File size: 3,789 Bytes
d6fdb17
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
from __future__ import annotations

import dataclasses
import os
from typing import Any, List

import numpy as np
import orjson

from autogpt.llm_utils import create_embedding_with_ada
from autogpt.memory.base import MemoryProviderSingleton

EMBED_DIM = 1536
SAVE_OPTIONS = orjson.OPT_SERIALIZE_NUMPY | orjson.OPT_SERIALIZE_DATACLASS


def create_default_embeddings():
    return np.zeros((0, EMBED_DIM)).astype(np.float32)


@dataclasses.dataclass
class CacheContent:
    texts: List[str] = dataclasses.field(default_factory=list)
    embeddings: np.ndarray = dataclasses.field(
        default_factory=create_default_embeddings
    )


class LocalCache(MemoryProviderSingleton):
    """A class that stores the memory in a local file"""

    def __init__(self, cfg) -> None:
        """Initialize a class instance

        Args:
            cfg: Config object

        Returns:
            None
        """
        self.filename = f"{cfg.memory_index}.json"
        if os.path.exists(self.filename):
            try:
                with open(self.filename, "w+b") as f:
                    file_content = f.read()
                    if not file_content.strip():
                        file_content = b"{}"
                        f.write(file_content)

                    loaded = orjson.loads(file_content)
                    self.data = CacheContent(**loaded)
            except orjson.JSONDecodeError:
                print(f"Error: The file '{self.filename}' is not in JSON format.")
                self.data = CacheContent()
        else:
            print(
                f"Warning: The file '{self.filename}' does not exist. "
                "Local memory would not be saved to a file."
            )
            self.data = CacheContent()

    def add(self, text: str):
        """
        Add text to our list of texts, add embedding as row to our
            embeddings-matrix

        Args:
            text: str

        Returns: None
        """
        if "Command Error:" in text:
            return ""
        self.data.texts.append(text)

        embedding = create_embedding_with_ada(text)

        vector = np.array(embedding).astype(np.float32)
        vector = vector[np.newaxis, :]
        self.data.embeddings = np.concatenate(
            [
                self.data.embeddings,
                vector,
            ],
            axis=0,
        )

        with open(self.filename, "wb") as f:
            out = orjson.dumps(self.data, option=SAVE_OPTIONS)
            f.write(out)
        return text

    def clear(self) -> str:
        """
        Clears the redis server.

        Returns: A message indicating that the memory has been cleared.
        """
        self.data = CacheContent()
        return "Obliviated"

    def get(self, data: str) -> list[Any] | None:
        """
        Gets the data from the memory that is most relevant to the given data.

        Args:
            data: The data to compare to.

        Returns: The most relevant data.
        """
        return self.get_relevant(data, 1)

    def get_relevant(self, text: str, k: int) -> list[Any]:
        """ "
        matrix-vector mult to find score-for-each-row-of-matrix
         get indices for top-k winning scores
         return texts for those indices
        Args:
            text: str
            k: int

        Returns: List[str]
        """
        embedding = create_embedding_with_ada(text)

        scores = np.dot(self.data.embeddings, embedding)

        top_k_indices = np.argsort(scores)[-k:][::-1]

        return [self.data.texts[i] for i in top_k_indices]

    def get_stats(self) -> tuple[int, tuple[int, ...]]:
        """
        Returns: The stats of the local cache.
        """
        return len(self.data.texts), self.data.embeddings.shape