fix: fixed mulit-round chat memory problem & change the vectordb to

repo_agent/chat_with_repo/chat_with_repo.py

@@ -45,19 +45,46 @@ def parse_documents(self, document):
         self.leaf_nodes = get_leaf_nodes(self.nodes)
         self.nodes_by_id = {node.node_id: node for node in self.nodes}
 
-    def create_index(self):
-        # Create and persist index
+
+    def save_storedb(self):
+        # save the index to chromadb
+        db = chromadb.PersistentClient(path="./chroma_db")
+        chroma_collection = db.get_or_create_collection("quickstart")
+        vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
+
+        storage_context = StorageContext.from_defaults(vector_store=vector_store)
+        storage_context.docstore.add_documents(self.nodes)
+
         self.automerging_index = VectorStoreIndex(
-            self.leaf_nodes, storage_context=self.storage_context, service_context=self.service_context
+           self.leaf_nodes, storage_context=storage_context, service_context=self.service_context
+        )
+
+    def load_storedb(self):    
+        # load the index from chromadb
+        db2 = chromadb.PersistentClient(path="./chroma_db")
+        chroma_collection = db2.get_or_create_collection("quickstart")
+        vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
+        self.automerging_index = VectorStoreIndex.from_vector_store(
+            vector_store,
+            service_context=self.service_context,
         )
-        self.automerging_index.storage_context.persist(persist_dir="./merging_index")
+
+
 
 class ChatbotResponder:
     def __init__(self, automerging_engine):
         self.automerging_engine = automerging_engine
 
+    def format_chat_prompt(self,message, chat_history, instruction):
+        prompt = f"System:{instruction}"
+        for turn in chat_history:
+            user_message, bot_message = turn
+            prompt = f"{prompt}\nUser: {user_message}\nAssistant: {bot_message}"
+        prompt = f"{prompt}\nUser: {message}\nAssistant:"
+        return prompt
+
     def respond(self, message, chat_history, instruction):
-        prompt = message + instruction
+        prompt = self.format_chat_prompt(message, chat_history, instruction)
         chat_history = chat_history + [[message, ""]]
         auto_merging_response = self.automerging_engine.query(prompt)
         bot_message = str(auto_merging_response)
@@ -73,7 +100,8 @@ def respond(self, message, chat_history, instruction):
     indexer = DocumentIndexer("../../Markdown_Docs/", [".md", ".py"])
     document = indexer.load_documents()
     indexer.parse_documents(document)
-    indexer.create_index()
+    indexer.save_storedb()
+    indexer.load_storedb()
     automerging_index = indexer.automerging_index
     automerging_retriever = automerging_index.as_retriever(similarity_top_k=12)
     retriever = AutoMergingRetriever(

repo_agent/chat_with_repo/requirements .txt

@@ -2,85 +2,59 @@ aiofiles==23.2.1
 aiohttp==3.9.1
 aiosignal==1.3.1
 altair==5.2.0
-annotated-types==0.6.0
-anyio==3.7.1
-appnope==0.1.3
 asgiref==3.7.2
-asttokens==2.4.1
 attrs==23.1.0
 backoff==2.2.1
 bcrypt==4.1.2
 beautifulsoup4==4.12.2
 cachetools==5.3.2
-certifi==2023.11.17
 cfgv==3.4.0
-charset-normalizer==3.3.2
 chroma-hnswlib==0.7.3
 chromadb==0.4.21
 click==8.1.7
 colorama==0.4.6
 coloredlogs==15.0.1
-comm==0.1.4
 contourpy==1.2.0
 cycler==0.12.1
 dataclasses-json==0.6.3
-debugpy==1.8.0
-decorator==5.1.1
 deprecated==1.2.14
 distlib==0.3.8
-distro==1.8.0
-exceptiongroup==1.2.0
-executing==2.0.1
 fastapi==0.108.0
 ffmpy==0.3.1
 filelock==3.13.1
 flatbuffers==23.5.26
 fonttools==4.47.0
 frozenlist==1.4.1
 fsspec==2023.12.2
-gitdb==4.0.11
 gitpython==3.1.40
 google-auth==2.25.2
 googleapis-common-protos==1.62.0
 gradio==4.12.0
 gradio-client==0.8.0
 greenlet==3.0.3
 grpcio==1.60.0
-h11==0.14.0
-httpcore==1.0.2
 httptools==0.6.1
-httpx==0.25.1
 huggingface-hub==0.20.1
 humanfriendly==10.0
 identify==2.5.33
-idna==3.4
-importlib-metadata==6.8.0
 importlib-resources==6.1.1
-ipykernel==6.26.0
-ipython==8.17.2
-jedi==0.19.1
 jinja2==3.1.2
 joblib==1.3.2
 jsonschema==4.20.0
 jsonschema-specifications==2023.12.1
-jupyter-client==8.6.0
-jupyter-core==5.5.0
 kiwisolver==1.4.5
 kubernetes==28.1.0
 llama-index==0.9.23
-loguru==0.7.2
 markdown-it-py==3.0.0
 markupsafe==2.1.3
 marshmallow==3.20.1
 matplotlib==3.8.2
-matplotlib-inline==0.1.6
 mdurl==0.1.2
 mmh3==4.0.1
 monotonic==1.6
 mpmath==1.3.0
 multidict==6.0.4
 mypy-extensions==1.0.0
-nest-asyncio==1.5.8
 networkx==3.0
 nltk==3.8.1
 nodeenv==1.8.0
@@ -100,21 +74,12 @@ opentelemetry-semantic-conventions==0.43b0
 opentelemetry-util-http==0.43b0
 orjson==3.9.10
 overrides==7.4.0
-packaging==23.2
 pandas==2.1.4
-parso==0.8.3
-pexpect==4.8.0
-pickleshare==0.7.5
 pillow==9.3.0
-platformdirs==4.0.0
 posthog==3.1.0
 pre-commit==3.6.0
-prompt-toolkit==3.0.41
 protobuf==4.25.1
-psutil==5.9.5
-ptyprocess==0.7.0
 pulsar-client==3.3.0
-pure-eval==0.2.2
 pyasn1==0.5.1
 pyasn1-modules==0.3.0
 pydantic==2.5.3
@@ -124,16 +89,12 @@ pygments==2.17.2
 pyparsing==3.1.1
 pypika==0.48.9
 pyreadline3==3.4.1
-python-dateutil==2.8.2
 python-dotenv==1.0.0
 python-multipart==0.0.6
 pytz==2023.3.post1
 pywin32==306
 pyyaml==6.0.1
-pyzmq==25.1.1
 referencing==0.32.0
-regex==2023.10.3
-requests==2.31.0
 requests-oauthlib==1.3.1
 rich==13.7.0
 rpds-py==0.16.2
@@ -145,26 +106,18 @@ semantic-version==2.10.0
 sentence-transformers==2.2.2
 sentencepiece==0.1.99
 shellingham==1.5.4
-six==1.16.0
-smmap==5.0.1
-sniffio==1.3.0
 soupsieve==2.5
 sqlalchemy==2.0.24
-stack-data==0.6.2
 starlette==0.32.0.post1
 sympy==1.12
 tenacity==8.2.3
 threadpoolctl==3.2.0
-tiktoken==0.5.2
 tokenizers==0.15.0
 tomlkit==0.12.0
 toolz==0.12.0
 torch==2.1.2+cu118
 torchaudio==2.1.2+cu118
 torchvision==0.16.2+cu118
-tornado==6.3.3
-tqdm==4.66.1
-traitlets==5.13.0
 transformers==4.36.2
 typer==0.9.0
 typing-extensions==4.8.0
@@ -174,10 +127,8 @@ urllib3==1.26.18
 uvicorn==0.25.0
 virtualenv==20.25.0
 watchfiles==0.21.0
-wcwidth==0.2.12
 websocket-client==1.7.0
 websockets==11.0.3
-wheel==0.41.3
 win32-setctime==1.1.0
 wrapt==1.16.0
 yarl==1.9.4