=
+
+# Naming style matching correct class attribute names.
+class-attribute-naming-style=any
+
+# Regular expression matching correct class attribute names. Overrides class-
+# attribute-naming-style. If left empty, class attribute names will be checked
+# with the set naming style.
+#class-attribute-rgx=
+
+# Naming style matching correct class constant names.
+class-const-naming-style=UPPER_CASE
+
+# Regular expression matching correct class constant names. Overrides class-
+# const-naming-style. If left empty, class constant names will be checked with
+# the set naming style.
+#class-const-rgx=
+
+# Naming style matching correct class names.
+class-naming-style=PascalCase
+
+# Regular expression matching correct class names. Overrides class-naming-
+# style. If left empty, class names will be checked with the set naming style.
+#class-rgx=
+
+# Naming style matching correct constant names.
+const-naming-style=UPPER_CASE
+
+# Regular expression matching correct constant names. Overrides const-naming-
+# style. If left empty, constant names will be checked with the set naming
+# style.
+#const-rgx=
+
+# Minimum line length for functions/classes that require docstrings, shorter
+# ones are exempt.
+docstring-min-length=-1
+
+# Naming style matching correct function names.
+function-naming-style=snake_case
+
+# Regular expression matching correct function names. Overrides function-
+# naming-style. If left empty, function names will be checked with the set
+# naming style.
+#function-rgx=
+
+# Good variable names which should always be accepted, separated by a comma.
+good-names=i,
+           j,
+           k,
+           ex,
+           Run,
+           _
+
+# Good variable names regexes, separated by a comma. If names match any regex,
+# they will always be accepted
+good-names-rgxs=
+
+# Include a hint for the correct naming format with invalid-name.
+include-naming-hint=no
+
+# Naming style matching correct inline iteration names.
+inlinevar-naming-style=any
+
+# Regular expression matching correct inline iteration names. Overrides
+# inlinevar-naming-style. If left empty, inline iteration names will be checked
+# with the set naming style.
+#inlinevar-rgx=
+
+# Naming style matching correct method names.
+method-naming-style=snake_case
+
+# Regular expression matching correct method names. Overrides method-naming-
+# style. If left empty, method names will be checked with the set naming style.
+#method-rgx=
+
+# Naming style matching correct module names.
+module-naming-style=snake_case
+
+# Regular expression matching correct module names. Overrides module-naming-
+# style. If left empty, module names will be checked with the set naming style.
+#module-rgx=
+
+# Colon-delimited sets of names that determine each other's naming style when
+# the name regexes allow several styles.
+name-group=
+
+# Regular expression which should only match function or class names that do
+# not require a docstring.
+no-docstring-rgx=^_
+
+# List of decorators that produce properties, such as abc.abstractproperty. Add
+# to this list to register other decorators that produce valid properties.
+# These decorators are taken in consideration only for invalid-name.
+property-classes=abc.abstractproperty
+
+# Regular expression matching correct type alias names. If left empty, type
+# alias names will be checked with the set naming style.
+#typealias-rgx=
+
+# Regular expression matching correct type variable names. If left empty, type
+# variable names will be checked with the set naming style.
+#typevar-rgx=
+
+# Naming style matching correct variable names.
+variable-naming-style=snake_case
+
+# Regular expression matching correct variable names. Overrides variable-
+# naming-style. If left empty, variable names will be checked with the set
+# naming style.
+#variable-rgx=
+
+
+[CLASSES]
+
+# Warn about protected attribute access inside special methods
+check-protected-access-in-special-methods=no
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods=__init__,
+                      __new__,
+                      setUp,
+                      asyncSetUp,
+                      __post_init__
+
+# List of member names, which should be excluded from the protected access
+# warning.
+exclude-protected=_asdict,_fields,_replace,_source,_make,os._exit
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg=cls
+
+# List of valid names for the first argument in a metaclass class method.
+valid-metaclass-classmethod-first-arg=mcs
+
+
+[DESIGN]
+
+# List of regular expressions of class ancestor names to ignore when counting
+# public methods (see R0903)
+exclude-too-few-public-methods=
+
+# List of qualified class names to ignore when counting class parents (see
+# R0901)
+ignored-parents=
+
+# Maximum number of arguments for function / method.
+max-args=5
+
+# Maximum number of attributes for a class (see R0902).
+max-attributes=7
+
+# Maximum number of boolean expressions in an if statement (see R0916).
+max-bool-expr=5
+
+# Maximum number of branch for function / method body.
+max-branches=12
+
+# Maximum number of locals for function / method body.
+max-locals=15
+
+# Maximum number of parents for a class (see R0901).
+max-parents=7
+
+# Maximum number of public methods for a class (see R0904).
+max-public-methods=20
+
+# Maximum number of return / yield for function / method body.
+max-returns=6
+
+# Maximum number of statements in function / method body.
+max-statements=50
+
+# Minimum number of public methods for a class (see R0903).
+min-public-methods=2
+
+
+[EXCEPTIONS]
+
+# Exceptions that will emit a warning when caught.
+overgeneral-exceptions=builtins.BaseException,builtins.Exception
+
+
+[FORMAT]
+
+# Expected format of line ending, e.g. empty (any line ending), LF or CRLF.
+expected-line-ending-format=
+
+# Regexp for a line that is allowed to be longer than the limit.
+ignore-long-lines=^\s*(# )?<?https?://\S+>?$
+
+# Number of spaces of indent required inside a hanging or continued line.
+indent-after-paren=4
+
+# String used as indentation unit. This is usually "    " (4 spaces) or "\t" (1
+# tab).
+indent-string='    '
+
+# Maximum number of characters on a single line.
+max-line-length=100
+
+# Maximum number of lines in a module.
+max-module-lines=1000
+
+# Allow the body of a class to be on the same line as the declaration if body
+# contains single statement.
+single-line-class-stmt=no
+
+# Allow the body of an if to be on the same line as the test if there is no
+# else.
+single-line-if-stmt=no
+
+
+[IMPORTS]
+
+# List of modules that can be imported at any level, not just the top level
+# one.
+allow-any-import-level=
+
+# Allow explicit reexports by alias from a package __init__.
+allow-reexport-from-package=no
+
+# Allow wildcard imports from modules that define __all__.
+allow-wildcard-with-all=no
+
+# Deprecated modules which should not be used, separated by a comma.
+deprecated-modules=
+
+# Output a graph (.gv or any supported image format) of external dependencies
+# to the given file (report RP0402 must not be disabled).
+ext-import-graph=
+
+# Output a graph (.gv or any supported image format) of all (i.e. internal and
+# external) dependencies to the given file (report RP0402 must not be
+# disabled).
+import-graph=
+
+# Output a graph (.gv or any supported image format) of internal dependencies
+# to the given file (report RP0402 must not be disabled).
+int-import-graph=
+
+# Force import order to recognize a module as part of the standard
+# compatibility libraries.
+known-standard-library=
+
+# Force import order to recognize a module as part of a third party library.
+known-third-party=enchant
+
+# Couples of modules and preferred modules, separated by a comma.
+preferred-modules=
+
+
+[LOGGING]
+
+# The type of string formatting that logging methods do. `old` means using %
+# formatting, `new` is for `{}` formatting.
+logging-format-style=old
+
+# Logging modules to check that the string format arguments are in logging
+# function parameter format.
+logging-modules=logging
+
+
+[MESSAGES CONTROL]
+
+# Only show warnings with the listed confidence levels. Leave empty to show
+# all. Valid levels: HIGH, CONTROL_FLOW, INFERENCE, INFERENCE_FAILURE,
+# UNDEFINED.
+confidence=HIGH,
+           CONTROL_FLOW,
+           INFERENCE,
+           INFERENCE_FAILURE,
+           UNDEFINED
+
+# Disable the message, report, category or checker with the given id(s). You
+# can either give multiple identifiers separated by comma (,) or put this
+# option multiple times (only on the command line, not in the configuration
+# file where it should appear only once). You can also use "--disable=all" to
+# disable everything first and then re-enable specific checks. For example, if
+# you want to run only the similarities checker, you can use "--disable=all
+# --enable=similarities". If you want to run only the classes checker, but have
+# no Warning level messages displayed, use "--disable=all --enable=classes
+# --disable=W".
+disable=raw-checker-failed,
+        bad-inline-option,
+        locally-disabled,
+        file-ignored,
+        suppressed-message,
+        useless-suppression,
+        deprecated-pragma,
+        use-symbolic-message-instead,
+        use-implicit-booleaness-not-comparison-to-string,
+        use-implicit-booleaness-not-comparison-to-zero,
+        missing-module-docstring,
+        missing-function-docstring,
+        missing-class-docstring
+        
+
+# Enable the message, report, category or checker with the given id(s). You can
+# either give multiple identifier separated by comma (,) or put this option
+# multiple time (only on the command line, not in the configuration file where
+# it should appear only once). See also the "--disable" option for examples.
+enable=
+
+
+[METHOD_ARGS]
+
+# List of qualified names (i.e., library.method) which require a timeout
+# parameter e.g. 'requests.api.get,requests.api.post'
+timeout-methods=requests.api.delete,requests.api.get,requests.api.head,requests.api.options,requests.api.patch,requests.api.post,requests.api.put,requests.api.request
+
+
+[MISCELLANEOUS]
+
+# List of note tags to take in consideration, separated by a comma.
+notes=FIXME,
+      XXX,
+      TODO
+
+# Regular expression of note tags to take in consideration.
+notes-rgx=
+
+
+[REFACTORING]
+
+# Maximum number of nested blocks for function / method body
+max-nested-blocks=5
+
+# Complete name of functions that never returns. When checking for
+# inconsistent-return-statements if a never returning function is called then
+# it will be considered as an explicit return statement and no message will be
+# printed.
+never-returning-functions=sys.exit,argparse.parse_error
+
+
+[REPORTS]
+
+# Python expression which should return a score less than or equal to 10. You
+# have access to the variables 'fatal', 'error', 'warning', 'refactor',
+# 'convention', and 'info' which contain the number of messages in each
+# category, as well as 'statement' which is the total number of statements
+# analyzed. This score is used by the global evaluation report (RP0004).
+evaluation=max(0, 0 if fatal else 10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10))
+
+# Template used to display messages. This is a python new-style format string
+# used to format the message information. See doc for all details.
+msg-template=
+
+# Set the output format. Available formats are: text, parseable, colorized,
+# json2 (improved json format), json (old json format) and msvs (visual
+# studio). You can also give a reporter class, e.g.
+# mypackage.mymodule.MyReporterClass.
+#output-format=
+
+# Tells whether to display a full report or only the messages.
+reports=no
+
+# Activate the evaluation score.
+score=yes
+
+
+[SIMILARITIES]
+
+# Comments are removed from the similarity computation
+ignore-comments=yes
+
+# Docstrings are removed from the similarity computation
+ignore-docstrings=yes
+
+# Imports are removed from the similarity computation
+ignore-imports=yes
+
+# Signatures are removed from the similarity computation
+ignore-signatures=yes
+
+# Minimum lines number of a similarity.
+min-similarity-lines=4
+
+
+[SPELLING]
+
+# Limits count of emitted suggestions for spelling mistakes.
+max-spelling-suggestions=4
+
+# Spelling dictionary name. No available dictionaries : You need to install
+# both the python package and the system dependency for enchant to work.
+spelling-dict=
+
+# List of comma separated words that should be considered directives if they
+# appear at the beginning of a comment and should not be checked.
+spelling-ignore-comment-directives=fmt: on,fmt: off,noqa:,noqa,nosec,isort:skip,mypy:
+
+# List of comma separated words that should not be checked.
+spelling-ignore-words=
+
+# A path to a file that contains the private dictionary; one word per line.
+spelling-private-dict-file=
+
+# Tells whether to store unknown words to the private dictionary (see the
+# --spelling-private-dict-file option) instead of raising a message.
+spelling-store-unknown-words=no
+
+
+[STRING]
+
+# This flag controls whether inconsistent-quotes generates a warning when the
+# character used as a quote delimiter is used inconsistently within a module.
+check-quote-consistency=yes
+
+# This flag controls whether the implicit-str-concat should generate a warning
+# on implicit string concatenation in sequences defined over several lines.
+check-str-concat-over-line-jumps=no
+
+
+[TYPECHECK]
+
+# List of decorators that produce context managers, such as
+# contextlib.contextmanager. Add to this list to register other decorators that
+# produce valid context managers.
+contextmanager-decorators=contextlib.contextmanager
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E1101 when accessed. Python regular
+# expressions are accepted.
+generated-members=
+
+# Tells whether to warn about missing members when the owner of the attribute
+# is inferred to be None.
+ignore-none=yes
+
+# This flag controls whether pylint should warn about no-member and similar
+# checks whenever an opaque object is returned when inferring. The inference
+# can return multiple potential results while evaluating a Python object, but
+# some branches might not be evaluated, which results in partial inference. In
+# that case, it might be useful to still emit no-member and other checks for
+# the rest of the inferred objects.
+ignore-on-opaque-inference=yes
+
+# List of symbolic message names to ignore for Mixin members.
+ignored-checks-for-mixins=no-member,
+                          not-async-context-manager,
+                          not-context-manager,
+                          attribute-defined-outside-init
+
+# List of class names for which member attributes should not be checked (useful
+# for classes with dynamically set attributes). This supports the use of
+# qualified names.
+ignored-classes=optparse.Values,thread._local,_thread._local,argparse.Namespace
+
+# Show a hint with possible names when a member name was not found. The aspect
+# of finding the hint is based on edit distance.
+missing-member-hint=yes
+
+# The minimum edit distance a name should have in order to be considered a
+# similar match for a missing member name.
+missing-member-hint-distance=1
+
+# The total number of similar names that should be taken in consideration when
+# showing a hint for a missing member.
+missing-member-max-choices=1
+
+# Regex pattern to define which classes are considered mixins.
+mixin-class-rgx=.*[Mm]ixin
+
+# List of decorators that change the signature of a decorated function.
+signature-mutators=
+
+
+[VARIABLES]
+
+# List of additional names supposed to be defined in builtins. Remember that
+# you should avoid defining new builtins when possible.
+additional-builtins=
+
+# Tells whether unused global variables should be treated as a violation.
+allow-global-unused-variables=yes
+
+# List of names allowed to shadow builtins
+allowed-redefined-builtins=
+
+# List of strings which can identify a callback function by name. A callback
+# name must start or end with one of those strings.
+callbacks=cb_,
+          _cb
+
+# A regular expression matching the name of dummy variables (i.e. expected to
+# not be used).
+dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_
+
+# Argument names that match this expression will be ignored.
+ignored-argument-names=_.*|^ignored_|^unused_
+
+# Tells whether we should check for unused import in __init__ files.
+init-import=no
+
+# List of qualified module names which can have objects that can redefine
+# builtins.
+redefining-builtins-modules=six.moves,past.builtins,future.builtins,builtins,io

README.md

@@ -67,6 +67,8 @@ Try it yourself on Whatsapp with one of our <a href="https://keepi.ai">partners<
 
 ## Getting started
 
+### Run with Docker
+
 To run cognee you need to have <a href="https://docs.docker.com/get-docker" target="_blank">Docker</a> installed on your machine.
 
 Run <a href="https://www.cognee.ai" target="_blank">Cognee</a> in a couple of steps:
@@ -74,15 +76,23 @@ Run <a href="https://www.cognee.ai" target="_blank">Cognee</a> in a couple of st
 - Run `docker compose up` in order to start graph and relational databases
 - Run `docker compose up cognee` in order start Cognee
 
-<!-- Send API requests add-memory, user-query-to-graph, document-to-graph-db, user-query-processor to the locahost:8000 -->
-
-## Debugging
+#### Debugging
 To run Cognee with debugger attached you need to build the Cognee image with the `DEBUG` flag set to true.
 
 - `docker compose build cognee --no-cache --build-arg DEBUG=true`
 - `docker compose up cognee`
 
 
+### Run without Docker
+- Run `PYTHONPATH=. python cognitive_architecture/setup_database.py` to setup database
+- Run `python -m gunicorn -w 1 -k uvicorn.workers.UvicornWorker -t 30000 --bind=127.0.0.1:8000 --log-level debug api:app`
+
+#### Debugging
+- Run `python -m debugpy --wait-for-client --listen localhost:5678 -m gunicorn -w 1 -k uvicorn.workers.UvicornWorker -t 30000 --bind=127.0.0.1:8000 --log-level debug api:app`
+- Attach debugger
+
+<!-- Send API requests add-memory, user-query-to-graph, document-to-graph-db, user-query-processor to the locahost:8000 -->
+
 ## Demo
 
 [<img src="https://i3.ytimg.com/vi/yjParvJVgPI/maxresdefault.jpg" width="100%">](https://www.youtube.com/watch?v=yjParvJVgPI "Learn about cognee: 55")

api.py

@@ -18,7 +18,7 @@ from cognitive_architecture.config import Config
 config = Config()
 config.load()
 
-from typing import Dict, Any
+from typing import Dict, Any, List
 from fastapi import FastAPI, BackgroundTasks, HTTPException
 from fastapi.responses import JSONResponse
 from pydantic import BaseModel
@@ -57,6 +57,54 @@ def health_check():
 class Payload(BaseModel):
     payload: Dict[str, Any]
 
+from cognitive_architecture.api.v1.memory.create_memory import MemoryType
+
+class CreateMemoryPayload(BaseModel):
+    user_id: str
+    memory_name: str
+    memory_type: MemoryType
+
+@app.post("/create-memory", response_model=dict)
+async def create_memory(payload: CreateMemoryPayload):
+    from cognitive_architecture.api.v1.memory.create_memory import create_memory as create_memory_v1, MemoryException
+
+    try:
+        await create_memory_v1(
+            payload.user_id,
+            payload.memory_name,
+            payload.memory_type or MemoryType.VECTOR,
+        )
+    except MemoryException as error:
+        return JSONResponse(
+            status_code = 409,
+            content = { "error": error.message }
+        )
+
+    return JSONResponse(
+        status_code = 200,
+        content = { "memory_name": payload.memory_name }
+    )
+
+
+class RememberPayload(BaseModel):
+    user_id: str
+    memory_name: str
+    payload: List[str]
+
+@app.post("/remember", response_model=dict)
+async def remember(payload: RememberPayload):
+    from cognitive_architecture.api.v1.memory.remember import remember as remember_v1
+    
+    await remember_v1(
+        payload.user_id,
+        payload.memory_name,
+        payload.payload
+    )
+
+    return JSONResponse(
+        status_code = 200,
+        content = { "message": "ok" }
+    )
 
 @app.post("/add-memory", response_model=dict)
 async def add_memory(
@@ -83,9 +131,9 @@ async def add_memory(
                 content = None
 
             output = await load_documents_to_vectorstore(
-                session,
-                decoded_payload["user_id"],
+                session = session,
                 content = content,
+                user_id = decoded_payload["user_id"],
                 loader_settings = settings_for_loader,
             )
             return JSONResponse(content={"response": output}, status_code=200)
@@ -114,9 +162,9 @@ async def add_memory(
             loader_settings = {"format": "PDF", "source": "DEVICE", "path": [".data"]}
 
             output = await load_documents_to_vectorstore(
-                session,
                 user_id = user_id,
                 content = content,
+                session = session,
                 loader_settings = loader_settings,
             )
             return JSONResponse(content={"response": output}, status_code=200)

cognitive_architecture/api/v1/memory/create_memory.py

@@ -0,0 +1,32 @@
+from enum import Enum
+from qdrant_client.models import Distance, VectorParams
+from cognitive_architecture.modules.memory.vector import create_vector_memory
+from cognitive_architecture.modules.users.memory import is_existing_memory, register_memory_for_user
+from cognitive_architecture.infrastructure.databases.vector.qdrant.adapter import CollectionConfig
+
+class MemoryType(Enum):
+    GRAPH = "GRAPH"
+    VECTOR = "VECTOR"
+    RELATIONAL = "RELATIONAL"
+
+class MemoryException(Exception):
+    message: str
+
+    def __init__(self, message: str):
+        self.message = message
+
+
+async def create_memory(user_id: str, memory_name: str, memory_type: MemoryType):
+    if await is_existing_memory(memory_name):
+        raise MemoryException(f'Memory with the name "{memory_name}" already exists. Memory names must be unique.')
+
+    match memory_type:
+        case MemoryType.VECTOR:
+            await create_vector_memory(memory_name, CollectionConfig(
+                vector_config = VectorParams(
+                    size = 1536,
+                    distance = Distance.DOT,
+                )
+            ))
+
+    await register_memory_for_user(user_id, memory_name)

cognitive_architecture/api/v1/memory/remember.py

@@ -0,0 +1,21 @@
+from typing import List
+from enum import Enum
+from cognitive_architecture.modules.users.memory import create_information_points, is_existing_memory
+
+class MemoryType(Enum):
+    GRAPH = "GRAPH"
+    VECTOR = "VECTOR"
+    RELATIONAL = "RELATIONAL"
+
+class MemoryException(Exception):
+    message: str
+
+    def __init__(self, message: str):
+        self.message = message
+
+
+async def remember(user_id: str, memory_name: str, payload: List[str]):
+    if await is_existing_memory(memory_name) is False:
+        raise MemoryException(f"Memory with the name \"{memory_name}\" doesn't exist.")
+
+    await create_information_points(memory_name, payload)

cognitive_architecture/config.py

@@ -30,8 +30,11 @@ class Config:
     db_path = Path(__file__).resolve().parent / "database/data"
 
     vectordb: str = os.getenv("VECTORDB", "weaviate")
+    qdrant_path: str = os.getenv("QDRANT_PATH")
+    qdrant_url: str = os.getenv("QDRANT_URL")
+    qdrant_api_key: str = os.getenv("QDRANT_API_KEY")
     db_type: str = os.getenv("DB_TYPE", "sqlite")
-    db_name: str = os.getenv("DB_NAME", "cognee.db")
+    db_name: str = os.getenv("DB_NAME", "cognee.sqlite")
     db_host: str = os.getenv("DB_HOST", "localhost")
     db_port: str = os.getenv("DB_PORT", "5432")
     db_user: str = os.getenv("DB_USER", "cognee")

cognitive_architecture/database/relationaldb/models/docs.py

@@ -2,11 +2,8 @@
 from datetime import datetime
 from sqlalchemy import Column, String, DateTime, ForeignKey, Boolean
 from sqlalchemy.orm import relationship
-import os
-import sys
 from ..database import Base
 
-
 class DocsModel(Base):
     """ Docs model"""
     __tablename__ = "docs"

cognitive_architecture/database/relationaldb/models/memory.py

@@ -1,6 +1,6 @@
 """ This module contains the MemoryModel class, which is a SQLAlchemy model for the memory table in the relational database. """
 from datetime import datetime
-from sqlalchemy import Column, String, DateTime, ForeignKey
+from sqlalchemy import Column, String, DateTime, ForeignKey, UUID
 from sqlalchemy.orm import relationship
 from ..database import Base
 
@@ -9,7 +9,7 @@ class MemoryModel(Base):
     """ Memory model"""
     __tablename__ = "memories"
 
-    id = Column(String, primary_key=True)
+    id = Column(UUID, primary_key=True)
     user_id = Column(String, ForeignKey("users.id"), index=True)
     operation_id = Column(String, ForeignKey("operations.id"), index=True)
     memory_name = Column(String, nullable=True)

cognitive_architecture/infrastructure/databases/relational/general/adapter.py

@@ -0,0 +1,74 @@
+import uuid
+from pathlib import Path
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import create_async_engine, async_sessionmaker, AsyncSession
+from cognitive_architecture.config import Config
+# from ..relational_db_interface import RelationalDBInterface
+from cognitive_architecture.database.relationaldb.models.memory import MemoryModel
+
+config = Config()
+config.load()
+
+class RelationalDBAdapter():
+    session_maker: async_sessionmaker[AsyncSession]
+
+    def __init__(self):
+        engine = create_async_engine(
+            self.get_database_url(),
+            pool_recycle = 3600,
+            echo = config.sqlalchemy_logging,
+        )
+        self.create_session = async_sessionmaker[AsyncSession](
+            bind = engine,
+            class_ = AsyncSession,
+            expire_on_commit = False,
+        )
+
+    def get_database_url(
+        self,
+        db_type = config.db_type,
+        db_name = config.db_name,
+        db_path = config.db_path,
+        user = config.db_user,
+        password = config.db_password,
+        host = config.db_host,
+        port = config.db_port,
+    ):
+        if db_type == "sqlite":
+            db_path = (Path(db_path) / db_name).absolute()
+            return f"sqlite+aiosqlite:///{db_path}"  # SQLite uses file path
+        elif db_type == "duckdb":
+            db_path = (Path(db_path) / db_name).absolute()
+            return f"duckdb+aiosqlite:///{db_path}"
+        elif db_type == "postgresql":
+            # Ensure optional parameters are handled gracefully
+            port_str = f":{port}" if port else ""
+            password_str = f":{password}" if password else ""
+            if not all([user, host]):
+                raise ValueError("User and host are required for PostgreSQL connections.")
+            return f"postgresql+asyncpg://{user}{password_str}@{host}{port_str}/{db_name}"
+        else:
+            raise ValueError(f"Unsupported database type: {db_type}")
+
+    async def add_memory(self, user_id: str, memory_name: str):
+        memory_id = uuid.uuid4()
+
+        async with self.create_session() as session:
+            async with session.begin():
+                return session.add(MemoryModel(
+                    id = memory_id,
+                    user_id = user_id,
+                    memory_name = memory_name,
+                ))
+
+    async def get_memory_by_name(self, memory_name: int):
+        async with self.create_session() as session:
+            async with session.begin():
+                result = await session.execute(
+                    select(MemoryModel.id)
+                        .where(MemoryModel.memory_name == memory_name)
+                )
+
+                memory = result.scalars().one_or_none()
+
+                return memory

cognitive_architecture/infrastructure/databases/relational/general/models/memory_model.py

@@ -0,0 +1,26 @@
+# from datetime import datetime, timezone
+# from sqlalchemy.orm import relationship
+# # from sqlalchemy.orm import DeclarativeBase
+# from sqlalchemy import Column, String, DateTime, ForeignKey
+# from cognitive_architecture.database.relationaldb.database import Base
+
+
+# class MemoryModel(Base):
+#     __tablename__ = "memories_v1"
+
+#     id = Column(String, primary_key = True)
+#     user_id = Column(String, ForeignKey("users.id"), index = True)
+#     memory_name = Column(String, nullable = True)
+#     memory_category = Column(String, nullable = True)
+#     created_at = Column(DateTime, default = datetime.now(timezone.utc))
+#     updated_at = Column(DateTime, onupdate = datetime.now(timezone.utc))
+#     methods_list = Column(String, nullable = True)
+#     attributes_list = Column(String, nullable = True)
+
+#     user = relationship("User", back_populates="memories")
+#     metadatas = relationship(
+#         "MetaDatas", back_populates="memory", cascade="all, delete-orphan"
+#     )
+
+#     def __repr__(self):
+#         return f"<Memory(id={self.id}, user_id={self.user_id}, created_at={self.created_at}, updated_at={self.updated_at})>"

cognitive_architecture/infrastructure/databases/relational/get_database.py

@@ -0,0 +1,4 @@
+from .general.adapter import RelationalDBAdapter
+
+def get_database():
+    return RelationalDBAdapter()

cognitive_architecture/infrastructure/databases/relational/relational_db_interface.py

@@ -0,0 +1,26 @@
+from abc import abstractmethod
+from typing import Protocol, TypeVar, Type, List
+
+RowDataType = TypeVar('RowDataType')
+
+class RelationalDBInterface(Protocol):
+    @abstractmethod
+    async def create_database(self, database_name: str, database_path: str): raise NotImplementedError
+
+    @abstractmethod
+    async def create_table(self, table_name: str, table_config: object): raise NotImplementedError
+
+    @abstractmethod
+    async def add_row(self, table_name: str, row_data: Type[RowDataType]): raise NotImplementedError
+
+    @abstractmethod
+    async def add_rows(self, table_name: str, rows_data: List[Type[RowDataType]]): raise NotImplementedError
+
+    @abstractmethod
+    async def get_row(self, table_name: str, row_id: str): raise NotImplementedError
+
+    @abstractmethod
+    async def update_row(self, table_name: str, row_id: str, row_data: Type[RowDataType]): raise NotImplementedError
+
+    @abstractmethod
+    async def delete_row(self, table_name: str, row_id: str): raise NotImplementedError

cognitive_architecture/infrastructure/databases/vector/get_vector_database.py

@@ -0,0 +1,8 @@
+from cognitive_architecture.config import Config
+from .qdrant import QDrantAdapter
+
+config = Config()
+config.load()
+
+def get_vector_database():
+    return QDrantAdapter(config.qdrant_path, config.qdrant_url, config.qdrant_api_key)

cognitive_architecture/infrastructure/databases/vector/lancedb/adapter.py

@@ -0,0 +1,95 @@
+import typing
+from qdrant_client import AsyncQdrantClient, models
+from databases.vector.vector_db_interface import VectorDBInterface
+
+class VectorConfig(extra='forbid'):
+    size: int
+    distance: str
+    on_disk: bool
+
+class CollectionConfig(extra='forbid'):
+    vector_config: VectorConfig
+    hnsw_config: models.HnswConfig
+    optimizers_config: models.OptimizersConfig
+    quantization_config: models.QuantizationConfig
+
+class LanceDBAdapter(VectorDBInterface):
+    def __init__(self, lancedb_url, lancedb_api_key):
+        self.lancedb_url = lancedb_url
+        self.lancedb_api_key = lancedb_api_key
+
+    def get_lancedb_client(self) -> AsyncQdrantClient:
+        return AsyncQdrantClient(
+            url = self.lancedb_url,
+            api_key = self.lancedb_api_key,
+            location = ':memory:'
+        )
+
+    async def create_collection(
+      self,
+      collection_name: str,
+      collection_config: CollectionConfig
+    ):
+        client = self.get_lancedb_client()
+
+        return await client.create_collection(
+            collection_name = collection_name,
+            vectors_config = collection_config.vector_config,
+            hnsw_config = collection_config.hnsw_config,
+            optimizers_config = collection_config.optimizers_config,
+            quantization_config = collection_config.quantization_config
+        )
+
+    async def create_data_points(self, collection_name: str, data_points: typing.List[any]):
+        client = self.get_lancedb_client()
+
+        async def create_data_point(data):
+            return {
+                'vector': {},
+                'payload': data
+            }
+
+        return await client.upload_points(
+            collection_name = collection_name,
+            points = map(create_data_point, data_points)
+        )
+
+
+# class LanceDB(VectorDB):
+#     def __init__(self, *args, **kwargs):
+#         super().__init__(*args, **kwargs)
+#         self.db = self.init_lancedb()
+
+#     def init_lancedb(self):
+#         # Initialize LanceDB connection
+#         # Adjust the URI as needed for your LanceDB setup
+#         uri = "s3://my-bucket/lancedb" if self.namespace else "~/.lancedb"
+#         db = lancedb.connect(uri, api_key=os.getenv("LANCEDB_API_KEY"))
+#         return db
+
+#     def create_table(
+#         self,
+#         name: str,
+#         schema: Optional[pa.Schema] = None,
+#         data: Optional[pd.DataFrame] = None,
+#     ):
+#         # Create a table in LanceDB. If schema is not provided, it will be inferred from the data.
+#         if data is not None and schema is None:
+#             schema = pa.Schema.from_pandas(data)
+#         table = self.db.create_table(name, schema=schema)
+#         if data is not None:
+#             table.add(data.to_dict("records"))
+#         return table
+
+#     def add_memories(self, table_name: str, data: pd.DataFrame):
+#         # Add data to an existing table in LanceDB
+#         table = self.db.open_table(table_name)
+#         table.add(data.to_dict("records"))
+
+#     def fetch_memories(
+#         self, table_name: str, query_vector: List[float], top_k: int = 10
+#     ):
+#         # Perform a vector search in the specified table
+#         table = self.db.open_table(table_name)
+#         results = table.search(query_vector).limit(top_k).to_pandas()
+#         return results

cognitive_architecture/infrastructure/databases/vector/pinecone/adapter.py

@@ -0,0 +1,8 @@
+class PineconeVectorDB(VectorDB):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.init_pinecone(self.index_name)
+
+    def init_pinecone(self, index_name):
+        # Pinecone initialization logic
+        pass

cognitive_architecture/infrastructure/databases/vector/qdrant/__init__.py

@@ -0,0 +1 @@
+from .adapter import QDrantAdapter

cognitive_architecture/infrastructure/databases/vector/qdrant/adapter.py

@@ -1,13 +1,61 @@
-from vector.vector_db_interface import VectorDBInterface
-from qdrant_client import AsyncQdrantClient
+from typing import List, Optional
+from pydantic import BaseModel, Field
+from qdrant_client import AsyncQdrantClient, models
+from ..vector_db_interface import VectorDBInterface
+
+class CollectionConfig(BaseModel, extra = "forbid"):
+    vector_config: models.VectorParams = Field(..., description="Vector configuration")
+    hnsw_config: Optional[models.HnswConfig] = Field(default = None, description="HNSW vector index configuration")
+    optimizers_config: Optional[models.OptimizersConfig] = Field(default = None, description="Optimizers configuration")
+    quantization_config: Optional[models.QuantizationConfig] = Field(default = None, description="Quantization configuration")
 
 class QDrantAdapter(VectorDBInterface):
-    def __init__(self, qdrant_url, qdrant_api_key):
-        self.qdrant_client = AsyncQdrantClient(qdrant_url, qdrant_api_key)
+    qdrant_url: str = None
+    qdrant_path: str = None
+    qdrant_api_key: str = None
+  
+    def __init__(self, qdrant_path, qdrant_url, qdrant_api_key):
+        if qdrant_path is not None:
+            self.qdrant_path = qdrant_path
+        else:
+            self.qdrant_url = qdrant_url
+
+        self.qdrant_api_key = qdrant_api_key
+
+    def get_qdrant_client(self) -> AsyncQdrantClient:
+        if self.qdrant_path is not None:
+            return AsyncQdrantClient(
+                path = self.qdrant_path,
+            )
+        elif self.qdrant_url is not None:
+            return AsyncQdrantClient(
+                url = self.qdrant_url,
+                api_key = self.qdrant_api_key,
+            )
+
+        return AsyncQdrantClient(
+            location = ":memory:"
+        )
 
     async def create_collection(
       self,
       collection_name: str,
-      collection_config: object
+      collection_config: CollectionConfig,
     ):
-        return await self.qdrant_client.create_collection(collection_name, collection_config)
+        client = self.get_qdrant_client()
+
+        return await client.create_collection(
+            collection_name = collection_name,
+            vectors_config = collection_config.vector_config,
+            hnsw_config = collection_config.hnsw_config,
+            optimizers_config = collection_config.optimizers_config,
+            quantization_config = collection_config.quantization_config
+        )
+
+    async def create_data_points(self, collection_name: str, data_points: List[any]):
+        client = self.get_qdrant_client()
+
+        return await client.upload_points(
+            collection_name = collection_name,
+            points = data_points
+        )

cognitive_architecture/infrastructure/databases/vector/vector_db_interface.py

@@ -1,3 +1,4 @@
+from typing import List
 from abc import abstractmethod
 from typing import Protocol
 
@@ -10,59 +11,59 @@ class VectorDBInterface(Protocol):
         collection_config: object
     ): raise NotImplementedError
 
-    @abstractmethod
-    async def update_collection(
-        self,
-        collection_name: str,
-        collection_config: object
-    ): raise NotImplementedError
+    # @abstractmethod
+    # async def update_collection(
+    #     self,
+    #     collection_name: str,
+    #     collection_config: object
+    # ): raise NotImplementedError
 
-    @abstractmethod
-    async def delete_collection(
-        self,
-        collection_name: str
-    ): raise NotImplementedError
+    # @abstractmethod
+    # async def delete_collection(
+    #     self,
+    #     collection_name: str
+    # ): raise NotImplementedError
 
-    @abstractmethod
-    async def create_vector_index(
-        self,
-        collection_name: str,
-        vector_index_config: object
-    ): raise NotImplementedError
+    # @abstractmethod
+    # async def create_vector_index(
+    #     self,
+    #     collection_name: str,
+    #     vector_index_config: object
+    # ): raise NotImplementedError
 
-    @abstractmethod
-    async def create_data_index(
-        self,
-        collection_name: str,
-        vector_index_config: object
-    ): raise NotImplementedError
+    # @abstractmethod
+    # async def create_data_index(
+    #     self,
+    #     collection_name: str,
+    #     vector_index_config: object
+    # ): raise NotImplementedError
 
     """ Data points """
     @abstractmethod
-    async def create_data_point(
+    async def create_data_points(
         self,
         collection_name: str,
-        payload: object
+        data_points: List[any]
     ): raise NotImplementedError
 
-    @abstractmethod
-    async def get_data_point(
-        self,
-        collection_name: str,
-        data_point_id: str
-    ): raise NotImplementedError
+    # @abstractmethod
+    # async def get_data_point(
+    #     self,
+    #     collection_name: str,
+    #     data_point_id: str
+    # ): raise NotImplementedError
 
-    @abstractmethod
-    async def update_data_point(
-        self,
-        collection_name: str,
-        data_point_id: str,
-        payload: object
-    ): raise NotImplementedError
+    # @abstractmethod
+    # async def update_data_point(
+    #     self,
+    #     collection_name: str,
+    #     data_point_id: str,
+    #     payload: object
+    # ): raise NotImplementedError
 
-    @abstractmethod
-    async def delete_data_point(
-        self,
-        collection_name: str,
-        data_point_id: str
-    ): raise NotImplementedError
+    # @abstractmethod
+    # async def delete_data_point(
+    #     self,
+    #     collection_name: str,
+    #     data_point_id: str
+    # ): raise NotImplementedError

cognitive_architecture/infrastructure/databases/vector/weviate/adapter.py

@@ -0,0 +1,417 @@
+from weaviate.gql.get import HybridFusion
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.retrievers import WeaviateHybridSearchRetriever, ParentDocumentRetriever
+from databases.vector.vector_db_interface import VectorDBInterface
+# from langchain.text_splitter import RecursiveCharacterTextSplitter
+from cognitive_architecture.database.vectordb.loaders.loaders import _document_loader
+
+class WeaviateVectorDB(VectorDBInterface):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.init_weaviate(embeddings=self.embeddings, namespace=self.namespace)
+
+    def init_weaviate(
+        self,
+        embeddings=OpenAIEmbeddings(openai_api_key=os.getenv("OPENAI_API_KEY", "")),
+        namespace=None,
+        retriever_type="",
+    ):
+        # Weaviate initialization logic
+        auth_config = weaviate.auth.AuthApiKey(
+            api_key=os.environ.get("WEAVIATE_API_KEY")
+        )
+        client = weaviate.Client(
+            url=os.environ.get("WEAVIATE_URL"),
+            auth_client_secret=auth_config,
+            additional_headers={"X-OpenAI-Api-Key": os.environ.get("OPENAI_API_KEY")},
+        )
+
+        if retriever_type == "single_document_context":
+            retriever = WeaviateHybridSearchRetriever(
+                client=client,
+                index_name=namespace,
+                text_key="text",
+                attributes=[],
+                embedding=embeddings,
+                create_schema_if_missing=True,
+            )
+            return retriever
+        elif retriever_type == "multi_document_context":
+            retriever = WeaviateHybridSearchRetriever(
+                client=client,
+                index_name=namespace,
+                text_key="text",
+                attributes=[],
+                embedding=embeddings,
+                create_schema_if_missing=True,
+            )
+            return retriever
+        else:
+            return client
+            # child_splitter = RecursiveCharacterTextSplitter(chunk_size=400)
+            # store = InMemoryStore()
+            # retriever = ParentDocumentRetriever(
+            #     vectorstore=vectorstore,
+            #     docstore=store,
+            #     child_splitter=child_splitter,
+            # )
+
+    from marshmallow import Schema, fields
+
+    def create_document_structure(observation, params, metadata_schema_class=None):
+        """
+        Create and validate a document structure with optional custom fields.
+
+        :param observation: Content of the document.
+        :param params: Metadata information.
+        :param metadata_schema_class: Custom metadata schema class (optional).
+        :return: A list containing the validated document data.
+        """
+        document_data = {"metadata": params, "page_content": observation}
+
+        def get_document_schema():
+            class DynamicDocumentSchema(Schema):
+                metadata = fields.Nested(metadata_schema_class, required=True)
+                page_content = fields.Str(required=True)
+
+            return DynamicDocumentSchema
+
+        # Validate and deserialize, defaulting to "1.0" if not provided
+        CurrentDocumentSchema = get_document_schema()
+        loaded_document = CurrentDocumentSchema().load(document_data)
+        return [loaded_document]
+
+    def _stuct(self, observation, params, metadata_schema_class=None):
+        """Utility function to create the document structure with optional custom fields."""
+        # Construct document data
+        document_data = {"metadata": params, "page_content": observation}
+
+        def get_document_schema():
+            class DynamicDocumentSchema(Schema):
+                metadata = fields.Nested(metadata_schema_class, required=True)
+                page_content = fields.Str(required=True)
+
+            return DynamicDocumentSchema
+
+        # Validate and deserialize  # Default to "1.0" if not provided
+        CurrentDocumentSchema = get_document_schema()
+        loaded_document = CurrentDocumentSchema().load(document_data)
+        return [loaded_document]
+
+    async def add_memories(
+        self,
+        observation,
+        loader_settings=None,
+        params=None,
+        namespace=None,
+        metadata_schema_class=None,
+        embeddings="hybrid",
+    ):
+        # Update Weaviate memories here
+        if namespace is None:
+            namespace = self.namespace
+        params["user_id"] = self.user_id
+        logging.info("User id is %s", self.user_id)
+        retriever = self.init_weaviate(
+            embeddings=OpenAIEmbeddings(),
+            namespace=namespace,
+            retriever_type="single_document_context",
+        )
+        if loader_settings:
+            # Assuming _document_loader returns a list of documents
+            documents = await _document_loader(observation, loader_settings)
+            logging.info("here are the docs %s", str(documents))
+            chunk_count = 0
+            for doc_list in documents:
+                for doc in doc_list:
+                    chunk_count += 1
+                    params["chunk_count"] = doc.metadata.get("chunk_count", "None")
+                    logging.info(
+                        "Loading document with provided loader settings %s", str(doc)
+                    )
+                    params["source"] = doc.metadata.get("source", "None")
+                    logging.info("Params are %s", str(params))
+                    retriever.add_documents(
+                        [Document(metadata=params, page_content=doc.page_content)]
+                    )
+        else:
+            chunk_count = 0
+            from cognitive_architecture.database.vectordb.chunkers.chunkers import (
+                chunk_data,
+            )
+
+            documents = [
+                chunk_data(
+                    chunk_strategy="VANILLA",
+                    source_data=observation,
+                    chunk_size=300,
+                    chunk_overlap=20,
+                )
+            ]
+            for doc in documents[0]:
+                chunk_count += 1
+                params["chunk_order"] = chunk_count
+                params["source"] = "User loaded"
+                logging.info(
+                    "Loading document with default loader settings %s", str(doc)
+                )
+                logging.info("Params are %s", str(params))
+                retriever.add_documents(
+                    [Document(metadata=params, page_content=doc.page_content)]
+                )
+
+    async def fetch_memories(
+        self,
+        observation: str,
+        namespace: str = None,
+        search_type: str = "hybrid",
+        params=None,
+        **kwargs,
+    ):
+        """
+        Fetch documents from weaviate.
+
+        Parameters:
+        - observation (str): User query.
+        - namespace (str, optional): Type of memory accessed.
+        - search_type (str, optional): Type of search ('text', 'hybrid', 'bm25', 'generate', 'generate_grouped'). Defaults to 'hybrid'.
+        - **kwargs: Additional parameters for flexibility.
+
+        Returns:
+        List of documents matching the query or an empty list in case of error.
+
+        Example:
+            fetch_memories(query="some query", search_type='text', additional_param='value')
+        """
+        client = self.init_weaviate(namespace=self.namespace)
+        if search_type is None:
+            search_type = "hybrid"
+
+        if not namespace:
+            namespace = self.namespace
+
+        logging.info("Query on namespace %s", namespace)
+
+        params_user_id = {
+            "path": ["user_id"],
+            "operator": "Like",
+            "valueText": self.user_id,
+        }
+
+        def list_objects_of_class(class_name, schema):
+            return [
+                prop["name"]
+                for class_obj in schema["classes"]
+                if class_obj["class"] == class_name
+                for prop in class_obj["properties"]
+            ]
+
+        base_query = (
+            client.query.get(
+                namespace, list(list_objects_of_class(namespace, client.schema.get()))
+            )
+            .with_additional(
+                ["id", "creationTimeUnix", "lastUpdateTimeUnix", "score", "distance"]
+            )
+            .with_where(params_user_id)
+            .with_limit(10)
+        )
+
+        n_of_observations = kwargs.get("n_of_observations", 2)
+
+        # try:
+        if search_type == "text":
+            query_output = (
+                base_query.with_near_text({"concepts": [observation]})
+                .with_autocut(n_of_observations)
+                .do()
+            )
+        elif search_type == "hybrid":
+            query_output = (
+                base_query.with_hybrid(
+                    query=observation, fusion_type=HybridFusion.RELATIVE_SCORE
+                )
+                .with_autocut(n_of_observations)
+                .do()
+            )
+        elif search_type == "bm25":
+            query_output = (
+                base_query.with_bm25(query=observation)
+                .with_autocut(n_of_observations)
+                .do()
+            )
+        elif search_type == "summary":
+            filter_object = {
+                "operator": "And",
+                "operands": [
+                    {
+                        "path": ["user_id"],
+                        "operator": "Equal",
+                        "valueText": self.user_id,
+                    },
+                    {
+                        "path": ["chunk_order"],
+                        "operator": "LessThan",
+                        "valueNumber": 30,
+                    },
+                ],
+            }
+            base_query = (
+                client.query.get(
+                    namespace,
+                    list(list_objects_of_class(namespace, client.schema.get())),
+                )
+                .with_additional(
+                    [
+                        "id",
+                        "creationTimeUnix",
+                        "lastUpdateTimeUnix",
+                        "score",
+                        "distance",
+                    ]
+                )
+                .with_where(filter_object)
+                .with_limit(30)
+            )
+            query_output = (
+                base_query
+                # .with_hybrid(query=observation, fusion_type=HybridFusion.RELATIVE_SCORE)
+                .do()
+            )
+
+        elif search_type == "summary_filter_by_object_name":
+            filter_object = {
+                "operator": "And",
+                "operands": [
+                    {
+                        "path": ["user_id"],
+                        "operator": "Equal",
+                        "valueText": self.user_id,
+                    },
+                    {
+                        "path": ["doc_id"],
+                        "operator": "Equal",
+                        "valueText": params,
+                    },
+                ],
+            }
+            base_query = (
+                client.query.get(
+                    namespace,
+                    list(list_objects_of_class(namespace, client.schema.get())),
+                )
+                .with_additional(
+                    [
+                        "id",
+                        "creationTimeUnix",
+                        "lastUpdateTimeUnix",
+                        "score",
+                        "distance",
+                    ]
+                )
+                .with_where(filter_object)
+                .with_limit(30)
+                .with_hybrid(query=observation, fusion_type=HybridFusion.RELATIVE_SCORE)
+            )
+            query_output = base_query.do()
+
+            return query_output
+        elif search_type == "generate":
+            generate_prompt = kwargs.get("generate_prompt", "")
+            query_output = (
+                base_query.with_generate(single_prompt=observation)
+                .with_near_text({"concepts": [observation]})
+                .with_autocut(n_of_observations)
+                .do()
+            )
+        elif search_type == "generate_grouped":
+            generate_prompt = kwargs.get("generate_prompt", "")
+            query_output = (
+                base_query.with_generate(grouped_task=observation)
+                .with_near_text({"concepts": [observation]})
+                .with_autocut(n_of_observations)
+                .do()
+            )
+        else:
+            logging.error(f"Invalid search_type: {search_type}")
+            return []
+        # except Exception as e:
+        #     logging.error(f"Error executing query: {str(e)}")
+        #     return []
+
+        return query_output
+
+    async def delete_memories(self, namespace: str, params: dict = None):
+        if namespace is None:
+            namespace = self.namespace
+        client = self.init_weaviate(namespace=self.namespace)
+        if params:
+            where_filter = {
+                "path": ["id"],
+                "operator": "Equal",
+                "valueText": params.get("id", None),
+            }
+            return client.batch.delete_objects(
+                class_name=self.namespace,
+                # Same `where` filter as in the GraphQL API
+                where=where_filter,
+            )
+        else:
+            # Delete all objects
+            return client.batch.delete_objects(
+                class_name=namespace,
+                where={
+                    "path": ["version"],
+                    "operator": "Equal",
+                    "valueText": "1.0",
+                },
+            )
+
+    async def count_memories(self, namespace: str = None, params: dict = None) -> int:
+        """
+        Count memories in a Weaviate database.
+
+        Args:
+            namespace (str, optional): The Weaviate namespace to count memories in. If not provided, uses the default namespace.
+
+        Returns:
+            int: The number of memories in the specified namespace.
+        """
+        if namespace is None:
+            namespace = self.namespace
+
+        client = self.init_weaviate(namespace=namespace)
+
+        try:
+            object_count = client.query.aggregate(namespace).with_meta_count().do()
+            return object_count
+        except Exception as e:
+            logging.info(f"Error counting memories: {str(e)}")
+            # Handle the error or log it
+            return 0
+
+    def update_memories(self, observation, namespace: str, params: dict = None):
+        client = self.init_weaviate(namespace=self.namespace)
+
+        client.data_object.update(
+            data_object={
+                # "text": observation,
+                "user_id": str(self.user_id),
+                "version": params.get("version", None) or "",
+                "agreement_id": params.get("agreement_id", None) or "",
+                "privacy_policy": params.get("privacy_policy", None) or "",
+                "terms_of_service": params.get("terms_of_service", None) or "",
+                "format": params.get("format", None) or "",
+                "schema_version": params.get("schema_version", None) or "",
+                "checksum": params.get("checksum", None) or "",
+                "owner": params.get("owner", None) or "",
+                "license": params.get("license", None) or "",
+                "validity_start": params.get("validity_start", None) or "",
+                "validity_end": params.get("validity_end", None) or ""
+                # **source_metadata,
+            },
+            class_name="Test",
+            uuid=params.get("id", None),
+            consistency_level=weaviate.data.replication.ConsistencyLevel.ALL,  # default QUORUM
+        )
+        return

cognitive_architecture/modules/memory/memory-legacy.py

@@ -0,0 +1,311 @@
+class Memory:
+    def __init__(
+        self,
+        user_id: str = "676",
+        session=None,
+        index_name: str = None,
+        db_type: str = globalConfig.vectordb,
+        namespace: str = None,
+        memory_id: str = None,
+        memory_class=None,
+        job_id: str = None,
+    ) -> None:
+        self.load_environment_variables()
+        self.memory_id = memory_id
+        self.user_id = user_id
+        self.session = session
+        self.index_name = index_name
+        self.db_type = db_type
+        self.namespace = namespace
+        self.memory_instances = []
+        self.memory_class = memory_class
+        self.job_id = job_id
+        # self.memory_class = DynamicBaseMemory(
+        #     "Memory", user_id, str(self.memory_id), index_name, db_type, namespace
+        # )
+
+    def load_environment_variables(self) -> None:
+        self.OPENAI_TEMPERATURE = globalConfig.openai_temperature
+        self.OPENAI_API_KEY = globalConfig.openai_key
+
+    @classmethod
+    async def create_memory(
+        cls,
+        user_id: str,
+        session,
+        job_id: str = None,
+        memory_label: str = None,
+        **kwargs,
+    ):
+        """
+        Class method that acts as a factory method for creating Memory instances.
+        It performs necessary DB checks or updates before instance creation.
+        """
+        existing_user = await cls.check_existing_user(user_id, session)
+        logging.info(f"Existing user: {existing_user}")
+
+        if existing_user:
+            # Handle existing user scenario...
+            memory_id = await cls.check_existing_memory(user_id, memory_label, session)
+            if memory_id is None:
+                memory_id = await cls.handle_new_memory(
+                    user_id=user_id,
+                    session=session,
+                    job_id=job_id,
+                    memory_name=memory_label,
+                )
+            logging.info(
+                f"Existing user {user_id} found in the DB. Memory ID: {memory_id}"
+            )
+        else:
+            # Handle new user scenario...
+            await cls.handle_new_user(user_id, session)
+
+            memory_id = await cls.handle_new_memory(
+                user_id=user_id,
+                session=session,
+                job_id=job_id,
+                memory_name=memory_label,
+            )
+            logging.info(
+                f"New user {user_id} created in the DB. Memory ID: {memory_id}"
+            )
+
+        memory_class = DynamicBaseMemory(
+            memory_label,
+            user_id,
+            str(memory_id),
+            index_name=memory_label,
+            db_type=globalConfig.vectordb,
+            **kwargs,
+        )
+
+        return cls(
+            user_id=user_id,
+            session=session,
+            memory_id=memory_id,
+            job_id=job_id,
+            memory_class=memory_class,
+            **kwargs,
+        )
+
+    async def list_memory_classes(self):
+        """
+        Lists all available memory classes in the memory instance.
+        """
+        # Use a list comprehension to filter attributes that end with '_class'
+        return [attr for attr in dir(self) if attr.endswith("_class")]
+
+    @staticmethod
+    async def check_existing_user(user_id: str, session):
+        """Check if a user exists in the DB and return it."""
+        result = await session.execute(select(User).where(User.id == user_id))
+        return result.scalar_one_or_none()
+
+    @staticmethod
+    async def check_existing_memory(user_id: str, memory_label: str, session):
+        """Check if a user memory exists in the DB and return it. Filters by user and label"""
+        try:
+            result = await session.execute(
+                select(MemoryModel.id)
+                .where(MemoryModel.user_id == user_id)
+                .filter_by(memory_name=memory_label)
+                .order_by(MemoryModel.created_at)
+            )
+            return result.scalar_one_or_none()
+        except Exception as e:
+            logging.error(f"An error occurred: {str(e)}")
+            return None
+
+    @staticmethod
+    async def handle_new_user(user_id: str, session):
+        """
+        Handle new user creation in the database.
+
+        Args:
+            user_id (str): The unique identifier for the new user.
+            session: The database session for the operation.
+
+        Returns:
+            str: A success message or an error message.
+
+        Raises:
+            Exception: If any error occurs during the user creation process.
+        """
+        try:
+            new_user = User(id=user_id)
+            await add_entity(session, new_user)
+            return "User creation successful."
+        except Exception as e:
+            return f"Error creating user: {str(e)}"
+
+    @staticmethod
+    async def handle_new_memory(
+        user_id: str,
+        session,
+        job_id: str = None,
+        memory_name: str = None,
+        memory_category: str = "PUBLIC",
+    ):
+        """
+        Handle new memory creation associated with a user.
+
+        Args:
+            user_id (str): The user's unique identifier.
+            session: The database session for the operation.
+            job_id (str, optional): The identifier of the associated job, if any.
+            memory_name (str, optional): The name of the memory.
+
+        Returns:
+            str: The unique memory ID if successful, or an error message.
+
+        Raises:
+            Exception: If any error occurs during memory creation.
+        """
+        try:
+            memory_id = str(uuid.uuid4())
+            logging.info("Job id %s", job_id)
+            memory = MemoryModel(
+                id=memory_id,
+                user_id=user_id,
+                operation_id=job_id,
+                memory_name=memory_name,
+                memory_category=memory_category,
+                methods_list=str(["Memory", "SemanticMemory", "EpisodicMemory"]),
+                attributes_list=str(
+                    [
+                        "user_id",
+                        "index_name",
+                        "db_type",
+                        "knowledge_source",
+                        "knowledge_type",
+                        "memory_id",
+                        "long_term_memory",
+                        "short_term_memory",
+                        "namespace",
+                    ]
+                ),
+            )
+            await add_entity(session, memory)
+            return memory_id
+        except Exception as e:
+            return f"Error creating memory: {str(e)}"
+
+    async def add_memory_instance(self, memory_class_name: str):
+        """Add a new memory instance to the memory_instances list."""
+        instance = DynamicBaseMemory(
+            memory_class_name,
+            self.user_id,
+            self.memory_id,
+            self.index_name,
+            self.db_type,
+            self.namespace,
+        )
+        print("The following instance was defined", instance)
+        self.memory_instances.append(instance)
+
+    async def query_method(self):
+        methods_list = await self.session.execute(
+            select(MemoryModel.methods_list).where(MemoryModel.id == self.memory_id)
+        )
+        methods_list = methods_list.scalar_one_or_none()
+        return methods_list
+
+    async def manage_memory_attributes(self, existing_user):
+        """Manage memory attributes based on the user existence."""
+        if existing_user:
+            print(f"ID before query: {self.memory_id}, type: {type(self.memory_id)}")
+
+            # attributes_list = await self.session.query(MemoryModel.attributes_list).filter_by(id=self.memory_id[0]).scalar()
+            attributes_list = await self.query_method()
+            logging.info(f"Attributes list: {attributes_list}")
+            if attributes_list is not None:
+                attributes_list = ast.literal_eval(attributes_list)
+                await self.handle_attributes(attributes_list)
+            else:
+                logging.warning("attributes_list is None!")
+        else:
+            attributes_list = [
+                "user_id",
+                "index_name",
+                "db_type",
+                "knowledge_source",
+                "knowledge_type",
+                "memory_id",
+                "long_term_memory",
+                "short_term_memory",
+                "namespace",
+            ]
+            await self.handle_attributes(attributes_list)
+
+    async def handle_attributes(self, attributes_list):
+        """Handle attributes for existing memory instances."""
+        for attr in attributes_list:
+            await self.memory_class.add_attribute(attr)
+
+    async def manage_memory_methods(self, existing_user):
+        """
+        Manage memory methods based on the user existence.
+        """
+        if existing_user:
+            # Fetch existing methods from the database
+            # methods_list = await self.session.query(MemoryModel.methods_list).filter_by(id=self.memory_id).scalar()
+
+            methods_list = await self.session.execute(
+                select(MemoryModel.methods_list).where(
+                    MemoryModel.id == self.memory_id[0]
+                )
+            )
+            methods_list = methods_list.scalar_one_or_none()
+            methods_list = ast.literal_eval(methods_list)
+        else:
+            # Define default methods for a new user
+            methods_list = [
+                "async_create_long_term_memory",
+                "async_init",
+                "add_memories",
+                "fetch_memories",
+                "delete_memories",
+                "async_create_short_term_memory",
+                "_create_buffer_context",
+                "_get_task_list",
+                "_run_main_buffer",
+                "_available_operations",
+                "_provide_feedback",
+            ]
+        # Apply methods to memory instances
+        for class_instance in self.memory_instances:
+            for method in methods_list:
+                class_instance.add_method(method)
+
+    async def dynamic_method_call(
+        self, dynamic_base_memory_instance, method_name: str, *args, **kwargs
+    ):
+        if method_name in dynamic_base_memory_instance.methods:
+            method = getattr(dynamic_base_memory_instance, method_name, None)
+            if method:
+                return await method(*args, **kwargs)
+        raise AttributeError(
+            f"{dynamic_base_memory_instance.name} object has no attribute {method_name}"
+        )
+
+    async def add_dynamic_memory_class(self, class_name: str, namespace: str):
+        logging.info("Here is the memory id %s", self.memory_id[0])
+        new_memory_class = DynamicBaseMemory(
+            class_name,
+            self.user_id,
+            self.memory_id[0],
+            self.index_name,
+            self.db_type,
+            namespace,
+        )
+        setattr(self, f"{class_name.lower()}_class", new_memory_class)
+        return new_memory_class
+
+    async def add_attribute_to_class(self, class_instance, attribute_name: str):
+        # add this to database  for a particular user  and load under memory id
+        await class_instance.add_attribute(attribute_name)
+
+    async def add_method_to_class(self, class_instance, method_name: str):
+        # add this to database for a particular user and load under memory id
+        await class_instance.add_method(method_name)

cognitive_architecture/modules/memory/vector/__init__.py

@@ -0,0 +1 @@
+from .create_vector_memory import create_vector_memory

cognitive_architecture/modules/memory/vector/create_vector_memory.py

@@ -0,0 +1,7 @@
+from cognitive_architecture.infrastructure.databases.vector.qdrant.adapter import CollectionConfig
+from cognitive_architecture.infrastructure.databases.vector.get_vector_database import get_vector_database
+
+async def create_vector_memory(memory_name: str, collection_config: CollectionConfig):
+    vector_db = get_vector_database()
+
+    return await vector_db.create_collection(memory_name, collection_config)

cognitive_architecture/modules/users/memory/__init__.py

@@ -0,0 +1,3 @@
+from .is_existing_memory import is_existing_memory
+from .register_memory_for_user import register_memory_for_user
+from .create_information_points import create_information_points

cognitive_architecture/modules/users/memory/create_information_points.py

@@ -0,0 +1,23 @@
+import uuid
+from typing import List
+from qdrant_client.models import PointStruct
+from cognitive_architecture.infrastructure.databases.vector.get_vector_database import get_vector_database
+from cognitive_architecture.openai_tools import async_get_embedding_with_backoff
+
+async def create_information_points(memory_name: str, payload: List[str]):
+    vector_db = get_vector_database()
+
+    data_points = list()
+    for point in map(create_data_point, payload):
+        data_points.append(await point)
+
+    return await vector_db.create_data_points(memory_name, data_points)
+
+async def create_data_point(data: str) -> PointStruct:
+    return PointStruct(
+        id = str(uuid.uuid4()),
+        vector = await async_get_embedding_with_backoff(data),
+        payload = {
+            "raw": data,
+        }
+    )

cognitive_architecture/modules/users/memory/is_existing_memory.py

@@ -0,0 +1,6 @@
+from cognitive_architecture.infrastructure.databases.relational.get_database import get_database
+
+async def is_existing_memory(memory_name: str):
+    memory = await (get_database().get_memory_by_name(memory_name))
+
+    return memory is not None

cognitive_architecture/modules/users/memory/register_memory_for_user.py

@@ -0,0 +1,4 @@
+from cognitive_architecture.infrastructure.databases.relational.get_database import get_database
+
+def register_memory_for_user(user_id: str, memory_name: str):
+    return get_database().add_memory(user_id, memory_name)

cognitive_architecture/openai_tools.py

@@ -3,24 +3,21 @@ import asyncio
 import random
 import os
 import time
-
+import openai
 
 HOST = os.getenv("OPENAI_API_BASE")
 HOST_TYPE = os.getenv("BACKEND_TYPE")  # default None == ChatCompletion
 
-import openai
-
 if HOST is not None:
     openai.api_base = HOST
 
-
 def retry_with_exponential_backoff(
     func,
     initial_delay: float = 1,
     exponential_base: float = 2,
     jitter: bool = True,
     max_retries: int = 20,
-    errors: tuple = (openai.error.RateLimitError,),
+    errors: tuple = (openai.RateLimitError,),
 ):
     """Retry a function with exponential backoff."""
 
@@ -35,7 +32,7 @@ def retry_with_exponential_backoff(
                 return func(*args, **kwargs)
 
             # Retry on specified errors
-            except errors as e:
+            except errors:
                 # Increment retries
                 num_retries += 1
 
@@ -61,7 +58,7 @@ def retry_with_exponential_backoff(
 @retry_with_exponential_backoff
 def completions_with_backoff(**kwargs):
     # Local model
-    return openai.ChatCompletion.create(**kwargs)
+    return openai.chat.completions.create(**kwargs)
 
 
 def aretry_with_exponential_backoff(
@@ -70,7 +67,7 @@ def aretry_with_exponential_backoff(
     exponential_base: float = 2,
     jitter: bool = True,
     max_retries: int = 20,
-    errors: tuple = (openai.error.RateLimitError,),
+    errors: tuple = (openai.RateLimitError,),
 ):
     """Retry a function with exponential backoff."""
 
@@ -111,13 +108,19 @@ def aretry_with_exponential_backoff(
 
 @aretry_with_exponential_backoff
 async def acompletions_with_backoff(**kwargs):
-    return await openai.ChatCompletion.acreate(**kwargs)
+    return await openai.chat.completions.acreate(**kwargs)
 
 
 @aretry_with_exponential_backoff
 async def acreate_embedding_with_backoff(**kwargs):
     """Wrapper around Embedding.acreate w/ backoff"""
-    return await openai.Embedding.acreate(**kwargs)
+
+    client = openai.AsyncOpenAI(
+        # This is the default and can be omitted
+        api_key=os.environ.get("OPENAI_API_KEY"),
+    )
+
+    return await client.embeddings.create(**kwargs)
 
 
 async def async_get_embedding_with_backoff(text, model="text-embedding-ada-002"):
@@ -125,17 +128,17 @@ async def async_get_embedding_with_backoff(text, model="text-embedding-ada-002")
     It specifies defaults + handles rate-limiting + is async"""
     text = text.replace("\n", " ")
     response = await acreate_embedding_with_backoff(input=[text], model=model)
-    embedding = response["data"][0]["embedding"]
+    embedding = response.data[0].embedding
     return embedding
 
 
 @retry_with_exponential_backoff
 def create_embedding_with_backoff(**kwargs):
-    return openai.Embedding.create(**kwargs)
+    return openai.embeddings.create(**kwargs)
 
 
 def get_embedding_with_backoff(text, model="text-embedding-ada-002"):
     text = text.replace("\n", " ")
     response = create_embedding_with_backoff(input=[text], model=model)
-    embedding = response["data"][0]["embedding"]
+    embedding = response.data[0].embedding
     return embedding

cognitive_architecture/setup_database.py

@@ -5,11 +5,11 @@ logger = logging.getLogger(__name__)
 
 async def main():
     """Runs as a part of startup docker scripts to create the database and tables."""
-    from config import Config
+    from cognitive_architecture.config import Config
     config = Config()
     config.load()
 
-    from database.database_manager import DatabaseManager
+    from cognitive_architecture.database.database_manager import DatabaseManager
 
     db_manager = DatabaseManager()
     database_name = config.db_name

entrypoint.sh

@@ -7,7 +7,7 @@ echo "Environment: $ENVIRONMENT"
 if [ "$ENVIRONMENT" != "local" ]; then
     echo "Running fetch_secret.py"
 
-    python cognitive_architecture/fetch_secret.py
+    PYTHONPATH=. python cognitive_architecture/fetch_secret.py
 
     if [ $? -ne 0 ]; then
         echo "Error: fetch_secret.py failed"
@@ -19,7 +19,7 @@ fi
 
 echo "Creating database..."
 
-python cognitive_architecture/setup_database.py
+PYTHONPATH=. python cognitive_architecture/setup_database.py
 if [ $? -ne 0 ]; then
     echo "Error: setup_database.py failed"
     exit 1

pyproject.toml

@@ -20,50 +20,30 @@ classifiers = [
 python = "^3.10"
 langchain = "^0.0.338"
 
-nltk = "3.8.1"
 openai = "1.3.3"
-pinecone-client = "2.2.2"
 python-dotenv = "1.0.0"
-pyyaml = "6.0"
 fastapi = "0.104.1"
 uvicorn = "0.22.0"
-pexpect = "^4.8.0"
 boto3 = "^1.26.125"
-gptcache = "^0.1.22"
 gunicorn = "^20.1.0"
-tiktoken = "^0.4.0"
-spacy = "^3.5.3"
-python-jose = "^3.3.0"
-pypdf = "^3.12.0"
-fastjsonschema = "^2.18.0"
-marvin = "^1.3.0"
-dlt = { version ="^0.3.8",  extras = ["duckdb"]}
 weaviate-client = "4.4b1"
-python-multipart = "^0.0.6"
-pymupdf = "^1.23.3"
-psycopg2 = "^2.9.8"
-llama-index = "^0.8.39.post2"
-llama-hub = "^0.0.34"
 sqlalchemy = "^2.0.21"
 asyncpg = "^0.28.0"
-dash = "^2.14.0"
-unstructured = {extras = ["pdf"], version = "^0.10.23"}
-sentence-transformers = "2.2.2"
-torch = "2.0.*"
-pdf2image = "^1.16.3"
 instructor = "^0.3.4"
 networkx = "^3.2.1"
 graphviz = "^0.20.1"
-greenlet = "^3.0.1"
 neo4j = "^5.14.1"
-grpcio = "^1.60.0"
 langdetect = "^1.0.9"
 iso639 = "^0.1.4"
 debugpy = "^1.8.0"
 lancedb = "^0.5.5"
 pyarrow = "^15.0.0"
 pylint = "^3.0.3"
-aiosqlite = "^0.19.0"
+qdrant-client = "^1.7.3"
+aiosqlite = "^0.20.0"
+pymupdf = "^1.23.25"
+pandas = "^2.2.1"
+greenlet = "^3.0.3"
 
 [build-system]
 requires = ["poetry-core"]